{
  "notice": "bxzxxr MCP archive: a record of what public MCP servers declared when we listed them (we never call their tools). It is data, not a rating: nothing here says a server is safe, secure, verified or trustworthy, and a server can change after we looked. Secrets we detected are redacted; redacted tool lists are withheld and only their hash is shown.",
  "infrastructure": {
    "host": "mindthread.tw",
    "site": "mindthread.tw",
    "addresses": [
      {
        "address": "76.76.21.21",
        "endpoints": 533,
        "shared_infrastructure": true,
        "network": {
          "asn": 16509,
          "name": "AMAZON-02 - Amazon.com, Inc.",
          "prefix": "76.76.21.0/24",
          "country": "US"
        }
      }
    ],
    "addresses_recorded": true,
    "address_history": [
      {
        "addresses": [
          "76.76.21.21"
        ],
        "first_seen": "2026-11-21T16:47:00.989Z",
        "last_seen": "2026-11-21T16:47:00.989Z",
        "checks": 1
      }
    ],
    "hosting": [
      {
        "value": "Vercel",
        "evidence": "Server header \"Vercel\""
      }
    ],
    "software": [],
    "server_info": {
      "name": "mindthread",
      "version": "1.22.3",
      "protocol_version": "2025-06-18"
    },
    "headers": {
      "server": "Vercel",
      "strict-transport-security": "max-age=63072000"
    },
    "auth": null
  },
  "related": {
    "same_address": {
      "total": 532,
      "sample": [
        {
          "id": "139",
          "url": "https://agentblueprint.ai/mcp",
          "server_name": "ai.agentblueprint/agent-blueprint",
          "last_state": "listed",
          "last_checked_at": "2026-11-22T04:34:00.875Z"
        },
        {
          "id": "141",
          "url": "https://agentcv.ai/mcp",
          "server_name": "ai.agentcv/registry",
          "last_state": "listed",
          "last_checked_at": "2026-11-22T04:34:00.875Z"
        },
        {
          "id": "207",
          "url": "https://alcock.ai/api/mcp",
          "server_name": "ai.alcock/arena",
          "last_state": "listed",
          "last_checked_at": "2026-11-22T04:35:02.466Z"
        },
        {
          "id": "249",
          "url": "https://arabickeyboard.ai/mcp",
          "server_name": "ai.arabickeyboard/name-calligraphy",
          "last_state": "listed",
          "last_checked_at": "2026-11-22T04:36:01.093Z"
        },
        {
          "id": "321",
          "url": "https://aviado.ai/api/mcp",
          "server_name": "ai.aviado/health",
          "last_state": "listed",
          "last_checked_at": "2026-11-22T04:38:01.448Z"
        },
        {
          "id": "730",
          "url": "https://droneintelligence.ai/api/mcp",
          "server_name": "ai.droneintelligence/drone-intelligence",
          "last_state": "listed",
          "last_checked_at": "2026-11-22T04:48:01.210Z"
        },
        {
          "id": "903",
          "url": "https://framethrower.ai/api/mcp",
          "server_name": "ai.framethrower/framethrower",
          "last_state": "listed",
          "last_checked_at": "2026-11-22T04:51:02.780Z"
        },
        {
          "id": "910",
          "url": "https://fukushi.ai/api/mcp",
          "server_name": "ai.fukushi/dictionary",
          "last_state": "listed",
          "last_checked_at": "2026-11-22T04:53:00.885Z"
        },
        {
          "id": "1235",
          "url": "https://instabids.ai/api/agent/mcp",
          "server_name": "ai.instabids/instabids",
          "last_state": "listed",
          "last_checked_at": "2026-11-22T04:58:00.936Z"
        },
        {
          "id": "1255",
          "url": "https://jasonlovell.ai/mcp",
          "server_name": "ai.jasonlovell/site",
          "last_state": "listed",
          "last_checked_at": "2026-11-22T04:59:01.356Z"
        },
        {
          "id": "1418",
          "url": "https://listplus.ai/mcp",
          "server_name": "ai.listplus/listplus",
          "last_state": "listed",
          "last_checked_at": "2026-11-22T05:03:00.741Z"
        },
        {
          "id": "1691",
          "url": "https://opencancer.ai/api/mcp",
          "server_name": "ai.opencancer/opencancer",
          "last_state": "listed",
          "last_checked_at": "2026-11-22T06:44:04.042Z"
        },
        {
          "id": "1733",
          "url": "https://overwing.ai/mcp",
          "server_name": "ai.overwing/mcp",
          "last_state": "listed",
          "last_checked_at": "2026-11-22T06:45:02.375Z"
        },
        {
          "id": "1765",
          "url": "https://pechincha.ai/mcp",
          "server_name": "ai.pechincha/deals",
          "last_state": "listed",
          "last_checked_at": "2026-11-22T06:45:03.297Z"
        },
        {
          "id": "2148",
          "url": "https://shurco.ai/mcp",
          "server_name": "ai.shurco/llm-pricing",
          "last_state": "listed",
          "last_checked_at": "2026-11-22T06:49:02.107Z"
        },
        {
          "id": "2448",
          "url": "https://stablenews.ai/mcp/news",
          "server_name": "ai.stablenews/news",
          "last_state": "listed",
          "last_checked_at": "2026-11-22T06:50:04.002Z"
        },
        {
          "id": "2486",
          "url": "https://subpay.ai/mcp",
          "server_name": "ai.subpay/document-reader",
          "last_state": "listed",
          "last_checked_at": "2026-11-22T06:50:05.173Z"
        },
        {
          "id": "2487",
          "url": "https://subpay.ai/invoice/mcp",
          "server_name": "ai.subpay/invoice-reader",
          "last_state": "listed",
          "last_checked_at": "2026-11-22T06:51:08.332Z"
        },
        {
          "id": "2488",
          "url": "https://subpay.ai/find/mcp",
          "server_name": "ai.subpay/tool-finder",
          "last_state": "listed",
          "last_checked_at": "2026-11-22T06:52:02.549Z"
        },
        {
          "id": "2516",
          "url": "https://synthfolk.ai/api/mcp",
          "server_name": "ai.synthfolk/directory",
          "last_state": "listed",
          "last_checked_at": "2026-11-22T06:51:08.804Z"
        }
      ]
    },
    "same_site": {
      "total": 0,
      "sample": []
    },
    "same_tool_list": {
      "total": 0,
      "sample": []
    },
    "same_publisher": {
      "publisher": "io.github.ppcvote",
      "total": 0,
      "sample": []
    },
    "same_repository": {
      "repository_url": "https://github.com/ppcvote/mindthread-mcp",
      "total": 0,
      "sample": []
    },
    "note": "Shared addresses on big platforms (Cloudflare, Vercel and the like) put unrelated servers together; those are marked shared_infrastructure. A match is a pivot, not a link between operators."
