{
  "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": "www.arcreport.ai",
    "site": "arcreport.ai",
    "addresses": [
      {
        "address": "76.76.21.61",
        "endpoints": 37,
        "shared_infrastructure": true,
        "network": {
          "asn": 16509,
          "name": "AMAZON-02 - Amazon.com, Inc.",
          "prefix": "76.76.21.0/24",
          "country": "US"
        }
      },
      {
        "address": "66.33.60.130",
        "endpoints": 34,
        "shared_infrastructure": true,
        "network": {
          "asn": 16509,
          "name": "AMAZON-02 - Amazon.com, Inc.",
          "prefix": "66.33.60.0/24",
          "country": "US"
        }
      }
    ],
    "addresses_recorded": true,
    "address_history": [
      {
        "addresses": [
          "76.76.21.61",
          "66.33.60.130"
        ],
        "first_seen": "2026-11-22T04:36:01.094Z",
        "last_seen": "2026-11-22T04:36:01.094Z",
        "checks": 1
      }
    ],
    "hosting": [
      {
        "value": "Vercel",
        "evidence": "Server header \"Vercel\""
      }
    ],
    "software": [],
    "server_info": {
      "name": "ARC ask — public Index read",
      "version": "1.0.0",
      "protocol_version": "2025-06-18"
    },
    "headers": {
      "server": "Vercel",
      "strict-transport-security": "max-age=63072000; includeSubDomains",
      "access-control-allow-origin": "*"
    },
    "auth": null
  },
  "related": {
    "same_address": {
      "total": 36,
      "sample": [
        {
          "id": "1173",
          "url": "https://app.howseen.ai/api/mcp",
          "server_name": "ai.howseen/howseen-mcp",
          "last_state": "listed",
          "last_checked_at": "2026-11-22T04:56:01.230Z"
        },
        {
          "id": "1559",
          "url": "https://docs.modellix.ai/mcp",
          "server_name": "ai.modellix/docs-search",
          "last_state": "listed",
          "last_checked_at": "2026-11-22T06:43:08.743Z"
        },
        {
          "id": "1590",
          "url": "https://app.mypenny.ai/mcp",
          "server_name": "ai.mypenny/mypenny",
          "last_state": "listed",
          "last_checked_at": "2026-11-22T06:43:09.558Z"
        },
        {
          "id": "3422",
          "url": "https://pocket.hologallery.app/mcp",
          "server_name": "app.hologallery.pocket/pokemon-tcg-pocket-catalog",
          "last_state": "listed",
          "last_checked_at": "2026-11-22T07:01:02.470Z"
        },
        {
          "id": "3429",
          "url": "https://www.housefile.app/mcp",
          "server_name": "app.housefile/licensing",
          "last_state": "listed",
          "last_checked_at": "2026-11-22T07:01:02.661Z"
        },
        {
          "id": "4491",
          "url": "https://www.sofiaferro.com.ar/api/mcp",
          "server_name": "ar.com.sofiaferro/portfolio",
          "last_state": "listed",
          "last_checked_at": "2026-11-22T07:12:01.927Z"
        },
        {
          "id": "5220",
          "url": "https://enmente.clinic/api/mcp/",
          "server_name": "clinic.enmente/mcp",
          "last_state": "listed",
          "last_checked_at": "2026-11-22T07:26:02.073Z"
        },
        {
          "id": "5642",
          "url": "https://www.meetclair.co/api/mcp",
          "server_name": "co.meetclair/clair",
          "last_state": "listed",
          "last_checked_at": "2026-11-22T07:31:03.571Z"
        },
        {
          "id": "6455",
          "url": "https://api.aiengineerprofessional.com/api/mcp",
          "server_name": "com.aiengineerprofessional/engineerpro-library",
          "last_state": "listed",
          "last_checked_at": "2026-11-22T07:44:02.688Z"
        },
        {
          "id": "7497",
          "url": "https://timer.cloudforbots.com/mcp",
          "server_name": "com.botrecipe/timer",
          "last_state": "listed",
