{
  "fixes": {
    "slug": "metricool",
    "name": "Metricool API + MCP",
    "listing": "https://www.anchorterminal.com/tools/metricool",
    "markdown": "# Fix list: Metricool API + MCP\n\nFrom Anchor Terminal's listing at https://www.anchorterminal.com/tools/metricool, the October 2026 research run, assessed 1 October 2026. Grade E, 38.7 out of 100.\n\nThis is everything the published grade says the listing lacks, the biggest possible gain to the total first. It comes from the reason given for each score, the checklist each category was scored against (https://www.anchorterminal.com/benchmark/#checklist), the provenance checks, the deductions, what we couldn't check and what the review panel asked for. A fix counts at the next check, once it's public.\n\nFor a coding agent working on Metricool API + MCP: work through the items below in the product, its docs and its public pages. Each category gives the reason for its score, with the points each checklist item earned, and the checklist itself, so the gap is the items that earned less than their points. Change the product, not the wording, and keep a note of what you changed and where it's published.\n\n## 1. Reliability, 35 out of 100, up to 13 more on the total\n\nWhy it scored 35: A status page at status.metricool.com, per the 30 September check (20). Its robots.txt blocked our reader on 1 and 2 October, for the page, its history and the incident API, and the statuspage.io mirror too, so we have no readable history. That's our limit, not proof of a clean record. IsDown's Metricool page lists three entries since December 2025, all in June 2026, but shows no components and reads like user reports, so we don't treat it as a mirror (5). No rate limits published. The API guide, the errors page and the MCP limits page give plan caps (20 scheduled posts and 30 days of analytics on Free) but no request limits (0). No 429 or retry guidance found (0). No SLA found (0). The API and MCP aren't labelled beta (10).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-reliability):\n\nHosted APIs, MCP servers, models and platforms.\n\n- 20, a public status page with component history (Statuspage, Instatus, BetterStack or the vendor's own).\n- 0 to 30, the incident record for the last 90 days on that page. 30 for a clean record or trivial incidents only, 20 for minor incidents only, 10 for one major outage (an hour or more of a core API down, or errors across the board), 0 for several. 5 when there's no history we could read, and the note says so.\n- 15, rate limits documented with numbers.\n- 15, documented 429 or overload handling (Retry-After, backoff guidance), and idempotency keys or safe-retry guidance where writes are involved.\n- 10, an SLA published for any paid tier.\n- 10, the surface agents use is generally available, not beta or preview.\n\nLocal packages, SDKs, frameworks and stdio MCP servers.\n\n- 20, installs from an official package with supported runtimes stated.\n- 25, a public CI and test suite, passing on the default branch.\n- 0 to 25, open crash or regression issues relative to activity (25 for few and handled, 0 for many, old and unanswered).\n- 15, semver discipline and breaking changes called out in a changelog.\n- 15, version 1.0 or later, or declared stable.\n\nProtocols are read from their reference implementations, the public facilitators or servers, spec stability and test vectors.\n\n## 2. Agent ergonomics, 39 out of 100, up to 9.9 more on the total\n\nWhy it scored 39: The help centre's MCP basics page lists six hosted tools, four that read (metrics, analytics, best time, scheduled posts) and two that write (create and update a scheduled post). We couldn't read their definitions without an OAuth session, and the older PyPI package lists 28 (20). Analytics take date ranges. We didn't verify pagination or field selection (8). Two documented error cases, no codes an agent can act on (5). No idempotency or tool annotations found, though the MCP can submit a post for review instead of scheduling it (3). No SDKs, and three values per REST call (3).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-ergonomics):\n\n- 0 to 25, context cost. For MCP, the number and size of the tool definitions (25 for ten or fewer compact tools, 15 for 11 to 30, 5 for more than 30, plus up to 10 back for toolsets, dynamic loading or read-only subsets). For APIs, whether responses can be sized (field selection, limits, summaries).\n- 20, pagination, filtering and output-size controls.\n- 20, actionable, documented error responses, codes and messages an agent can recover from.\n- 20, idempotency or safe retries, and for MCP the `readOnlyHint` and `destructiveHint` annotations.\n- 15, sensible defaults, few required parameters, and official SDKs in at least two languages.\n\nModels are read for tool use, structured output, prompt caching, context length, batch and SDKs. Frameworks for how much code and how many defaults a tool-calling agent with MCP needs.