  },
  "endpoint": {
    "id": "36043",
    "server_name": "io.github.ppcvote/mindthread",
    "url": "https://mindthread.tw/api/mcp",
    "host": "mindthread.tw",
    "transport": "streamable-http",
    "last_checked_at": "2026-11-21T16:47:00.989Z",
    "last_state": "listed",
    "last_detail": null,
    "consecutive_failures": 0,
    "current_sha": "f2ad8d2bedddd7bb391ee29736f7e1b9dff9acbfd2e7b802c8ee86948ec27188",
    "first_listed_at": "2026-11-21T16:47:00.989Z",
    "created_at": "2026-11-21T11:15:09.765Z",
    "resolved_addresses": [
      "76.76.21.21"
    ]
  },
  "server": {
    "name": "io.github.ppcvote/mindthread",
    "title": "MindThread",
    "description": "Threads scheduler for AI agents: write, schedule and publish posts, review replies, read insights.",
    "version": "0.2.0",
    "registry_status": "active",
    "repository_url": "https://github.com/ppcvote/mindthread-mcp",
    "website_url": "https://mindthread.tw/developers",
    "published_at": "2026-10-26T11:19:55.596Z",
    "updated_at": "2026-10-26T11:19:55.596Z",
    "first_seen": "2026-11-21T11:15:09.213Z"
  },
  "other_endpoints": [],
  "intel": {
    "capabilities": [],
    "evm_addresses": [],
    "chains": [],
    "tokens": [],
    "computed_at": "2026-11-22T15:48:05.531Z"
  },
  "operator": null,
  "needs_sign_in": false,
  "reachability": {
    "window_days": 30,
    "checks": 1,
    "answered": 1,
    "answered_percent": 100,
    "avg_listing_latency_ms": 398,
    "first_check_in_window": "2026-11-21T16:47:00.989Z",
    "consecutive_failures_now": 0,
    "days": [
      {
        "day": "2026-11-21",
        "checks": 1,
        "answered": 1,
        "last_state": "listed"
      }
    ]
  },
  "tool_list": {
    "sha256": "f2ad8d2bedddd7bb391ee29736f7e1b9dff9acbfd2e7b802c8ee86948ec27188",
    "tools": 43,
    "resources": 0,
    "prompts": 0,
    "first_seen": "2026-11-21T16:47:01.389Z",
    "tool_names": [
      "get_me",
      "list_accounts",
      "get_material",
      "build_material",
      "get_account_settings",
      "update_account_settings",
      "list_guardrail_changes",
      "list_account_settings",
      "preview_account_settings",
      "apply_account_settings",
      "revert_account_settings_batch",
      "get_account_settings_batch",
      "generate_posts",
      "publish",
      "schedule_text",
      "list_schedules",
      "cancel_schedule",
      "list_library",
      "add_library",
      "delete_library_item",
      "approve_library_item",
      "update_library_item",
      "get_cloud_patrol",
      "set_cloud_patrol",
      "cloud_patrol_log",
      "cloud_patrol_stats",
      "list_pending_replies",
      "approve_pending_reply",
      "reject_pending_reply",
      "list_events",
      "get_top_posts",
      "save_brand_doc",
      "get_brand_doc",
      "analytics_insights",
      "list_formulas",
      "get_playbook",
      "connect_account_link",
      "disable_this_key",
      "get_my_usage",
      "get_approval",
      "bulk_archive_library",
      "bulk_delete_library",
      "bulk_queue_library"
    ],
    "declared": {
      "tools": [
        {
          "name": "get_me",
          "title": "My plan and key",
          "description": "Returns the current plan, this connection's identity and permissions (each permission is allow, ask or deny), remaining daily calls in this connection's pool, remaining patrol points, and the connected accounts. Applies at the start of a session and whenever a call answered approval_required or insufficient_scope, to see which permission is involved.",
          "inputSchema": {
            "type": "object",
            "required": [],
            "properties": {}
          },
          "annotations": {
            "title": "My plan and key",
            "readOnlyHint": true,
            "openWorldHint": false,
            "idempotentHint": true,
            "destructiveHint": false
          }
        },
        {
          "name": "list_accounts",
          "title": "List connected accounts",
          "description": "Lists the Threads accounts connected to this MindThread member, with the id to pass as account_id to every other tool. Applies whenever an account id is needed and the user named an account by username or description.",
          "inputSchema": {
            "type": "object",
            "required": [],
            "properties": {}
          },
          "annotations": {
            "title": "List connected accounts",
            "readOnlyHint": true,
            "openWorldHint": false,
            "idempotentHint": true,
            "destructiveHint": false
          }
        },
        {
          "name": "get_material",
          "title": "Get brand material",
          "description": "Returns the account's material digest (who the brand is, what it sells, claims, experiences, FAQ, sourced numbers, voice) that every generation path appends to the persona. has_material:false means generation currently runs on the persona alone. Applies before generating when it is unclear whether the account has material.",
          "inputSchema": {
            "type": "object",
            "required": [
              "account_id"
            ],
            "properties": {
              "account_id": {
                "type": "string",
                "description": "Account id"
              }
            }
          },
          "annotations": {
            "title": "Get brand material",
            "readOnlyHint": true,
            "openWorldHint": false,
            "idempotentHint": true,
            "destructiveHint": false
          }
        },
        {
          "name": "build_material",
          "title": "Build brand material",
          "description": "Builds or rebuilds the account's material digest from up to 8 https pages of the brand's own website, optional notes with real cases and FAQs (up to 6,000 characters), and the account's top posts. Replaces the previous digest. Counts as one AI generation. dry:true returns a preview without saving. Applies once per account before the first generation, and again when the website changes.",
          "inputSchema": {
            "type": "object",
            "required": [
              "account_id"
            ],
            "properties": {
              "dry": {
                "type": "boolean",
                "description": "Preview only"
              },
              "urls": {
                "type": "array",
                "items": {
                  "type": "string"
                },
                "description": "Up to 8 https:// pages"
              },
              "notes": {
                "type": "string",
                "description": "Real experiences, cases, FAQs (≤6000 chars)"
              },
              "account_id": {
                "type": "string",
                "description": "Account id"
              }
            }
          },
          "annotations": {
            "title": "Build brand material",
            "readOnlyHint": false,
            "openWorldHint": true,
            "idempotentHint": false,
            "destructiveHint": true
          }
        },
        {
          "name": "get_account_settings",
          "title": "Get account settings",
          "description": "Returns one account's persona, schedule_times, review_before_publish, auto_reply_enabled, auto_thread, content_rules, and the guardrails block: etag (used as if_match on update), last_change, pending loosening approvals, and which paths the rules are enforced on. Applies before any settings change, because content_rules is replaced as a whole on update.",
          "inputSchema": {
            "type": "object",
            "required": [
              "account_id"
            ],
            "properties": {
              "account_id": {
                "type": "string",
                "description": "Account id"
              }
            }
          },
          "annotations": {
            "title": "Get account settings",
            "readOnlyHint": true,
            "openWorldHint": false,
            "idempotentHint": true,
            "destructiveHint": false
          }
        },
        {
          "name": "update_account_settings",
          "title": "Update account settings",
          "description": "Changes an account's persona (up to 4,000 characters), schedule_times (comma-separated HH:MM in the account time zone, up to 8), review_before_publish, auto_reply_enabled, auto_thread, auto_link_to_comment, enabled, random posting (random_schedule, random_per_day, random_window, and random_exclude: up to 3 ranges such as 17:00-18:00 that random times skip), and content_rules (max_chars, min_chars, forbid_cta, forbid_hashtags, banned_phrases, facts as the only numbers the AI may use, forbid_causal_claims, judge_claims, one_fact_per_post, mention_limits, enforce warn or block). Only the fields sent are changed, except content_rules, which is replaced as a whole. if_match (the guardrails etag) makes a concurrent change answer 412 instead of overwriting; reason (up to 200 characters) is stored in the revision; dry_run:true previews whether the change would apply, ask the owner or be denied, without writing anything. A change that loosens a guardrail may wait for the owner's confirmation. Applies when the user asks to change voice, posting times, review mode, auto-reply or content rules.",
          "inputSchema": {
            "type": "object",
            "required": [
              "account_id"
            ],
            "properties": {
              "reason": {
                "type": "string",
                "description": "Why, up to 200 chars (optional, 1.9.0)"
              },
              "dry_run": {
                "type": "boolean",
                "description": "true = preview only (1.9.0); at most 10 a minute per key"
              },
              "enabled": {
                "type": "boolean",
                "description": "Master switch"
              },
              "persona": {
                "type": "string",
                "description": "Brand persona, up to 4000 chars"
              },
              "if_match": {
                "type": "string",
                "description": "guardrails.etag from get_account_settings (optional, 1.9.0)"
              },
              "account_id": {
                "type": "string",
                "description": "Account id"
              },
              "auto_thread": {
                "type": "boolean",
                "description": "Auto-split >500 chars"
              },
              "content_rules": {
                "type": "object",
                "description": "Structured rules: max_chars, min_chars, forbid_cta, forbid_hashtags, banned_phrases[], facts[] (allowed numbers as plain sentences), forbid_causal_claims, judge_claims (model reviews for unsupported conclusions), one_fact_per_post, mention_limits [{phrase,max}], enforce (warn|block). null clears."