          "last_checked_at": "2026-11-22T08:14:06.018Z"
        },
        {
          "id": "13416",
          "url": "https://ai.nogamovement.com/api/mcp",
          "server_name": "com.nogamovement/la-tech-designs",
          "last_state": "listed",
          "last_checked_at": "2026-11-22T15:42:01.604Z"
        },
        {
          "id": "14010",
          "url": "https://chatgpt.payfresco.com/mcp",
          "server_name": "com.payfresco/payment-planner",
          "last_state": "listed",
          "last_checked_at": "2026-11-22T15:52:02.814Z"
        },
        {
          "id": "20211",
          "url": "https://askhound.haullabs.dev/api/mcp",
          "server_name": "dev.haullabs/askhound",
          "last_state": "listed",
          "last_checked_at": "2026-11-21T12:24:02.549Z"
        },
        {
          "id": "20325",
          "url": "https://mcp.mantlekit.dev/mcp",
          "server_name": "dev.mantlekit/launch-planner",
          "last_state": "listed",
          "last_checked_at": "2026-11-21T12:27:01.780Z"
        },
        {
          "id": "20568",
          "url": "https://mcp.redbison.dev/",
          "server_name": "dev.redbison/mcp",
          "last_state": "listed",
          "last_checked_at": "2026-11-21T12:33:03.590Z"
        },
        {
          "id": "22841",
          "url": "https://www.christiantechjobs.io/api/mcp",
          "server_name": "io.christiantechjobs/jobs",
          "last_state": "listed",
          "last_checked_at": "2026-11-21T13:23:04.086Z"
        },
        {
          "id": "24213",
          "url": "https://mcp.desearch.ai/mcp",
          "server_name": "io.github.Desearch-ai/mcp-desearch",
          "last_state": "listed",
          "last_checked_at": "2026-11-21T13:49:02.437Z"
        },
        {
          "id": "26847",
          "url": "https://mcp.swopme.co/mcp/commerce",
          "server_name": "io.github.Travisswop/swop",
          "last_state": "listed",
          "last_checked_at": "2026-11-21T14:36:00.892Z"
        },
        {
          "id": "30712",
          "url": "https://www.agentarchitect.me/mcp",
          "server_name": "io.github.jklop3841/agentarchitect-network",
          "last_state": "listed",
          "last_checked_at": "2026-11-21T15:57:02.127Z"
        },
        {
          "id": "36369",
          "url": "https://www.lendmail.fit/api/mcp",
          "server_name": "io.github.rich937/lendmail",
          "last_state": "listed",
          "last_checked_at": "2026-11-21T16:54:03.841Z"
        }
      ]
    },
    "same_site": {
      "total": 1,
      "sample": [
        {
          "id": "256",
          "url": "https://www.arcreport.ai/api/mcp",
          "server_name": "ai.arcreport/mcp",
          "last_state": "listed",
          "last_checked_at": "2026-11-22T04:37:01.678Z"
        }
      ]
    },
    "same_tool_list": {
      "total": 0,
      "sample": []
    },
    "same_publisher": {
      "publisher": "ai.arcreport",
      "total": 1,
      "sample": [
        {
          "name": "ai.arcreport/mcp",
          "title": "ARC: agent checkout reachability"
        }
      ]
    },
    "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": "255",
    "server_name": "ai.arcreport/ask",
    "url": "https://www.arcreport.ai/api/ask",
    "host": "www.arcreport.ai",
    "transport": "streamable-http",
    "last_checked_at": "2026-11-22T04:36:01.094Z",
    "last_state": "listed",
    "last_detail": null,
    "consecutive_failures": 0,
    "current_sha": "117c71ad500065e3afa3cca184cb261b6bb9f663a4ac4cd2323135610075610c",
    "first_listed_at": "2026-11-21T04:36:00.963Z",
    "created_at": "2026-11-21T04:30:08.959Z",
    "resolved_addresses": [
      "76.76.21.61",
      "66.33.60.130"
    ]
  },
  "server": {
    "name": "ai.arcreport/ask",
    "title": "ARC (arcreport.ai): can an agent reach checkout?",
