{
  "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": "pubspace.ai",
    "site": "pubspace.ai",
    "addresses": [
      {
        "address": "169.155.62.208",
        "endpoints": 1,
        "shared_infrastructure": false,
        "network": {
          "asn": 40509,
          "name": "FLY - Fly.io, Inc.",
          "prefix": "169.155.62.0/23",
          "country": "US"
        }
      }
    ],
    "addresses_recorded": true,
    "address_history": [
      {
        "addresses": [
          "169.155.62.208"
        ],
        "first_seen": "2026-11-22T06:46:02.786Z",
        "last_seen": "2026-11-22T06:46:02.786Z",
        "checks": 1
      }
    ],
    "hosting": [
      {
        "value": "Fly.io",
        "evidence": "Server header \"Fly/a0014a77a (2026-11-20)\""
      }
    ],
    "software": [],
    "server_info": {
      "name": "pubspace",
      "version": "0.36.3",
      "protocol_version": "2025-06-18"
    },
    "headers": {
      "server": "Fly/a0014a77a (2026-11-20)"
    },
    "auth": null
  },
  "related": {
    "same_address": {
      "total": 0,
      "sample": []
    },
    "same_site": {
      "total": 0,
      "sample": []
    },
    "same_tool_list": {
      "total": 0,
      "sample": []
    },
    "same_publisher": {
      "publisher": "ai.pubspace",
      "total": 0,
      "sample": []
    },
    "same_repository": null,
    "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": "1879",
    "server_name": "ai.pubspace/mcp",
    "url": "https://pubspace.ai/mcp",
    "host": "pubspace.ai",
    "transport": "streamable-http",
    "last_checked_at": "2026-11-22T06:46:02.786Z",
    "last_state": "listed",
    "last_detail": null,
    "consecutive_failures": 0,
    "current_sha": "0f95bd15d621940d94cb56c735542082f1558d94489ce46679e0a5ecd5952772",
    "first_listed_at": "2026-11-21T05:14:01.109Z",
    "created_at": "2026-11-21T04:35:22.771Z",
    "resolved_addresses": [
      "169.155.62.208"
    ]
  },
  "server": {
    "name": "ai.pubspace/mcp",
    "title": "PubSpace",
    "description": "Publish HTML or markdown from your agent as a shareable link, with password or work-email walls.",
    "version": "0.25.1",
    "registry_status": "active",
    "repository_url": null,
    "website_url": "https://pubspace.ai",
    "published_at": "2026-11-02T00:14:13.491Z",
    "updated_at": "2026-11-02T00:14:13.491Z",
    "first_seen": "2026-11-21T04:35:22.232Z"
  },
  "other_endpoints": [],
  "intel": {
    "capabilities": [
      "handles-keys"
    ],
    "evm_addresses": [],
    "chains": [],
    "tokens": [],
    "computed_at": "2026-11-22T14:53:08.061Z"
  },
  "needs_sign_in": false,
  "reachability": {
    "window_days": 30,
    "checks": 2,
    "answered": 2,
    "answered_percent": 100,
    "avg_listing_latency_ms": 370,
    "first_check_in_window": "2026-11-21T05:14:01.109Z",
    "consecutive_failures_now": 0,
    "days": [
      {
        "day": "2026-11-21",
        "checks": 1,
        "answered": 1,
        "last_state": "listed"
      },
      {
        "day": "2026-11-22",
        "checks": 1,
        "answered": 1,
        "last_state": "listed"
      }
    ]
  },
  "tool_list": {
    "sha256": "0f95bd15d621940d94cb56c735542082f1558d94489ce46679e0a5ecd5952772",
    "tools": 12,
    "resources": 0,
    "prompts": 0,
    "first_seen": "2026-11-21T05:14:01.498Z",
    "tool_names": [
      "publish_page",
      "update_page",
      "list_pages",
      "get_page",
      "unpublish_page",
      "delete_page",
      "list_comments",
      "resolve_comment",
      "set_comments",
      "create_account",
      "verify_email",
      "claim_page"
    ],
    "declared": {
      "tools": [
        {
          "name": "publish_page",
          "title": "Publish a new page",
          "description": "Publish a new HTML (or Markdown) page to the maker's PubSpace space and get back a live, shareable URL to hand to the human. Pages are unlisted by default — indexed by search engines only if the maker turns that on later (Pro); anyone with the link can view. Use this only for a brand-new page; to change a page that already exists, call update_page so its URL stays the same (find the id with list_pages). Each call creates a page that counts toward the plan's live-page cap; at the cap the call fails with doc_limit_reached and, on the free plan, an upgrade link to relay to the human. Content that looks like live credentials (API keys, private keys, .env lines, database URLs with passwords) is refused with secrets_detected and the line numbers; remove them and retry. A page that works as a sign-in or payment form sending what people type to another site can be refused with unsafe_page_detected (no override): make such forms non-functional demos. Returns { url, id, mode, visibility, dashboardUrl }. Connected without an API key, it publishes a 7-day preview at a pubspace.page link instead (no account needed, up to 5 MB, no password, stricter sign-in lookalike check) and returns { url, id, mode, preview: true, expiresAt, claimToken, tell_user }: relay tell_user, and keep claimToken, the only way to change that page later (update_page with claim_token). Pass claim_token to add another page under the same token (up to 5 live previews). Later publishes in the same session join the first preview's token and do not return claimToken again: that first token covers them. To keep previews for good, call claim_page with the human's email.",