              },
              "random_window": {
                "type": "string",
                "description": "HH:MM-HH:MM, start before end; 00:00-23:59 = whole day"
              },
              "random_exclude": {
                "type": "array",
                "items": {
                  "type": "string"
                },
                "description": "Up to 3 HH:MM-HH:MM ranges random times skip, no midnight crossing, no overlap; [] clears"
              },
              "random_per_day": {
                "type": "integer",
                "description": "Random posts per day, 1-30"
              },
              "schedule_times": {
                "type": "string",
                "description": "Comma-separated HH:MM, up to 8"
              },
              "random_schedule": {
                "type": "boolean",
                "description": "Random times every day instead of schedule_times (1.21.0)"
              },
              "auto_reply_enabled": {
                "type": "boolean",
                "description": "AI replies to comments on own posts"
              },
              "auto_link_to_comment": {
                "type": "boolean",
                "description": "Links go to first comment"
              },
              "review_before_publish": {
                "type": "boolean",
                "description": "AI drafts wait for approval"
              }
            }
          },
          "annotations": {
            "title": "Update account settings",
            "readOnlyHint": false,
            "openWorldHint": false,
            "idempotentHint": true,
            "destructiveHint": true
          }
        },
        {
          "name": "list_guardrail_changes",
          "title": "Guardrail change history",
          "description": "Lists an account's guardrail revisions, newest first (limit 1 to 50, default 20; before for the next page). Each revision has source (api, approval, rollback, system), actor, changed_fields, loosened, tightened, before, after and restore_body (an update_account_settings body that puts the earlier values back). Applies when the user asks what changed, who changed it, or wants to restore an earlier rule set.",
          "inputSchema": {
            "type": "object",
            "required": [
              "account_id"
            ],
            "properties": {
              "limit": {
                "type": "integer",
                "description": "1-50 (default 20)"
              },
              "before": {
                "type": "string",
                "description": "next_before from the previous page"
              },
              "account_id": {
                "type": "string",
                "description": "Account id"
              }
            }
          },
          "annotations": {
            "title": "Guardrail change history",
            "readOnlyHint": true,
            "openWorldHint": false,
            "idempotentHint": true,
            "destructiveHint": false
          }
        },
        {
          "name": "list_account_settings",
          "title": "List account settings (bulk)",
          "description": "Lists every connected Threads account of this member with the settings of the MindThread bulk settings sheet (run mode, auto-posting, review before publish, posting times, audience time zone, random schedule, library recycling, cold start, content language, AI quality, auto-reply and reply limits) and status chips (expired authorization, repeated publish failures, skipped nightly refill). Up to 100 accounts per page, with limit and cursor for more. columns describes each setting (type, allowed values, which ones are sensitive) and rules_url links to the field rules page. Applies when the user wants to see or compare settings across many accounts. 繁中：列出所有帳號的總表設定與狀態標籤。",
          "inputSchema": {
            "type": "object",
            "required": [],
            "properties": {
              "limit": {
                "type": "integer",
                "description": "1-100, default 100"
              },
              "cursor": {
                "type": "string",
                "description": "next_cursor from the previous page"
              }
            }
          },
          "annotations": {
            "title": "List account settings (bulk)",
            "readOnlyHint": true,
            "openWorldHint": false,
            "idempotentHint": true,
            "destructiveHint": false
          }
        },
        {
          "name": "preview_account_settings",
          "title": "Preview bulk settings changes",
          "description": "Shows what a batch of settings changes would do and writes nothing: for each account and cell the current value and the new value, warnings (for example no posting time left), and row errors (an account that is not this member's, an unknown column, a value outside the allowed range, a cell changed since it was read). Takes changes as a list of { account_id, set, base } or csv in the same format as the website download. The result carries apply_changes and a preview_id valid for 15 minutes, which apply_account_settings takes as they are. Applies before any bulk change, so the user sees the exact cells first. 繁中：預覽批次變更，逐格列出舊值與新值，什麼都不寫。",
          "inputSchema": {
            "type": "object",
            "required": [],
            "properties": {
              "csv": {
                "type": "string",
                "description": "Instead of changes: a CSV in the website download format (UTF-8), up to 1 MB"
              },
              "changes": {
                "type": "array",
                "items": {
                  "type": "object",
                  "required": [
                    "account_id",
                    "set"
                  ],
                  "properties": {
                    "set": {
                      "type": "object",
                      "description": "column key → new value"
                    },
                    "base": {
                      "type": "object",
                      "description": "column key → value you read; a cell changed since then is refused instead of overwritten"
                    },
                    "account_id": {
                      "type": "string"
                    }
                  }
                },
                "maxItems": 100,
                "description": "Up to 100 entries: { account_id, set: { column: value }, base?: { column: value you saw } }. Columns and allowed values: list_account_settings columns, or https://mindthread.tw/accounts/bulk/rules"
              }
            }
          },
          "annotations": {
            "title": "Preview bulk settings changes",
            "readOnlyHint": true,
            "openWorldHint": false,
            "idempotentHint": true,
            "destructiveHint": false
          }
        },
        {
          "name": "apply_account_settings",
          "title": "Apply bulk settings changes",
          "description": "Writes a batch of settings changes to up to 100 accounts, each account in its own transaction, and returns a per-row result (ok, unchanged, or failed with the reason) and a batch_id that revert_account_settings_batch can undo within 24 hours. idempotency_key is required: a retried request with the same key returns the first result instead of writing twice. Changes to run mode, auto-posting or review before publish affect posting right away and need confirm_sensitive:true, and that confirmation may wait for the owner's approval. Nothing is written without a preview: from a Claude or ChatGPT connection the preview_id from preview_account_settings is required, and a preview_id that does not match the changes is refused. Applies after the user has seen the preview and confirmed it. 繁中：套用批次變更（每帳號一個交易、24 小時內可復原），敏感欄位要 confirm_sensitive，目錄連線一定要先預覽並帶 preview_id。",
          "inputSchema": {
            "type": "object",
            "required": [
              "idempotency_key"
            ],
            "properties": {
              "csv": {
                "type": "string",
                "description": "Instead of changes: a CSV in the website download format (UTF-8)"
              },
              "reason": {
                "type": "string",
                "description": "Optional note stored with the batch, up to 200 characters"
              },
              "changes": {
                "type": "array",
                "items": {
                  "type": "object",
                  "required": [
                    "account_id",
                    "set"
                  ],
                  "properties": {
                    "set": {
                      "type": "object",
                      "description": "column key → new value"
                    },
                    "base": {
                      "type": "object",
                      "description": "column key → value you read; a cell changed since then is refused instead of overwritten"
                    },
                    "account_id": {
                      "type": "string"
                    }
                  }
                },