    "description": "Free open check: can an AI agent reach checkout on this store? Advisory; ARC stops before payment.",
    "version": "2026.10.14",
    "registry_status": "active",
    "repository_url": null,
    "website_url": "https://www.arcreport.ai/for-agents",
    "published_at": "2026-10-14T14:24:24.083Z",
    "updated_at": "2026-10-14T14:24:24.083Z",
    "first_seen": "2026-11-21T04:30:08.294Z"
  },
  "other_endpoints": [],
  "intel": {
    "capabilities": [
      "takes-payment"
    ],
    "evm_addresses": [],
    "chains": [],
    "tokens": [],
    "computed_at": "2026-11-22T14:50:14.849Z"
  },
  "needs_sign_in": false,
  "reachability": {
    "window_days": 30,
    "checks": 2,
    "answered": 2,
    "answered_percent": 100,
    "avg_listing_latency_ms": 503,
    "first_check_in_window": "2026-11-21T04:36:00.963Z",
    "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": "117c71ad500065e3afa3cca184cb261b6bb9f663a4ac4cd2323135610075610c",
    "tools": 7,
    "resources": 0,
    "prompts": 0,
    "first_seen": "2026-11-21T04:36:01.477Z",
    "tool_names": [
      "before_checkout",
      "find_stores",
      "why_blocked_and_fix",
      "report_outcome",
      "store_record",
      "compare",
      "guide"
    ],
    "declared": {
      "tools": [
        {
          "name": "before_checkout",
          "title": "Before checkout",
          "description": "Call this right before your agent tries to check out at a store, or when a user asks \"can my agent check out at <store>?\". Not for an attempt that already happened (log it with report_outcome), the reason an agent keeps failing (why_blocked_and_fix), or choosing between 2 or more stores (compare). Returns a one-line answer, reaches_checkout (true only when a checkout link came back or a shopper reached checkout; false when a route was measured and did not reach checkout; null when not shown either way: no agent catalog found and no browser test is null, and so is a product added to the cart with no shopper reaching checkout; null is not a no), protocol_route, browser_route, standard_shoppers when ARC's standard shoppers tried the store (a dated label, \"ARC's standard shoppers: N of M reached checkout, <date>\": a lower bound, not a verdict; ARC stops before payment and never places an order), best_route (the best saved way in), payment_methods_declared (the payment handler ids the store declares to agents in its own UCP profile, with source \"ucp_profile\", checked_at and a note; the store's own declaration, not a test of any agent paying there; null with payment_methods_note when ARC has no UCP profile reading, which is not a no), up to 3 blockers, checked_at, the Agent Readiness Grade (grade, with expired when over 30 days old; grade_note when not graded, which is not a mark against the store), alternatives_hint when the grade is D or F or expired (a find_stores call with min_grade B in the same category), and a full_record link (the precheck answer, which also carries product_markup). Example: before_checkout({\"url\":\"https://allbirds.com\"}) → {\"answer\":\"A saved check got a checkout link back at allbirds.com via storefront_mcp (6 hours ago).\",\"reaches_checkout\":true,…}. The answer leads with the dated fact; once the record is not current it starts \"Last known on <date>.\". reaches_checkout false or unknown is not a no. Saved checks only: no store fetch, no scan, no login. Advisory; ARC stops before payment. Every answer carries checked_at (the saved check it rests on; for a list, the oldest) and stale (true when that check is 24 hours old or older, or has no time). Errors: {error:{code, message, next_step}}.",
          "inputSchema": {
            "type": "object",
            "required": [
              "url"
            ],
            "properties": {
              "url": {
                "type": "string",
                "description": "Store or product URL, such as https://allbirds.com or allbirds.com."