\n\n## 3. Security \u0026 auth, 48 out of 100, up to 9.1 more on the total\n\nWhy it scored 48: REST takes one account token in the X-Mc-Auth header, not the query string, plus userId and blogId. The token has no scopes, but Advanced and Custom accounts can regenerate it in settings, which invalidates the old one at once. The hosted MCP uses OAuth with mcp:read and mcp:write scopes, and access can be revoked from the client (25). mcp:read gives a read-only session, and posts can go to review rather than out (12). Competitor and analytics data is mostly the account's own, with little untrusted text, and no injection guidance (8). No audit log found (0). The privacy policy names a DPO. No security.txt, disclosure route or certification found (3).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-security):\n\n- 0 to 30, the credential model. 30 for OAuth 2.1 with scopes, or scoped and revocable keys with rotation. 20 for plain revocable API keys. 10 for one all-powerful key. 10 off when a secret can travel in a URL query string as a documented option.\n- 0 to 20, read-only or least-privilege modes, and confirmation or approval for destructive actions.\n- 0 to 15, prompt-injection posture where the tool returns untrusted content (documented mitigations or guidance). A tool that returns no untrusted content gets 10.\n- 0 to 15, audit logs or per-call visibility for the operator.\n- 0 to 20, a security programme. security.txt or a disclosure policy, a bug bounty, SOC 2 or ISO 27001, advisories handled in public.\n\nModels are read for retention, whether API data trains models (and whether that's off by default), zero-retention options and certifications. Frameworks for telemetry defaults, approval hooks, guardrails and sandboxing.\n\n## 4. Payments \u0026 pricing, 30 out of 100, up to 8.8 more on the total\n\nWhy it scored 30: No x402 or other machine payment (0). Plan prices are public, with no per-call price (10). The Free plan includes the MCP for 1 brand without a card, though the REST API needs Advanced (20). A person has to sign up in a browser (0).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-payments):\n\nThe published rubric, also on the [x402 page](https://www.anchorterminal.com/x402/).\n\n- 40, a machine payment protocol (x402, MPP or L402) on the tool's own endpoints. 10 to 30 when it covers only some endpoints or only goes through a third party, and the note says which.\n- 20, per-call or per-unit pricing published without a login. 10 for public plan-only pricing, 0 for \"contact sales\" or prices behind a login.\n- 20, a free tier or trial that doesn't need a card.\n- 20, autonomous onboarding, meaning an agent can get access without a person signing up in a browser (keyless use, x402, a programmatic key API).\n\nPayment platforms and agent wallets rarely charge for their own API over a machine protocol, so the first line has steps for them, and the highest one that applies counts. 40 when x402, MPP or L402 runs on all their own endpoints, 30 when it runs on part of their own API, 25 when their merchants can accept one, 20 for running a facilitator, 15 for paying as a buyer, and 0 when the only protocol is their own. Merchant acceptance sits above a facilitator because the platform's own customers can charge agents through it, while a facilitator settles for sellers who wire up the protocol themselves. The counter-argument (a facilitator does more for the protocol as a whole) has a point. Each note says which step applied.\n\nOpen-source software you run yourself is scored on its hosted or paid option if it has one. A free, self-hosted package with nothing to buy gets 20, 20 and 20 for the last three lines, and 0 to 40 for the first only if it ships a payment protocol.\n\n## 5. Maintenance \u0026 community, 6 out of 100, up to 8.2 more on the total\n\nWhy it scored 6: No dated API or MCP change found. The PyPI server mcp-metricool is still at 1.1.9 from 7 October 2025 (0). No releases or dated changelog entries in the last 90 days (0). No public API changelog. The help centre's MCP pages were updated in late September 2026 and support exists (6). No official SDKs or registry entry (0). The GitHub repo the help centre names isn't public. The metricool organisation's only public repository is a fork of modelcontextprotocol/servers, last updated 13 May 2025 (0).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-maintenance):\n\n- 0 to 30, time since the last release, or the last published model or API change for a closed service. 30 within 30 days, 20 within 90, 10 within 180, 0 older.\n- 20, at least three releases or dated changelog entries in the last 90 days.\n- 0 to 25, responsiveness. Issues and pull requests answered on GitHub (the open issues and how recent the replies are). For closed services, a public changelog and a support or community channel that answers, 0 to 15.\n- 15, presence in the official MCP registry under a verified namespace (MCP servers), or current official SDKs (APIs and models).