                "maxItems": 100,
                "description": "Up to 100 entries: { account_id, set: { column: value }, base?: { column: value you saw } }. Columns and allowed values: list_account_settings columns, or https://mindthread.tw/accounts/bulk/rules"
              },
              "preview_id": {
                "type": "string",
                "description": "preview_id from preview_account_settings (required from Claude and ChatGPT connections)"
              },
              "idempotency_key": {
                "type": "string",
                "description": "8-200 characters; reuse the same key when retrying the same request"
              },
              "confirm_sensitive": {
                "type": "boolean",
                "description": "true when the batch changes run mode, auto-posting or review before publish"
              }
            }
          },
          "annotations": {
            "title": "Apply bulk settings changes",
            "readOnlyHint": false,
            "openWorldHint": false,
            "idempotentHint": true,
            "destructiveHint": true
          }
        },
        {
          "name": "revert_account_settings_batch",
          "title": "Undo a bulk settings batch",
          "description": "Restores the values that one batch changed, within 24 hours of the batch. Accounts changed again after the batch are skipped and listed with the reason, so a later edit is never overwritten. A batch can be reverted once. Applies when the user wants to undo a bulk change. 繁中：24 小時內復原一批變更，之後又被改過的帳號會跳過。",
          "inputSchema": {
            "type": "object",
            "required": [
              "batch_id"
            ],
            "properties": {
              "batch_id": {
                "type": "string",
                "description": "batch_id from apply_account_settings"
              }
            }
          },
          "annotations": {
            "title": "Undo a bulk settings batch",
            "readOnlyHint": false,
            "openWorldHint": false,
            "idempotentHint": false,
            "destructiveHint": true
          }
        },
        {
          "name": "get_account_settings_batch",
          "title": "Get a bulk settings batch",
          "description": "Returns one batch by batch_id: when it was sent and from where (website, API or MCP), counts, whether it can still be reverted, and each row's result with the failure reason. Applies after apply_account_settings, or when the user asks what a bulk change did. 繁中：查一批變更的逐列結果。",
          "inputSchema": {
            "type": "object",
            "required": [
              "batch_id"
            ],
            "properties": {
              "batch_id": {
                "type": "string",
                "description": "batch_id from apply_account_settings"
              }
            }
          },
          "annotations": {
            "title": "Get a bulk settings batch",
            "readOnlyHint": true,
            "openWorldHint": false,
            "idempotentHint": true,
            "destructiveHint": false
          }
        },
        {
          "name": "generate_posts",
          "title": "Generate post drafts",
          "description": "Generates 1 to 5 post drafts about a topic using a content formula (auto, or an id from list_formulas), the account persona and material, optional reference context (up to 8,000 characters) and a quality level (fast, standard, premium). Nothing is published or queued. The result carries rule_violations against the account's content_rules. Applies when the user wants drafts to read, edit or choose from.",
          "inputSchema": {
            "type": "object",
            "required": [
              "topic"
            ],
            "properties": {
              "count": {
                "type": "integer",
                "description": "1-5"
              },
              "topic": {
                "type": "string",
                "description": "What to write about"
              },
              "context": {
                "type": "string",
                "description": "Reference material up to 8000 chars"
              },
              "formula": {
                "type": "string",
                "description": "auto or a formula id from list_formulas"
              },
              "quality": {
                "type": "string",
                "description": "fast | standard | premium"
              },
              "account_id": {
                "type": "string",
                "description": "Persona source"
              }
            }
          },
          "annotations": {
            "title": "Generate post drafts",
            "readOnlyHint": false,
            "openWorldHint": false,
            "idempotentHint": false,
            "destructiveHint": false
          }
        },
        {
          "name": "publish",
          "title": "Publish or schedule a post",
          "description": "Publishes a post to Threads now (publish_now:true) or at publish_at (ISO 8601 with offset). Takes text, one public https image (media_urls with 1 url), a carousel (2 to 10 urls) or a video_url. Text over 500 characters is split into a thread. Publishing now or within 30 minutes uses the publish-now permission; a post 30 minutes or more ahead uses the schedule permission. Either may wait for the owner's confirmation when that permission is set to ask on this connection. publish_at takes any offset and comes back in UTC (Z); a publish_at more than 60 seconds in the past returns 400 publish_at_in_past with server_now. The same account needs at least 10 minutes between scheduled posts: a closer publish_at returns 400 schedule_too_dense with nearest_publish_at. idempotency_key makes a retried request return the first result instead of posting twice. Applies when the user has final text and wants it on Threads.",
          "inputSchema": {
            "type": "object",
            "required": [
              "account_id"
            ],
            "properties": {
              "text": {
                "type": "string",
                "description": "Post text / caption"
              },
              "video_url": {
                "type": "string",
                "description": "Public https MP4/MOV"
              },
              "account_id": {
                "type": "string",
                "description": "Account id"
              },
              "media_urls": {
                "type": "array",
                "items": {
                  "type": "string"
                },
                "description": "Public https image URLs (1 = image, 2-10 = carousel)"
              },
              "publish_at": {
                "type": "string",
                "description": "ISO 8601 if not publish_now"
              },
              "publish_now": {
                "type": "boolean",
                "description": "Publish immediately"
              },
              "idempotency_key": {
                "type": "string",
                "description": "Optional"
              }
            }
          },
          "annotations": {
            "title": "Publish or schedule a post",
            "readOnlyHint": false,
            "openWorldHint": true,
            "idempotentHint": false,
            "destructiveHint": true
          }
        },
        {
          "name": "schedule_text",
          "title": "Schedule a text post",
          "description": "Schedules an existing text (up to 500 characters) at publish_at, or at the next best slot with auto_optimize_time:true (the two are mutually exclusive). publish_at takes any offset and comes back in UTC (Z); a publish_at more than 60 seconds in the past returns 400 publish_at_in_past with server_now. The same account needs at least 10 minutes between scheduled posts: a closer publish_at returns 400 schedule_too_dense with nearest_publish_at. Checked against the account's content_rules: with enforce:block a violation returns 422 and nothing is scheduled; the post is checked again right before it publishes. Applies for text-only posts with a specific time or when the user wants the system to pick the time.",
          "inputSchema": {
            "type": "object",
            "required": [
              "account_id",
              "text"
            ],
            "properties": {
              "text": {
                "type": "string",
                "description": "Text"
              },
              "account_id": {
                "type": "string",
                "description": "Account id"
              },
              "publish_at": {
                "type": "string",
                "description": "ISO 8601 with offset (canonical time field)"
              },
              "schedule_at": {
                "type": "string",
                "description": "Deprecated alias of publish_at"
              },
              "auto_optimize_time": {
                "type": "boolean",
                "description": "Next best slot (mutually exclusive with publish_at)"
              }
            }
          },
          "annotations": {
            "title": "Schedule a text post",
            "readOnlyHint": false,