              }
            },
            "additionalProperties": false
          },
          "annotations": {
            "title": "Before checkout",
            "readOnlyHint": true,
            "openWorldHint": false,
            "idempotentHint": true,
            "destructiveHint": false
          }
        },
        {
          "name": "find_stores",
          "title": "Find stores",
          "description": "Call this when you need to pick a store for a product need and want one where a saved check shows an agent reached checkout. Filters: category or q (shopper words), min_grade (optional, default none), payment_method (optional: a payment handler id such as com.google.pay, or \"google pay\" or \"shop pay\"; keeps stores whose saved UCP profile declares it), limit (default 5). Returns total, the store hosts with checked_at and grade, and a full_list link; with payment_method, also payment_method (id, name, declared_by: how many listed stores declare it, and a note: a declaration is the store's own statement, not a test of any agent paying there). Each store carries its Agent Readiness Grade (grade, null when not graded). Stores whose saved checkout evidence is from the last 30 days come first (fresh_success: true), then older evidence. Within each, best current grade first (A, then B…); an expired grade ranks after current ones of the same letter; newest checked_at first within a grade. Results are ordered only by published grade and freshness, never by anything else. Pass min_grade to keep only stores with a current grade of that letter or better. Example: find_stores({\"category\":\"running shoes\",\"limit\":3}) → {\"total\":12,\"stores\":[{\"host\":\"…\",\"checked_at\":\"…\",\"grade\":{\"grade\":\"A\",…}}],…}. Example: \"Which stores declare Google Pay to agents?\" → find_stores({\"payment_method\":\"google pay\"}) → {\"payment_method\":{\"id\":\"com.google.pay\",\"declared_by\":…},\"stores\":[…],…}. An unknown payment_method is error code unknown_payment_method with handler_ids (the ids ARC has seen); not_available means retry in a minute. A store missing from the list is not a no. Saved checks only: no store fetch, no scan, no login. Advisory; ARC stops before payment. Every answer carries checked_at (the saved check it rests on; for a list, the oldest) and stale (true when that check is 24 hours old or older, or has no time). Errors: {error:{code, message, next_step}}.",
          "inputSchema": {
            "type": "object",
            "properties": {
              "q": {
                "type": "string",
                "description": "Product need, such as skincare or camping gear."
              },
              "limit": {
                "type": "integer",
                "default": 5,
                "maximum": 25,
                "minimum": 1,
                "description": "How many stores to return. Default 5."
              },
              "category": {
                "type": "string",
                "description": "Category or shopper words, such as footwear or running shoes."
              },
              "min_grade": {
                "enum": [
                  "A",
                  "B",
                  "C",
                  "D",
                  "F"
                ],
                "type": "string",
                "description": "Optional: keep only stores whose current (not expired) Agent Readiness Grade is this letter or better (A, B, C or D; F is accepted and means any graded store, since method v2 gives no F). Default none: every store is listed. Expired and not-graded stores are left out when this is set."
              },
              "payment_method": {
                "type": "string",
                "description": "Optional. A payment handler id as stores declare it in their UCP profile, such as com.google.pay or dev.shopify.shop_pay, or the plain name google pay or shop pay (any case)."
              }
            },
            "additionalProperties": false
          },
          "annotations": {
            "title": "Find stores",
            "readOnlyHint": true,
            "openWorldHint": false,
            "idempotentHint": true,
            "destructiveHint": false
          }
        },
        {
          "name": "why_blocked_and_fix",
          "title": "Why blocked, and the fix",
          "description": "Call this after before_checkout says reaches_checkout is false or null, or when an agent got stuck at a store and you want the reason and the fix. Returns why (the saved blockers), fix (the store page's recorded fix, or \"not recorded\"), next_step and links to the full record. Example: why_blocked_and_fix({\"store\":\"gymshark.com\"}) → {\"why\":[\"…\"],\"fix\":\"…\",\"next_step\":\"…\"}. Saved checks only: no store fetch, no scan, no login. Advisory; ARC stops before payment. Every answer carries checked_at (the saved check it rests on; for a list, the oldest) and stale (true when that check is 24 hours old or older, or has no time). Errors: {error:{code, message, next_step}}.",
          "inputSchema": {
            "type": "object",
            "required": [
              "store"
            ],
            "properties": {
              "store": {
                "type": "string",
                "description": "Store domain or URL, such as gymshark.com."