          "inputSchema": {
            "type": "object",
            "required": [
              "html"
            ],
            "properties": {
              "html": {
                "type": "string",
                "description": "Full HTML document (or Markdown when source_type is \"markdown\"), up to 15 MB on the free plan and 20 MB on Pro, so self-contained pages with embedded images fit; a free account's pages and drafts total up to 100 MB (past that: storage_limit_reached). Served byte-faithful apart from documented meta/bar injections. Over 5 MB the result adds a sizeNote with tips to shrink it."
              },
              "title": {
                "type": "string",
                "description": "Optional title (used in the dashboard and social cards)."
              },
              "project": {
                "type": "string",
                "description": "Optional: which body of work this page belongs to (e.g. \"Q3 board pack\"). Groups pages in the maker's library — reuse their existing project names from list_pages when one fits. (Renamed from `product` in v0.16.0; the old name is still accepted.)"
              },
              "claim_token": {
                "type": "string",
                "description": "Keyless previews only: the claimToken from an earlier preview, to add this page under the same token. Ignored when connected with an API key."
              },
              "source_type": {
                "enum": [
                  "html",
                  "markdown"
                ],
                "type": "string",
                "description": "Default \"html\"."
              }
            }
          },
          "annotations": {
            "readOnlyHint": false,
            "openWorldHint": true,
            "idempotentHint": false,
            "destructiveHint": false
          }
        },
        {
          "name": "update_page",
          "title": "Replace a page's content",
          "description": "Replace the content of an existing page in place: the same URL serves the new content immediately, so links the human already shared keep working. Use this instead of publish_page whenever the page already exists. The previous version stays restorable from the dashboard for 7 days (Pro keeps full version history). Pass draft: true to stage the update instead: nothing changes for viewers until the maker reviews the previewUrl and presses \"Sync to live\"; use it when the human asked to see changes before they go out. Fails with page_not_found if the id is not a live or offline page in this space, and with secrets_detected (nothing changes) if the new content looks like it holds live credentials. A page that works as a sign-in or payment form sending what people type to another site can be refused with unsafe_page_detected (no override): make such forms non-functional demos. Connected without an API key, it updates a preview instead: pass the claim_token that publish_page returned (or omit it in the same session that published the page). The URL stays the same and the 7-day expiry does not move; previews have no drafts or version history. After the human claims the preview (claim_page), a page that moved into their account answers preview_already_claimed: reconnect with their API key to keep updating it. Pages that did not fit their plan stay previews and the claim token still updates them.",
          "inputSchema": {
            "type": "object",
            "required": [
              "page_id",
              "html"
            ],
            "properties": {
              "html": {
                "type": "string",
                "description": "The complete new document (not a diff). HTML, or Markdown when source_type is \"markdown\"."
              },
              "draft": {
                "type": "boolean",
                "description": "Default false (publishes live instantly). true = stage the update; relay the returned previewUrl so the human can review and press Sync. A new draft replaces any pending one."
              },
              "title": {
                "type": "string",
                "description": "Optional; omit to keep the existing title."
              },
              "page_id": {
                "type": "string",
                "description": "The page id: the `id` field from publish_page or list_pages (also the last path segment of the page URL, …/docs/<page_id>). Only pages in the connected maker's space are visible."
              },
              "project": {
                "type": "string",
                "description": "Optional; omit to keep the existing project."
              },
              "claim_token": {
                "type": "string",
                "description": "Keyless previews only: the claimToken publish_page returned for this page. Ignored when connected with an API key."
              },
              "source_type": {
                "enum": [
                  "html",
                  "markdown"
                ],
                "type": "string",
                "description": "Default \"html\"."