\n- 10, package health, current dependencies and CI.\n\nModels are read for deprecation notice periods and model churn rather than release counts.\n\n## 6. Schema \u0026 documentation, 56 out of 100, up to 7.2 more on the total\n\nWhy it scored 56: OpenAPI 3.0 at app.metricool.com/api/swagger.json covering 553 paths, per the 30 September check. On 1 and 2 October app.metricool.com answered our reader's robots.txt request with an HTTP 500, so neither the spec nor the API docs page could be re-read (25). llms.txt on the help centre, re-read on 2 October (10). The help centre explains what the MCP can and can't do, and the MCP tools are closed source, so we didn't read their descriptions (8). Typed parameters per the spec, but every call also needs userId and blogId (8). The errors page documents two cases, access denied and posts scheduled without media (5). No API or MCP changelog. The only changelog in the help centre's llms.txt is for the Looker Studio connector (0).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-schema):\n\nAPIs and MCP servers.\n\n- 25, a machine-readable contract (a public OpenAPI file or similar; for MCP, typed JSON Schema inputs on every tool).\n- 10, llms.txt or Markdown docs served for agents.\n- 0 to 20, descriptions that say what a tool is for, when to use it and when not to, read from the tool definitions in the source or the API reference.\n- 0 to 15, typed inputs with enums, constraints and required fields, and no free-form JSON blobs.\n- 0 to 15, examples and documented error responses.\n- 15, versioning and a public changelog.\n\nModels are read from the API reference, the OpenAPI file, llms.txt, the structured-output and tool-use docs and the model cards. Frameworks from docs a model can follow, typed interfaces, examples and the API reference.\n\n## 7. Transparency \u0026 trust, 64 out of 100, up to 3.2 more on the total\n\nMade of editorial 47, provenance 80.\n\nWhy it scored 64: Closed service with published terms from METRICOOL SOFTWARE, SL of Madrid, part of the team.blue group (15). Privacy policy says all data sits on EU servers, gives statutory retention periods of 4 to 6 years and folds a DPA into the service terms. A signed DPA is available on request from legal@metricool.com, with deletion or return of data when the contract ends. Processors are named only by category (22). No deprecation policy or dated notices found (0). Data location stated, subprocessors not named (10).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-transparency):\n\n- 0 to 30, source availability and licence clarity. 30 for open source under an OSI licence, 15 for closed with clear terms, 0 for unclear terms.\n- 0 to 30, data handling and retention statements that agree with each other (privacy policy, DPA, retention periods, subprocessors).\n- 0 to 20, a deprecation policy or notices with dates.\n- 0 to 20, telemetry disclosed with an opt-out (local software), or subprocessors and data locations disclosed (hosted).\n\nThe other half of Transparency and trust is the provenance score, computed from checked facts (below). The category score is the mean of the two.\n\nProvenance checks not met in full (half of this category, computed from checked facts):\n\n- Changelog: not found (0 of 10)\n- security.txt: not found (0 of 10)\n\n## Deductions\n\nEach comes off the total. A fixed and documented problem counts for less at the next check.\n\n- 2026-10-01. The help centre says the Metricool MCP server is public at metricool/mcp-metricool on GitHub. That repo returned 404 on 30 September and asked for credentials on 1 and 2 October, and the metricool organisation page lists one public repository, a fork of modelcontextprotocol/servers. The open-source claim doesn't hold for readers. -2 (https://help.metricool.com/faqs-about-the-metricool-mcp-1i3w0, https://github.com/metricool)\n\n## What we couldn't check\n\nWhat we couldn't read counted as absent. Publishing it on a page a plain HTTP fetch can read (not only in a browser) lets the next check count it.\n\n- unchecked: status history. status.metricool.com and metricool.statuspage.io both block our reader through robots.txt, and IsDown's page doesn't mirror the official components, so reliability counts 5 for history\n- unchecked: the OpenAPI spec, still unreadable on 2 October because app.metricool.com answers robots.txt with HTTP 500, so path count and error schemas rely on the 30 September check\n- unchecked: the hosted MCP's tool definitions and annotations, which need an OAuth session. The help centre names six tools\n- The help centre still calls metricool/mcp-metricool a public repo. It isn't public on 2 October, whether private, deleted or moved\n\n## Weaknesses\n\n- REST API only on Advanced ($67 a month) and Custom\n- No published rate limits, 429 guidance or API changelog\n- Three values on every REST call (the X-Mc-Auth token, userId and blogId)\n- PyPI MCP package still at 1.1.9 from 7 October 2025, and the GitHub repo the help centre names isn't public\n- No security disclosure route or certification found\n\n## What costs an agent a turn today\n\nThe notes we give agents before they call it. Each one is a workaround an agent shouldn't need.