              }
            },
            "additionalProperties": false
          },
          "annotations": {
            "title": "Why blocked, and the fix",
            "readOnlyHint": true,
            "openWorldHint": false,
            "idempotentHint": true,
            "destructiveHint": false
          }
        },
        {
          "name": "report_outcome",
          "title": "Report the outcome",
          "description": "Call this right after your agent tried to check out at a store, to log, record or report what happened: it reached checkout, a captcha stopped it, it got as far as shipping, anything. Use it for any attempt that already happened, so the next agent knows; before_checkout is only for before an attempt. Free, no login. Omit contributor_key and ARC issues one; send it on later reports. No personal data: emails, phones, addresses, card numbers and IPs are rejected or stripped. Example: report_outcome({\"store_domain\":\"allbirds.com\",\"agent_family\":\"browser\",\"agent_name\":\"my-agent\",\"timestamp\":\"2026-11-05T10:00:00Z\",\"furthest_step\":\"checkout\",\"blocker\":\"none\"}) → {\"ok\":true,\"status\":\"unverified\",…}. A report stays private until 3 independent contributors agree. Same as POST /api/outcomes and report_checkout on /api/mcp. checked_at and stale are null on this answer: a report is not one of ARC's checks. Errors: {error:{code, message, next_step}}.",
          "inputSchema": {
            "type": "object",
            "required": [
              "store_domain",
              "agent_family",
              "furthest_step",
              "blocker"
            ],
            "properties": {
              "blocker": {
                "enum": [
                  "captcha",
                  "login_wall",
                  "bot_block",
                  "3ds",
                  "payment_declined",
                  "none"
                ],
                "type": "string",
                "description": "What stopped the agent, or none."
              },
              "timestamp": {
                "type": "string",
                "description": "Optional. ISO 8601 time of the attempt, within the last 14 days. Omit it and ARC uses the time it received the report."
              },
              "agent_name": {
                "type": "string",
                "description": "Optional. Name of the agent that tried the checkout. No personal name. Omit it and ARC records \"not recorded\"."
              },
              "agent_family": {
                "type": "string",
                "description": "Agent family, such as browser or a model family. No personal name."
              },
              "store_domain": {
                "type": "string",
                "description": "Store hostname, such as allbirds.com."
              },
              "furthest_step": {
                "enum": [
                  "product",
                  "cart",
                  "checkout",
                  "payment",
                  "placed"
                ],
                "type": "string",
                "description": "Furthest step the agent reached."
              },
              "contributor_key": {
                "type": "string",
                "description": "Optional. Omit it and ARC returns a free key. Send that key on later reports."
              },
              "store_error_text": {
                "type": "string",
                "description": "Optional store error text. Personal data is stripped."
              }
            },
            "additionalProperties": false
          },
          "annotations": {
            "title": "Report the outcome",
            "readOnlyHint": false,
            "openWorldHint": false,
            "idempotentHint": false,
            "destructiveHint": false
          }
        },
        {
          "name": "store_record",
          "title": "Store record",
          "description": "Call this when a user asks what ARC recorded for a store, or you need the citable store page. Returns the store page's verdict, checked_at (the day of the check), stale, category, tried (ARC's standard shoppers' newest dated run, or \"Not measured\"), the recorded fix, payment_methods_declared (as on before_checkout; null with payment_methods_note when ARC has no UCP profile reading, which is not a no), record_url (claimed, served, date, method and product_markup as JSON) and links to the page, its JSON and Markdown. Example: store_record({\"store\":\"allbirds.com\"}) → {\"verdict\":\"…\",\"page_url\":\"https://www.arcreport.ai/stores/allbirds.com\",…}. Reads the published snapshot behind /stores/<host>. Saved checks only: no store fetch, no scan, no login. Advisory; ARC stops before payment. Every answer carries checked_at (the saved check it rests on; for a list, the oldest) and stale (true when that check is 24 hours old or older, or has no time). Errors: {error:{code, message, next_step}}.",
          "inputSchema": {
            "type": "object",
            "required": [
              "store"
            ],
            "properties": {
              "store": {
                "type": "string",
                "description": "Store domain or URL, such as allbirds.com."