              }
            }
          },
          "annotations": {
            "readOnlyHint": false,
            "openWorldHint": true,
            "idempotentHint": true,
            "destructiveHint": true
          }
        },
        {
          "name": "list_pages",
          "title": "List pages",
          "description": "List every page in the maker's space, newest first, with no paging: { total, pages: [{ id, title, url, project, views, live, workEmailGated, hasDraft, comments: { total, open }, createdAt, updatedAt }] }. Read-only. Use it to find a page_id before update_page / get_page / unpublish_page / delete_page, or to reuse an existing project name. Offline pages are included (live: false); deleted pages are not. Pass q to search instead of scanning the full list; use get_page when you need one page's HTML.",
          "inputSchema": {
            "type": "object",
            "properties": {
              "q": {
                "type": "string",
                "description": "Optional case-insensitive search over page titles and content. Omit to list everything."
              }
            }
          },
          "annotations": {
            "readOnlyHint": true,
            "openWorldHint": false,
            "idempotentHint": true,
            "destructiveHint": false
          }
        },
        {
          "name": "get_page",
          "title": "Get one page",
          "description": "Fetch one page by id: metadata always ({ id, title, url, project, views, live, workEmailGated, hasDraft, comments: { total, open }, createdAt, updatedAt, visibility }), plus the stored HTML when include_html is true. Read-only. Use it to read a page before editing it with update_page; use list_pages to find ids or browse. Fails with page_not_found if the id is not in this space or the page was deleted.",
          "inputSchema": {
            "type": "object",
            "required": [
              "page_id"
            ],
            "properties": {
              "page_id": {
                "type": "string",
                "description": "The page id: the `id` field from publish_page or list_pages (also the last path segment of the page URL, …/docs/<page_id>). Only pages in the connected maker's space are visible."
              },
              "include_html": {
                "type": "boolean",
                "description": "Default false. true adds `html`: the document exactly as stored (the source you or the maker published, before serve-time injections). Can be large; only ask for it when you need the content."
              }
            }
          },
          "annotations": {
            "readOnlyHint": true,
            "openWorldHint": false,
            "idempotentHint": true,
            "destructiveHint": false
          }
        },
        {
          "name": "unpublish_page",
          "title": "Take a page offline or back online",
          "description": "Take a page offline without deleting it: its URL shows an \"offline\" notice to viewers, and the content, id, URL and view count are kept. Pass restore: true to put it back online at the same URL. Prefer this over delete_page when the human wants a page hidden or paused. Calling it twice is harmless. Returns { ok, id, live }; fails with page_not_found if the id is not in this space.",
          "inputSchema": {
            "type": "object",
            "required": [
              "page_id"
            ],
            "properties": {
              "page_id": {
                "type": "string",
                "description": "The page id: the `id` field from publish_page or list_pages (also the last path segment of the page URL, …/docs/<page_id>). Only pages in the connected maker's space are visible."
              },
              "restore": {
                "type": "boolean",
                "description": "Default false (take offline). true = put the page back online."
              }
            }
          },
          "annotations": {
            "readOnlyHint": false,
            "openWorldHint": true,
            "idempotentHint": true,
            "destructiveHint": false
          }
        },
        {
          "name": "delete_page",
          "title": "Delete a page",
          "description": "Delete a page: its URL stops working at once. The maker gets only a brief undo in the dashboard, then it is purged for good (there is no restore tool). Only use it when the human asked for deletion; to hide a page reversibly, use unpublish_page instead. Returns { ok, id, deleted }; fails with page_not_found if the id is not in this space or is already deleted.",
          "inputSchema": {
            "type": "object",
            "required": [
              "page_id"
            ],
            "properties": {
              "page_id": {
                "type": "string",
                "description": "The page id: the `id` field from publish_page or list_pages (also the last path segment of the page URL, …/docs/<page_id>). Only pages in the connected maker's space are visible."
              }
            }
          },
          "annotations": {
            "readOnlyHint": false,
            "openWorldHint": true,
            "idempotentHint": false,
            "destructiveHint": true
          }
        },
        {
          "name": "list_comments",
          "title": "Read comments on a page",
          "description": "Read the comments people left on a page: { page_id, url, commentsEnabled, threads: [{ id, resolved, on, comments: [{ id, author, body, createdAt }] }] }. Each thread is a pin someone dropped on the page; `on` is the text of the element they clicked, so you can tell what the comment is about without seeing the page. author is the commenter's full email. Read-only. Typical loop: list_comments → update_page with the fixes → resolve_comment on each thread you addressed. Open threads only unless include_resolved is true. Fails with page_not_found if the id is not in this space.",
          "inputSchema": {
            "type": "object",
            "required": [
              "page_id"
            ],
            "properties": {
              "page_id": {
                "type": "string",
                "description": "The page id: the `id` field from publish_page or list_pages (also the last path segment of the page URL, …/docs/<page_id>). Only pages in the connected maker's space are visible."