\n\n- Connect the hosted MCP at https://ai.metricool.com/mcp with OAuth, and ask only for mcp:read when the job is reporting\n- Call admin/simpleProfiles with your userId to list brands and their blogId values\n- Normalise media through `actions/normalize/image/url` first, or the post goes out without it\n- Give publicationDate a dateTime and an IANA timezone, in the future\n- Back off on your own, since no rate limits or Retry-After are documented\n\n## What the review panel asked for\n\n- Reject un-normalised media\n- Publish rate limits\n- publish the MCP source\n- publish a security.txt\n\n## When it's done\n\nSend what changed and where it's published as a dispute (https://www.anchorterminal.com/builders/#disputes, or `POST https://www.anchorterminal.com/api/v1/contact` with `\"kind\": \"dispute\"`). Disputes are answered in public, and the listing is checked again by the same checklist. Paying for an audit or a listing claim changes nothing here.\n",
    "grade": "E",
    "score": 38.7,
    "assessed": "2026-10-01",
    "run": "October 2026 research run",
    "categories": [
      {
        "key": "reliability",
        "name": "Reliability",
        "score": 35,
        "maxGain": 13,
        "reason": "A status page at status.metricool.com, per the 30 September check (20). Its robots.txt blocked our reader on 1 and 2 October, for the page, its history and the incident API, and the statuspage.io mirror too, so we have no readable history. That's our limit, not proof of a clean record. IsDown's Metricool page lists three entries since December 2025, all in June 2026, but shows no components and reads like user reports, so we don't treat it as a mirror (5). No rate limits published. The API guide, the errors page and the MCP limits page give plan caps (20 scheduled posts and 30 days of analytics on Free) but no request limits (0). No 429 or retry guidance found (0). No SLA found (0). The API and MCP aren't labelled beta (10).",
        "checklist": [
          "Hosted APIs, MCP servers, models and platforms.",
          "- 20, a public status page with component history (Statuspage, Instatus, BetterStack or the vendor's own).\n- 0 to 30, the incident record for the last 90 days on that page. 30 for a clean record or trivial incidents only, 20 for minor incidents only, 10 for one major outage (an hour or more of a core API down, or errors across the board), 0 for several. 5 when there's no history we could read, and the note says so.\n- 15, rate limits documented with numbers.\n- 15, documented 429 or overload handling (Retry-After, backoff guidance), and idempotency keys or safe-retry guidance where writes are involved.\n- 10, an SLA published for any paid tier.\n- 10, the surface agents use is generally available, not beta or preview.",
          "Local packages, SDKs, frameworks and stdio MCP servers.",
          "- 20, installs from an official package with supported runtimes stated.\n- 25, a public CI and test suite, passing on the default branch.\n- 0 to 25, open crash or regression issues relative to activity (25 for few and handled, 0 for many, old and unanswered).\n- 15, semver discipline and breaking changes called out in a changelog.\n- 15, version 1.0 or later, or declared stable.",
          "Protocols are read from their reference implementations, the public facilitators or servers, spec stability and test vectors."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-reliability"
      },
      {
        "key": "ergonomics",
        "name": "Agent ergonomics",
        "score": 39,
        "maxGain": 9.9,
        "reason": "The help centre's MCP basics page lists six hosted tools, four that read (metrics, analytics, best time, scheduled posts) and two that write (create and update a scheduled post). We couldn't read their definitions without an OAuth session, and the older PyPI package lists 28 (20). Analytics take date ranges. We didn't verify pagination or field selection (8). Two documented error cases, no codes an agent can act on (5). No idempotency or tool annotations found, though the MCP can submit a post for review instead of scheduling it (3). No SDKs, and three values per REST call (3).",
        "checklist": [
          "- 0 to 25, context cost. For MCP, the number and size of the tool definitions (25 for ten or fewer compact tools, 15 for 11 to 30, 5 for more than 30, plus up to 10 back for toolsets, dynamic loading or read-only subsets). For APIs, whether responses can be sized (field selection, limits, summaries).\n- 20, pagination, filtering and output-size controls.\n- 20, actionable, documented error responses, codes and messages an agent can recover from.\n- 20, idempotency or safe retries, and for MCP the `readOnlyHint` and `destructiveHint` annotations.\n- 15, sensible defaults, few required parameters, and official SDKs in at least two languages.",