              }
            },
            "additionalProperties": false
          },
          "annotations": {
            "title": "Store record",
            "readOnlyHint": true,
            "openWorldHint": false,
            "idempotentHint": true,
            "destructiveHint": false
          }
        },
        {
          "name": "compare",
          "title": "Compare stores",
          "description": "Call this when a user names 2 or more stores for the same item and asks which one to use, or when you must choose between a few stores and want the one where an agent is most likely to reach checkout. Use it instead of calling before_checkout once per store. Pass 2 to 10 store domains or URLs. Returns one short row per store (reaches_checkout, best_route, checked_at, grade, payment_methods_declared as on before_checkout), and pick: among stores whose saved check reached checkout in the last 30 days, the one with the best current Agent Readiness Grade (expired after current of the same letter, not graded last); null when no store has such evidence. A row with stale: true is more than 24 hours old: re-check right before the attempt. Rows are ordered only by saved checkout evidence, its freshness and published grade, never by anything else. Example: compare({\"stores\":[\"allbirds.com\",\"gymshark.com\"]}) → {\"pick\":\"allbirds.com\",\"stores\":[…]}. Each store counts as one precheck read. Saved checks only: no store fetch, no scan, no login. Advisory; ARC stops before payment. Every answer carries checked_at (the saved check it rests on; for a list, the oldest) and stale (true when that check is 24 hours old or older, or has no time). Errors: {error:{code, message, next_step}}.",
          "inputSchema": {
            "type": "object",
            "required": [
              "stores"
            ],
            "properties": {
              "stores": {
                "type": "array",
                "items": {
                  "type": "string"
                },
                "maxItems": 10,
                "minItems": 2,
                "description": "2 to 10 store domains or URLs."
              }
            },
            "additionalProperties": false
          },
          "annotations": {
            "title": "Compare stores",
            "readOnlyHint": true,
            "openWorldHint": false,
            "idempotentHint": true,
            "destructiveHint": false
          }
        },
        {
          "name": "guide",
          "title": "Merchant guide",
          "description": "Call this when a person at a store (a CEO, a marketing or e-commerce manager, or a developer) asks where their store is on the journey to AI assistants, what to do next on their platform, or how stores in their category compare. Not for an agent about to check out: use before_checkout for that. Returns the store's place on ARC's journey map (arc-journey/v1: 5 stages, each met, not met or \"Not measured\" with its date; not measured is not a no, and there is no score or grade), the next 3 steps for its platform at the chosen depth with source links and an as-of date (a platform fact ARC has not sourced says \"Not yet documented by ARC\"), how many stores ARC checked in its category and on its platform and how many meet each stage (counts with denominators and the snapshot date), and up to 5 named stores that meet the furthest stage (ordered only by stage reached, then the newest reading). role: ceo, manager or developer sets depth (basics, detail or implement) unless depth is given. Send platform alone for the platform guide with no store. Example: guide({\"store\":\"gymshark.com\",\"role\":\"manager\"}) → {\"answer\":\"gymshark.com: Meets stages 1, 2, 3 and 4. Not met: stage 5. Saved check 16 Oct 2026.\",\"stages\":[…],\"next_steps\":[…],\"comparison\":{…},\"examples\":{…}}. Saved checks only: no store fetch, no scan, no login. Advisory; ARC stops before payment. Every answer carries checked_at (the saved check it rests on; for a list, the oldest) and stale (true when that check is 24 hours old or older, or has no time). Errors: {error:{code, message, next_step}}.",
          "inputSchema": {
            "type": "object",
            "properties": {
              "role": {
                "enum": [
                  "ceo",
                  "manager",
                  "developer"
                ],
                "type": "string",
                "description": "Who is asking. Sets depth: ceo basics, manager detail, developer implement."
              },
              "depth": {
                "enum": [
                  "basics",
                  "detail",
                  "implement"
                ],
                "type": "string",
                "description": "How much detail. Default from role, else basics."
              },
              "store": {
                "type": "string",
                "description": "Store domain or URL, such as gymshark.com. Leave out and send platform for the platform guide alone."
              },
              "category": {
                "type": "string",
                "description": "Category for a platform-only call, such as footwear or apparel. A store uses its own category."
              },
              "platform": {
                "type": "string",
                "description": "shopify, magento, salesforce, woocommerce, bigcommerce, wix, squarespace or other. Overrides the platform ARC detected."