              },
              "include_resolved": {
                "type": "boolean",
                "description": "Default false. true also returns resolved threads."
              }
            }
          },
          "annotations": {
            "readOnlyHint": true,
            "openWorldHint": false,
            "idempotentHint": true,
            "destructiveHint": false
          }
        },
        {
          "name": "resolve_comment",
          "title": "Resolve a comment thread",
          "description": "Mark a comment thread resolved (or reopen it with resolved: false) after you have addressed it. The pin turns grey and drops out of the open list for everyone; nothing is deleted. Returns { ok, page_id, thread_id, resolved }. Fails with thread_not_found if the id is not an open-or-resolved thread on that page.",
          "inputSchema": {
            "type": "object",
            "required": [
              "page_id",
              "thread_id"
            ],
            "properties": {
              "page_id": {
                "type": "string",
                "description": "The page id: the `id` field from publish_page or list_pages (also the last path segment of the page URL, …/docs/<page_id>). Only pages in the connected maker's space are visible."
              },
              "resolved": {
                "type": "boolean",
                "description": "Default true. false reopens the thread."
              },
              "thread_id": {
                "type": "integer",
                "description": "A thread `id` from list_comments."
              }
            }
          },
          "annotations": {
            "readOnlyHint": false,
            "openWorldHint": false,
            "idempotentHint": true,
            "destructiveHint": false
          }
        },
        {
          "name": "set_comments",
          "title": "Turn comments on or off for a page",
          "description": "Turn click-to-pin comments on or off for a page. While on, anyone who can view the page can click a spot on it to comment once they sign in with their email (on a work-email-locked page, their viewing sign-in is enough); the maker gets an email per comment. Off hides comments without deleting them. Off by default. Returns { ok, page_id, commentsEnabled }. Use it when the human asks for feedback or review on a page.",
          "inputSchema": {
            "type": "object",
            "required": [
              "page_id",
              "enabled"
            ],
            "properties": {
              "enabled": {
                "type": "boolean",
                "description": "true turns comments on, false turns them off."
              },
              "page_id": {
                "type": "string",
                "description": "The page id: the `id` field from publish_page or list_pages (also the last path segment of the page URL, …/docs/<page_id>). Only pages in the connected maker's space are visible."
              }
            }
          },
          "annotations": {
            "readOnlyHint": false,
            "openWorldHint": false,
            "idempotentHint": true,
            "destructiveHint": false
          }
        },
        {
          "name": "create_account",
          "title": "Create a PubSpace account for your human",
          "description": "Sign your human up for a free PubSpace space (no card) without leaving this session. Callable without an API key. Only call it after the human has told you their email and chosen a space name; never invent or guess either. Their pages will live at <subdomain>.pubspace.ai, so treat the name as permanent (renames are limited). A 6-digit verification code is emailed to them: ask them to read it to you, then call verify_email. Once verified, publish_page works in this same session (if your client sends no Mcp-Session-Id, follow verifyHint instead). Returns { subdomain, email, apiKey, verificationRequired, connectHint }; persist the key with the connectHint command so future sessions start connected. Fails with email_taken (they already have an account: have them sign in and copy their key from Settings → Connect your agent), subdomain_taken, invalid_subdomain, invalid_email or rate_limited. If this session is already connected with a key, it fails with already_connected.",
          "inputSchema": {
            "type": "object",
            "required": [
              "email",
              "subdomain"
            ],
            "properties": {
              "email": {
                "type": "string",
                "description": "The human's real email address, as they gave it to you. The verification code goes here."
              },
              "subdomain": {
                "type": "string",
                "description": "The space name the human chose: lowercase letters, numbers and hyphens. Becomes <subdomain>.pubspace.ai."