            "openWorldHint": true,
            "idempotentHint": false,
            "destructiveHint": true
          }
        },
        {
          "name": "list_schedules",
          "title": "List scheduled posts",
          "description": "Lists scheduled posts, optionally filtered by account_id, with status, publish_at, and held_reason when a post was held (for example content_rules_violated or publish_result_unknown). Applies when the user asks what is coming up or why a post did not go out.",
          "inputSchema": {
            "type": "object",
            "required": [],
            "properties": {
              "account_id": {
                "type": "string",
                "description": "Filter by account"
              }
            }
          },
          "annotations": {
            "title": "List scheduled posts",
            "readOnlyHint": true,
            "openWorldHint": false,
            "idempotentHint": true,
            "destructiveHint": false
          }
        },
        {
          "name": "cancel_schedule",
          "title": "Cancel a scheduled post",
          "description": "Cancels a scheduled post by id. A post that is being published right now answers 409 publishing_in_progress. A cancelled post drops out of list_schedules. There is no way to move a scheduled time: cancel it and schedule again. Applies when the user no longer wants a scheduled post to go out.",
          "inputSchema": {
            "type": "object",
            "required": [
              "id"
            ],
            "properties": {
              "id": {
                "type": "string",
                "description": "Post id"
              }
            }
          },
          "annotations": {
            "title": "Cancel a scheduled post",
            "readOnlyHint": false,
            "openWorldHint": false,
            "idempotentHint": true,
            "destructiveHint": true
          }
        },
        {
          "name": "list_library",
          "title": "List library items",
          "description": "Lists an account's library items by status (queued, draft, published, failed; limit up to 200). Queued items publish automatically at the account's schedule_times; the result shows each item's position and next_publish_at. A draft with held_reason publish_result_unknown and reclaimed:true may already be on Threads. Applies when the user asks what is queued, what is waiting as a draft, or what failed.",
          "inputSchema": {
            "type": "object",
            "required": [
              "account_id"
            ],
            "properties": {
              "limit": {
                "type": "integer",
                "description": "max 200"
              },
              "status": {
                "type": "string",
                "description": "queued | draft | published | failed"
              },
              "account_id": {
                "type": "string",
                "description": "Account id"
              }
            }
          },
          "annotations": {
            "title": "List library items",
            "readOnlyHint": true,
            "openWorldHint": false,
            "idempotentHint": true,
            "destructiveHint": false
          }
        },
        {
          "name": "add_library",
          "title": "Add library items",
          "description": "Adds up to 20 items (text, optional public https images) to an account's library as queued (default; they publish automatically at schedule_times) or draft (they wait). Each text is checked against the account's content_rules. Applies after drafts are approved by the user and should enter the daily publishing queue, or should be parked as drafts.",
          "inputSchema": {
            "type": "object",
            "required": [
              "account_id",
              "items"
            ],
            "properties": {
              "items": {
                "type": "array",
                "items": {
                  "type": "object",
                  "required": [],
                  "properties": {
                    "text": {
                      "type": "string",
                      "description": "Text"
                    },
                    "media_urls": {
                      "type": "array",
                      "items": {
                        "type": "string"
                      },
                      "description": "Public https images"
                    }
                  }
                },
                "description": "Items"
              },
              "status": {
                "type": "string",
                "description": "queued (default) | draft"
              },
              "account_id": {
                "type": "string",
                "description": "Account id"
              }
            }
          },
          "annotations": {
            "title": "Add library items",
            "readOnlyHint": false,
            "openWorldHint": true,
            "idempotentHint": false,
            "destructiveHint": true
          }
        },
        {
          "name": "delete_library_item",
          "title": "Delete a library item",
          "description": "Permanently deletes one queued, draft or archived library item by id. Applies when the user explicitly wants an item gone rather than archived.",
          "inputSchema": {
            "type": "object",
            "required": [
              "id"
            ],
            "properties": {
              "id": {
                "type": "string",
                "description": "Item id"
              }
            }
          },
          "annotations": {
            "title": "Delete a library item",
            "readOnlyHint": false,
            "openWorldHint": false,
            "idempotentHint": true,
            "destructiveHint": true
          }
        },
        {
          "name": "approve_library_item",
          "title": "Approve a draft into the queue",
          "description": "Moves one draft into the publishing queue by id. A draft whose held_reason is publish_result_unknown answers 409 publish_result_unknown because it may already be on Threads; an item being published answers 409 publishing_in_progress. Applies when the user approves a single draft.",
          "inputSchema": {
            "type": "object",
            "required": [
              "id"
            ],
            "properties": {
              "id": {
                "type": "string",
                "description": "Item id"
              }
            }
          },
          "annotations": {
            "title": "Approve a draft into the queue",
            "readOnlyHint": false,
            "openWorldHint": true,
            "idempotentHint": true,
            "destructiveHint": true
          }
        },
        {
          "name": "update_library_item",
          "title": "Update a library item",
          "description": "Changes one library item by id: status (archived, draft, queued), text (checked against content_rules), or its place in the queue (position first or last, or an explicit order). 409 publishing_in_progress means it is being published; 409 publish_result_unknown means it may already be on Threads; 409 status_changed means it changed since it was read. Applies when the user wants to edit, reorder, archive or restore one item.",
          "inputSchema": {
            "type": "object",
            "required": [
              "id"
            ],
            "properties": {
              "id": {
                "type": "string",
                "description": "Item id"
              },
              "text": {
                "type": "string",
                "description": "New text"
              },
              "order": {
                "type": "integer",
                "description": "Explicit order"
              },
              "status": {
                "type": "string",
                "description": "archived | draft | queued"
              },
              "position": {
                "type": "string",
                "description": "first | last"
              }
            }
          },
          "annotations": {
            "title": "Update a library item",
            "readOnlyHint": false,
            "openWorldHint": true,
            "idempotentHint": true,
            "destructiveHint": true
          }
        },
        {
          "name": "get_cloud_patrol",
          "title": "Get cloud patrol settings",
          "description": "Returns an account's cloud patrol configuration and status: keywords, daily cap, replies sent today, review_before_reply, last scan time. Cloud patrol searches Threads every 15 minutes and replies to relevant fresh posts through the official API. Applies before changing patrol settings or when the user asks whether patrol is on.",
          "inputSchema": {
            "type": "object",
            "required": [
              "account_id"
            ],
            "properties": {
              "account_id": {
                "type": "string",
                "description": "Account id"
              }
            }
          },
          "annotations": {