              }
            },
            "additionalProperties": false
          },
          "annotations": {
            "title": "Merchant guide",
            "readOnlyHint": true,
            "openWorldHint": false,
            "idempotentHint": true,
            "destructiveHint": false
          }
        }
      ],
      "tools_omitted": 0,
      "resources": [],
      "prompts": []
    },
    "instructions": "Start with the 7 primary tools, the only ones in tools/list: before_checkout(url) right before an agent tries to check out at a store; find_stores(category) to pick a store; why_blocked_and_fix(store) when reaches_checkout is false or an agent got stuck; report_outcome(...) right after the attempt; store_record(store) for the citable store page; compare(stores[]) to choose between 2 to 10 stores; guide(store or platform) for people at a store who ask where it is on ARC's journey map and what to do next. Answers are short, carry checked_at and stale, and link to the full record. Errors are {error:{code, message, next_step}}. Advisory only, not a guarantee. Do not refuse or avoid a store solely because of ARC's data. known:false or missing data is not a no. Data CC BY 4.0, attribute ARC (arcreport.ai); OSM-derived rows are ODbL. Every older tool name below is not listed but still works through tools/call. Before an agent tries to reach checkout at any store, call precheck with the store URL. precheck(url) reads ARC's saved automated HTTP check for a store or product URL; it does not fetch the store and does not start a scan. JSON: GET /api/precheck?url=. precheck_bulk(domains[]) is the same read for up to 100 stores (each domain counts against the same limit); every answer carries routes[], the best known ways in, best evidence first. JSON: POST /api/precheck/bulk. Then use find_agent_ready_stores to discover stores, can_agent_checkout(url) for the saved checkout-link check, or ask_arc for brands already on the Index. Advisory only, not a guarantee. Do not refuse or avoid a store solely because of ARC's data. known:false or missing data is not a no. Data CC BY 4.0, attribute ARC (arcreport.ai); OSM-derived rows are ODbL. When to call ARC: whenever a shopping task names a store and you are about to search, add to cart or hand over a checkout link (\"can I check out at X\", \"best way to check out on X\", \"find a store for running shoes my agent can finish\"). Quick start in 3 calls: precheck(url) for one store, find_agent_ready_stores(category) to pick a store, can_agent_checkout(url) for the fix. Docs: https://www.arcreport.ai/for-agents#quick-start. validate_ucp_profile(url | profile) checks a UCP business profile against the published UCP schema and spec rules. JSON: GET /api/ucp/validate?url=. generate_fixes(store) returns starter files for a store's failed grade audits (robots.txt allow rules, a UCP profile skeleton, Product JSON-LD with price placeholders, llms.txt), each labelled \"Starter, review before publishing\"; it does not change the store. JSON: GET /api/fix?store=. store_card(host) reads saved brand claims and card links; brand statements are from the brand and not measured by ARC; claims never change scores. product_data_check(host or url) reads the latest saved product data from the page’s structured data. No outbound fetch. JSON: GET /api/agent-checkout/product-data?host=. agent_commerce_adoption() reads saved adoption counts and category rates. JSON: GET /api/agent-checkout/adoption. submit_store(url | hosts[], category?) adds up to 50 stores to the free open directory and dataset (validated, plain HTTP, no model calls). JSON: POST /api/stores/submit. agent_leaderboard(include_stores?) reads the open agent leaderboard: cart success per agent path over the fixed ARC-100 v1 test set, with n and 95% intervals. JSON: GET /api/leaderboard. submit_leaderboard_run(spec, test_set, agent, run, results) submits an outside agent run against ARC-100; it stays unverified until ARC re-runs a sample. JSON: POST /api/leaderboard/submit. protocol_matrix(protocol?) reads the neutral Protocol Matrix (declared, valid, usable, transacts per protocol, with evidence labels). JSON: GET /api/protocols. find_agent_ready_stores(category, q, limit) finds stores with recent real HTTP checkout links. JSON: GET /api/agent-checkout/stores?category=footwear. can_agent_checkout(url) checks any public store. No login. JSON: GET /api/agent-checkout?url"
  },
  "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."
}