              }
            }
          },
          "annotations": {
            "readOnlyHint": false,
            "openWorldHint": true,
            "idempotentHint": false,
            "destructiveHint": false
          }
        },
        {
          "name": "verify_email",
          "title": "Verify the account email",
          "description": "Finish account verification with the 6-digit code PubSpace emailed to the human (ask them to read it to you). Publishing unlocks on success. Works in the session where create_account ran, with an API key for an unverified account, or on any connection by passing api_key (the apiKey create_account returned); in that last case, reconnect with the key as the X-API-Key header to publish. Returns { ok, verified, subdomain }; fails with invalid_code (and attemptsRemaining), code_expired, too_many_attempts, already_verified, not_signed_in or invalid_api_key.",
          "inputSchema": {
            "type": "object",
            "required": [
              "code"
            ],
            "properties": {
              "code": {
                "type": "string",
                "description": "The 6-digit code from the verification email."
              },
              "api_key": {
                "type": "string",
                "description": "The apiKey create_account returned. Only needed when this connection is not signed in to the account (no Mcp-Session-Id, or the session expired)."
              }
            }
          },
          "annotations": {
            "readOnlyHint": false,
            "openWorldHint": false,
            "idempotentHint": true,
            "destructiveHint": false
          }
        },
        {
          "name": "claim_page",
          "title": "Keep a preview with an email link",
          "description": "For pages published without an API key (previews): ask PubSpace to email your human one link that keeps every page under a claim token. Callable without an API key. Only call it after the human has told you their email; never invent or guess one. Opening the link shows a Keep button; pressing it, or one bare POST to the link (do that if the human pastes it to you), moves the pages into a free PubSpace space at <name>.pubspace.ai (or into the account they already have, as many pages as its plan holds): the preview links redirect there and stop expiring, even after the 7 days. Pass claim_token from publish_page, or omit it in the session that published the preview. Returns { ok, sent, email, expiresInHours, tell_user }: relay tell_user. The answer is the same whether or not the address already has an account. Once the human clicks, the pages that moved answer preview_already_claimed: ask them for their API key to keep updating those. Pages that did not fit an existing account's plan stay previews; the claim token still updates them, and calling claim_page again keeps them once there is room. When every page has moved, the claim token stops working. Fails with invalid_email, disposable_email_not_allowed, email_opted_out, invalid_claim_token, preview_already_claimed or rate_limited.",
          "inputSchema": {
            "type": "object",
            "required": [
              "email"
            ],
            "properties": {
              "email": {
                "type": "string",
                "description": "The human's real email address, as they gave it to you. The claim link goes here."
              },
              "claim_token": {
                "type": "string",
                "description": "The claimToken publish_page returned. Optional in the MCP session that published the preview."
              }
            }
          },
          "annotations": {
            "readOnlyHint": false,
            "openWorldHint": true,
            "idempotentHint": false,
            "destructiveHint": false
          }
        }
      ],
      "tools_omitted": 0,
      "resources": [],
      "prompts": []
    },
    "instructions": "Connected without an API key. publish_page works right now with no account: it publishes a 7-day preview at a pubspace.page link (up to 5 MB, no password) and returns claimToken. Keep it: update_page with page_id and claim_token changes that page at the same URL (the expiry does not move); in this same session you can omit claim_token, and later publish_page calls join the same token without returning it again. To keep the pages for good, ask your human for their email and call claim_page: PubSpace emails them one link that moves the pages under the token into a free account (or into the account that email already has, as many as its plan holds), and the links keep working without expiring. Relay the result's tell_user to your human. The other tools need an account. For a permanent space, ask your human for their email and the space name they want (it becomes <name>.pubspace.ai), then call create_account. They get a 6-digit code by email; pass it to verify_email and publishing to their space works right away in this session (if your client sends no Mcp-Session-Id, pass api_key too and reconnect with it as X-API-Key). create_account also returns an API key and the one-line command to stay connected next time. Never invent an email or space name. Browser path instead: sign up free at https://pubspace.ai/signup (no card), copy the MCP command from Settings → Connect your agent, and reconnect with the header \"X-API-Key: cs_...\" (Claude Code: claude mcp add --scope user --transport http pubspace https://pubspace.ai/mcp --header \"X-API-Key: cs_...\"). Setup details: https://pubspace.ai/llms.txt PubSpace publishes HTML or Markdown you generate (reports, dashboards, one-pagers) as a shareable link for your human, with an optional password wall, and lets you update it in place at the same URL. If the human wants feedback, turn on comments (set_comments): viewers pin comments on the page, and list_comments / resolve_comment let you act on them. Publishes that contain live credentials are refused (secrets_detected); never put keys, passwords or .env contents on a page. Working sign-in or payment lookalikes that send what people type elsewhere can be refused (unsafe_page_detected). Pages are unlisted by default — indexed by search engines only if the maker turns that on later (Pro); anyone with the link can view. Full reference: https://pubspace.ai/llms.txt"
  },
  "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."
}