            "title": "Get cloud patrol settings",
            "readOnlyHint": true,
            "openWorldHint": false,
            "idempotentHint": true,
            "destructiveHint": false
          }
        },
        {
          "name": "set_cloud_patrol",
          "title": "Set cloud patrol",
          "description": "Creates or updates an account's cloud patrol: keywords (1 to 10; a \"#tag\" entry searches a topic tag), reply persona, daily_cap (1 to 50 on free and trial, up to 80 on paid plans, up to 150 with a haixun add-on), enabled, and review_before_reply. When patrol is on, the account replies to relevant fresh Threads posts through the official API every 15 minutes, one patrol point per delivered reply; with review_before_reply:true every drafted reply waits in list_pending_replies instead of going out. Turning patrol on, or changing a patrol that is already on, needs the patrol permission, which is not granted to directory connections: the owner does it in MindThread. Applies when the user wants to stop patrol or tune its keywords, persona and cap while it is off.",
          "inputSchema": {
            "type": "object",
            "required": [
              "account_id"
            ],
            "properties": {
              "mode": {
                "enum": [
                  "reply",
                  "discover"
                ],
                "type": "string",
                "description": "\"reply\" (default): AI drafts and posts replies. \"discover\": only list matching posts for you to read; no AI, nothing posted"
              },
              "enabled": {
                "type": "boolean",
                "description": "Start / stop"
              },
              "persona": {
                "type": "string",
                "description": "Reply persona"
              },
              "keywords": {
                "type": "array",
                "items": {
                  "type": "string"
                },
                "description": "1-10 entries; \"#tag\" = topic-tag search"
              },
              "daily_cap": {
                "type": "integer",
                "description": "reply: 1-50 free/trial, up to 80 paid, up to 150 with add-on; discover: 1 to plan daily haixun points (default)"
              },
              "reply_max": {
                "type": "integer",
                "maximum": 200,
                "minimum": 20,
                "description": "Max characters per reply, 20-200, or null for the language default. A persona asking for a length is followed up to this limit"
              },
              "account_id": {
                "type": "string",
                "description": "Account id"
              },
              "reply_mode": {
                "enum": [
                  "ai",
                  "rotate",
                  "consume"
                ],
                "type": "string",
                "description": "\"ai\" (default): AI writes each reply in the persona. \"rotate\": post your fixed replies in order, word for word, starting over after the last (AI still decides which posts to reply to). \"consume\": like rotate but each reply is used once; patrol stops for the account when all are used. Fixed replies come from rotate_replies or the imported library (import_cloud_patrol_replies)"
              },
              "rotate_replies": {
                "type": "array",
                "items": {
                  "type": "string"
                },
                "description": "1-10 fixed replies used in order when reply_mode is \"rotate\"; each within the account reply length limit; changing them restarts from the first"
              },
              "review_before_reply": {
                "type": "boolean",
                "description": "Hold drafts for approval"
              }
            }
          },
          "annotations": {
            "title": "Set cloud patrol",
            "readOnlyHint": false,
            "openWorldHint": true,
            "idempotentHint": true,
            "destructiveHint": true
          }
        },
        {
          "name": "cloud_patrol_log",
          "title": "Cloud patrol reply log",
          "description": "Lists replies sent by cloud patrol for an account in the last 1 to 7 days, with the target post and the reply text. Applies when the user wants to read what was actually said.",
          "inputSchema": {
            "type": "object",
            "required": [
              "account_id"
            ],
            "properties": {
              "days": {
                "type": "integer",
                "description": "1-7"
              },
              "account_id": {
                "type": "string",
                "description": "Account id"
              }
            }
          },
          "annotations": {
            "title": "Cloud patrol reply log",
            "readOnlyHint": true,
            "openWorldHint": false,
            "idempotentHint": true,
            "destructiveHint": false
          }
        },
        {
          "name": "cloud_patrol_stats",
          "title": "Cloud patrol results",
          "description": "Returns views and likes earned by cloud patrol replies for an account over 1 to 14 days, with the top replies. Applies when the user asks whether patrol is working or which keywords perform.",
          "inputSchema": {
            "type": "object",
            "required": [
              "account_id"
            ],
            "properties": {
              "days": {
                "type": "integer",
                "description": "1-14"
              },
              "account_id": {
                "type": "string",
                "description": "Account id"
              }
            }
          },
          "annotations": {
            "title": "Cloud patrol results",
            "readOnlyHint": true,
            "openWorldHint": false,
            "idempotentHint": true,
            "destructiveHint": false
          }
        },
        {
          "name": "list_pending_replies",
          "title": "List drafted replies awaiting review",
          "description": "Lists cloud patrol reply drafts for an account by status (pending by default; also sent, rejected, expired). Each pending draft has the target post, the drafted reply and an expiry 24 hours after it was drafted. Each call counts against the daily quota even when nothing is pending. Applies when review_before_reply is on and the user wants to decide what goes out.",
          "inputSchema": {
            "type": "object",
            "required": [
              "account_id"
            ],
            "properties": {
              "status": {
                "type": "string",
                "description": "pending (default) | sent | rejected | expired"
              },
              "account_id": {
                "type": "string",
                "description": "Account id"
              }
            }
          },
          "annotations": {
            "title": "List drafted replies awaiting review",
            "readOnlyHint": true,
            "openWorldHint": false,
            "idempotentHint": true,
            "destructiveHint": false
          }
        },
        {
          "name": "approve_pending_reply",
          "title": "Send a drafted reply",
          "description": "Approves one drafted cloud patrol reply by id and sends it to Threads now, optionally with an edited reply text that passes the same quality gates as generated text. May wait for the owner's confirmation. Applies when the user has read a pending draft and wants it posted.",
          "inputSchema": {
            "type": "object",
            "required": [
              "id"
            ],
            "properties": {
              "id": {
                "type": "string",
                "description": "Pending id"
              },
              "reply": {
                "type": "string",
                "description": "Optional edited reply"
              }
            }
          },
          "annotations": {
            "title": "Send a drafted reply",
            "readOnlyHint": false,
            "openWorldHint": true,
            "idempotentHint": false,
            "destructiveHint": true
          }
        },
        {
          "name": "reject_pending_reply",
          "title": "Reject a drafted reply",
          "description": "Rejects one drafted cloud patrol reply by id with an optional note. It is never sent and the same post is not proposed again. Applies when the user does not want a drafted reply to go out.",
          "inputSchema": {
            "type": "object",
            "required": [
              "id"
            ],
            "properties": {
              "id": {
                "type": "string",
                "description": "Pending id"
              },
              "reason": {
                "type": "string",
                "description": "Optional note"
              }
            }
          },
          "annotations": {
            "title": "Reject a drafted reply",
            "readOnlyHint": false,
            "openWorldHint": false,
            "idempotentHint": true,
            "destructiveHint": true
          }
        },
        {
          "name": "list_events",
          "title": "List recent events",
          "description": "Returns the member's event feed for the last 7 days, newest first (limit 1 to 200): post.published, post.failed, reply.sent, patrol.reply, patrol.pending, token.expiring, usage.threshold, approval.decided. since (ISO 8601) returns only newer events; types filters by name. Each call counts against the daily quota even when nothing is new, so poll sparingly (every 30 minutes on the free plan). Applies when the user asks what happened recently or whether a post went out.",
          "inputSchema": {
            "type": "object",
            "required": [],
            "properties": {
              "limit": {
                "type": "integer",
                "description": "1-200"
              },
              "since": {
                "type": "string",
                "description": "ISO 8601"
              },
              "types": {
                "type": "string",
                "description": "Comma-separated event names"
              }
            }
          },
          "annotations": {
            "title": "List recent events",
            "readOnlyHint": true,
            "openWorldHint": false,
            "idempotentHint": true,
            "destructiveHint": false
          }
        },
        {
          "name": "get_top_posts",
          "title": "Get top posts",
          "description": "Returns the best posts of a Threads account this member connected, ranked by engagement (likes + replies + reposts + quotes) or by views, likes, replies, reposts or quotes, with each post's text and metrics from MindThread's insights cache. Other people's accounts cannot be read: the Threads API only returns insights for the authorized user's own posts. Applies when the user wants to study what worked on their own account, for example to write a content document. 繁中：只讀會員自己連結的帳號，依互動排序取表現最好的貼文。",
          "inputSchema": {
            "type": "object",
            "required": [
              "account_id"
            ],
            "properties": {
              "days": {
                "type": "integer",
                "description": "Only posts from the last N days, 1-365 (omit = all fetched posts)"
              },
              "limit": {
                "type": "integer",
                "description": "1-50, default 20"
              },
              "metric": {
                "enum": [
                  "engagement",
                  "views",
                  "likes",
                  "replies",
                  "reposts",
                  "quotes"
                ],
                "type": "string",
                "description": "Ranking metric, default engagement"
              },
              "account_id": {
                "type": "string",
                "description": "Account id from list_accounts (only accounts this member connected)"
              }
            }
          },
          "annotations": {
            "title": "Get top posts",
            "readOnlyHint": true,
            "openWorldHint": false,
            "idempotentHint": true,
            "destructiveHint": false
          }
        },
        {
          "name": "save_brand_doc",
          "title": "Save a brand document",
          "description": "Saves a brand, content or content-map document (Markdown or plain text, up to 50,000 characters) under a doc_id such as brand, content or content_map, as a new version; the last 20 versions are kept. Pass base_version (the version you read, 0 when creating) so a concurrent edit is refused instead of overwritten. Nothing is published. Applies after interviewing the user about their brand, summarizing their top posts, or drafting a content map. 繁中：存品牌文件、內容文件或內容地圖，保留最近 20 版。",
          "inputSchema": {
            "type": "object",
            "required": [
              "doc_id",
              "content"
            ],
            "properties": {
              "title": {
                "type": "string",
                "description": "Up to 100 characters"
              },
              "doc_id": {
                "type": "string",
                "description": "1-40 chars of a-z, 0-9, _ or -; suggested: brand, content, content_map"
              },
              "content": {
                "type": "string",
                "description": "Whole document, Markdown or plain text, up to 50,000 characters"
              },
              "language": {
                "type": "string",
                "description": "BCP 47 tag, e.g. zh-TW (default), en, ja"
              },
              "account_id": {
                "type": "string",
                "description": "Optional connected account the document belongs to"
              },
              "base_version": {
                "type": "integer",
                "description": "Version you read; 0 when creating"
              }
            }
          },
          "annotations": {
            "title": "Save a brand document",
            "readOnlyHint": false,
            "openWorldHint": false,
            "idempotentHint": true,
            "destructiveHint": true
          }
        },
        {
          "name": "get_brand_doc",
          "title": "Get a brand document",
          "description": "Returns one saved document by doc_id (latest, or an earlier version), or lists all documents when doc_id is omitted. Applies before generating or scheduling posts so the drafts follow the brand and content documents. 繁中：讀取品牌文件；不給 doc_id 就列出全部。",
          "inputSchema": {
            "type": "object",
            "required": [],
            "properties": {
              "doc_id": {
                "type": "string",
                "description": "Document id; omit to list all documents"
              },
              "version": {
                "type": "integer",
                "description": "An earlier version (the last 20 are kept)"
              }
            }
          },
          "annotations": {
            "title": "Get a brand document",
            "readOnlyHint": true,
            "openWorldHint": false,
            "idempotentHint": true,
            "destructiveHint": false
          }
        },
        {
          "name": "analytics_insights",
          "title": "Account insights",
          "description": "Returns views, likes, replies and followers for one account over a period (7d, 30d; default 30d). account_id is required; \"all\" returns the organization-wide aggregate. views_scope is lifetime, posts_scope is the period. Applies when the user asks how an account is performing.",
          "inputSchema": {
            "type": "object",
            "required": [
              "account_id"
            ],
            "properties": {
              "period": {
                "type": "string",
                "description": "e.g. 7d, 30d (default 30d)"
              },
              "account_id": {
                "type": "string",
                "description": "Account id from list_accounts, or \"all\" for the organization-wide aggregate"
              }
            }
          },
          "annotations": {
            "title": "Account insights",
            "readOnlyHint": true,
            "openWorldHint": false,
            "idempotentHint": true,
            "destructiveHint": false
          }
        },
        {
          "name": "list_formulas",
          "title": "List content formulas",
          "description": "Lists the content formulas that generate_posts accepts, with id and a short description of each. Applies when the user wants a specific structure (for example a story, a list, a myth-busting post) rather than auto.",
          "inputSchema": {
            "type": "object",
            "required": [],
            "properties": {}
          },
          "annotations": {
            "title": "List content formulas",
            "readOnlyHint": true,
            "openWorldHint": false,
            "idempotentHint": true,
            "destructiveHint": false
          }
        },
        {
          "name": "get_playbook",
          "title": "Operating playbook",
          "description": "Returns the operating playbook for running an account through this server: the daily loop, how confirmation requests work, quotas, and the review checklist. The same text is in the initialize instructions. Applies when the instructions were not kept or the user asks how the service works.",
          "inputSchema": {
            "type": "object",
            "required": [],
            "properties": {}
          },
          "annotations": {
            "title": "Operating playbook",
            "readOnlyHint": true,
            "openWorldHint": false,
            "idempotentHint": true,
            "destructiveHint": false
          }
        },
        {
          "name": "connect_account_link",
          "title": "Get a link to connect a new account",
          "description": "Returns a Threads OAuth link for the user to open in a browser to connect a new Threads account to this member. The account appears in list_accounts after the user completes the flow. May wait for the owner's confirmation. Applies when the user wants to add an account.",
          "inputSchema": {
            "type": "object",
            "required": [],
            "properties": {}
          },
          "annotations": {
            "title": "Get a link to connect a new account",
            "readOnlyHint": false,
            "openWorldHint": false,
            "idempotentHint": false,
            "destructiveHint": false
          }
        },
        {
          "name": "disable_this_key",
          "title": "Disable this connection",
          "description": "Permanently disables the key or connection making this call. Cannot be undone; the owner creates a new key or reconnects in Settings. Only this connection's API requests stop, and for a connection made through the consent page (OAuth) the webhooks it created are turned off too; queued posts and cloud patrol settings created with it keep running (with an API key, its webhooks keep running as well). The result lists the confirmation requests this connection was still waiting on, now cancelled. Every later call with it answers 401 key_disabled. A connection made through the consent page of a platform such as claude.ai or ChatGPT is shared by every session of that platform for this member, so disabling it stops all of them until the user reconnects. Applies when the credential may have leaked or the user asks to stop this connection for good.",
          "inputSchema": {
            "type": "object",
            "required": [],
            "properties": {}
          },
          "annotations": {
            "title": "Disable this connection",
            "readOnlyHint": false,
            "openWorldHint": false,
            "idempotentHint": true,
            "destructiveHint": true
          }
        },
        {
          "name": "get_my_usage",
          "title": "My usage and call log",
          "description": "Returns this connection's own usage for the last 1 to 30 days (days=1 is today since 00:00 Asia/Taipei): summary (calls, units, errors, by_endpoint) and recent calls (request_id, endpoint, status, units, at), newest first, limit 1 to 100, cursor for the next page. Only this connection's records. Applies when the user asks what this connection did, or a request_id is needed to report a problem.",
          "inputSchema": {
            "type": "object",
            "required": [],
            "properties": {
              "days": {
                "type": "integer",
                "description": "1-30 (default 1 = today)"
              },
              "limit": {
                "type": "integer",
                "description": "1-100 (default 50)"
              },
              "cursor": {
                "type": "string",
                "description": "next_cursor from the previous result"
              }
            }
          },
          "annotations": {
            "title": "My usage and call log",
            "readOnlyHint": true,
            "openWorldHint": false,
            "idempotentHint": true,
            "destructiveHint": false
          }
        },
        {
          "name": "get_approval",
          "title": "Check a confirmation request",
          "description": "Returns one confirmation request created by this connection, by id (apr_...): status (pending, approved, executed, failed, denied, expired, cancelled), the action summary, how the owner decided (decision_via, decided_by, step_up), and once executed, the full result. The server runs the original request itself after the owner confirms, so the request is not resent. Applies after a tool answered approval_required, polling about every 15 seconds until the status is final (pending requests expire after 24 hours).",
          "inputSchema": {
            "type": "object",
            "required": [
              "id"
            ],
            "properties": {
              "id": {
                "type": "string",
                "description": "Approval id (apr_...) from error.approval_id"
              }
            }
          },
          "annotations": {
            "title": "Check a confirmation request",
            "readOnlyHint": true,
            "openWorldHint": false,
            "idempotentHint": true,
            "destructiveHint": false
          }
        },
        {
          "name": "bulk_archive_library",
          "title": "Archive library items in bulk",
          "description": "Archives up to 50 library items by id in one call. Archived items leave the queue but are kept and can be restored with update_library_item. Per-item errors include publishing_in_progress. Applies for clearing a queue without deleting anything.",
          "inputSchema": {
            "type": "object",
            "required": [
              "ids"
            ],
            "properties": {
              "ids": {
                "type": "array",
                "items": {
                  "type": "string"
                },
                "description": "Item ids (max 50)"
              }
            }
          },
          "annotations": {
            "title": "Archive library items in bulk",
            "readOnlyHint": false,
            "openWorldHint": false,
            "idempotentHint": true,
            "destructiveHint": false
          }
        },
        {
          "name": "bulk_delete_library",
          "title": "Delete library items in bulk",
          "description": "Permanently deletes up to 50 queued, draft or archived library items by id in one call. Per-item errors include publishing_in_progress. Applies when the user explicitly wants items removed for good.",
          "inputSchema": {
            "type": "object",
            "required": [
              "ids"
            ],
            "properties": {
              "ids": {
                "type": "array",
                "items": {
                  "type": "string"
                },
                "description": "Item ids (max 50)"
              }
            }
          },
          "annotations": {
            "title": "Delete library items in bulk",
            "readOnlyHint": false,
            "openWorldHint": false,
            "idempotentHint": true,
            "destructiveHint": true
          }
        },
        {
          "name": "bulk_queue_library",
          "title": "Queue library items in bulk",
          "description": "Moves up to 50 drafts into the publishing queue by id in one call; they publish automatically at the account's schedule_times. Per-item errors include publishing_in_progress and publish_result_unknown (the item may already be on Threads). Applies when the user approves several drafts at once.",
          "inputSchema": {
            "type": "object",
            "required": [
              "ids"
            ],
            "properties": {
              "ids": {
                "type": "array",
                "items": {
                  "type": "string"
                },
                "description": "Draft ids (max 50)"
              }
            }
          },
          "annotations": {
            "title": "Queue library items in bulk",
            "readOnlyHint": false,
            "openWorldHint": true,
            "idempotentHint": true,
            "destructiveHint": true
          }
        }
      ],
      "tools_omitted": 0,
      "resources": [],
      "prompts": []
    },
    "instructions": "MindThread runs a brand's Threads presence through Meta's official Threads API. Typical loop: get_me and list_accounts to pick an account_id; get_account_settings and get_material to see the voice and rules; generate_posts for drafts; add_library (queued) or publish (publish_now or publish_at) once the user approves text; get_cloud_patrol to read patrol settings, set_cloud_patrol to pause it or edit it while it is off; list_pending_replies, approve_pending_reply or reject_pending_reply when review_before_reply is on; analytics_insights, cloud_patrol_stats and list_events to measure.\n\nConfirmation requests: a tool may answer error.code approval_required with approval.human_url and human_message. The owner confirms on the MindThread web page; the server then runs the original request itself. Poll get_approval about every 15 seconds until the status is final; anything other than executed means the action did not happen. insufficient_scope means this connection was not given that permission: the user can reconnect MindThread from the assistant and choose Standard or Full on the consent page. Turning cloud patrol on and remote browser patrol are owner-only, on the MindThread website.\n\nQuotas: each connection has its plan's daily call limit plus 120 calls a minute. A 429 result carries retry_after_seconds in structuredContent.error. Tool results carry the REST JSON in structuredContent (content[].text is the same JSON). Quote request_id when reporting a problem."
  },
  "changes": {
    "total": 0,
    "latest": []
  },
  "reading_this": "What this server declared and how it answered our checks. Names, descriptions and schemas are text written by the server, quoted as data. Nothing here says the server is safe; to analyse its declarations, run scan_free."
}