          "Models are read for tool use, structured output, prompt caching, context length, batch and SDKs. Frameworks for how much code and how many defaults a tool-calling agent with MCP needs."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-ergonomics"
      },
      {
        "key": "security",
        "name": "Security \u0026 auth",
        "score": 48,
        "maxGain": 9.1,
        "reason": "REST takes one account token in the X-Mc-Auth header, not the query string, plus userId and blogId. The token has no scopes, but Advanced and Custom accounts can regenerate it in settings, which invalidates the old one at once. The hosted MCP uses OAuth with mcp:read and mcp:write scopes, and access can be revoked from the client (25). mcp:read gives a read-only session, and posts can go to review rather than out (12). Competitor and analytics data is mostly the account's own, with little untrusted text, and no injection guidance (8). No audit log found (0). The privacy policy names a DPO. No security.txt, disclosure route or certification found (3).",
        "checklist": [
          "- 0 to 30, the credential model. 30 for OAuth 2.1 with scopes, or scoped and revocable keys with rotation. 20 for plain revocable API keys. 10 for one all-powerful key. 10 off when a secret can travel in a URL query string as a documented option.\n- 0 to 20, read-only or least-privilege modes, and confirmation or approval for destructive actions.\n- 0 to 15, prompt-injection posture where the tool returns untrusted content (documented mitigations or guidance). A tool that returns no untrusted content gets 10.\n- 0 to 15, audit logs or per-call visibility for the operator.\n- 0 to 20, a security programme. security.txt or a disclosure policy, a bug bounty, SOC 2 or ISO 27001, advisories handled in public.",
          "Models are read for retention, whether API data trains models (and whether that's off by default), zero-retention options and certifications. Frameworks for telemetry defaults, approval hooks, guardrails and sandboxing."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-security"
      },
      {
        "key": "payments",
        "name": "Payments \u0026 pricing",
        "score": 30,
        "maxGain": 8.8,
        "reason": "No x402 or other machine payment (0). Plan prices are public, with no per-call price (10). The Free plan includes the MCP for 1 brand without a card, though the REST API needs Advanced (20). A person has to sign up in a browser (0).",
        "checklist": [
          "The published rubric, also on the [x402 page](https://www.anchorterminal.com/x402/).",
          "- 40, a machine payment protocol (x402, MPP or L402) on the tool's own endpoints. 10 to 30 when it covers only some endpoints or only goes through a third party, and the note says which.\n- 20, per-call or per-unit pricing published without a login. 10 for public plan-only pricing, 0 for \"contact sales\" or prices behind a login.\n- 20, a free tier or trial that doesn't need a card.\n- 20, autonomous onboarding, meaning an agent can get access without a person signing up in a browser (keyless use, x402, a programmatic key API).",
          "Payment platforms and agent wallets rarely charge for their own API over a machine protocol, so the first line has steps for them, and the highest one that applies counts. 40 when x402, MPP or L402 runs on all their own endpoints, 30 when it runs on part of their own API, 25 when their merchants can accept one, 20 for running a facilitator, 15 for paying as a buyer, and 0 when the only protocol is their own. Merchant acceptance sits above a facilitator because the platform's own customers can charge agents through it, while a facilitator settles for sellers who wire up the protocol themselves. The counter-argument (a facilitator does more for the protocol as a whole) has a point. Each note says which step applied.",
          "Open-source software you run yourself is scored on its hosted or paid option if it has one. A free, self-hosted package with nothing to buy gets 20, 20 and 20 for the last three lines, and 0 to 40 for the first only if it ships a payment protocol."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-payments"
      },
      {
        "key": "maintenance",
        "name": "Maintenance \u0026 community",
        "score": 6,
        "maxGain": 8.2,
        "reason": "No dated API or MCP change found. The PyPI server mcp-metricool is still at 1.1.9 from 7 October 2025 (0). No releases or dated changelog entries in the last 90 days (0). No public API changelog. The help centre's MCP pages were updated in late September 2026 and support exists (6). No official SDKs or registry entry (0). The GitHub repo the help centre names isn't public. The metricool organisation's only public repository is a fork of modelcontextprotocol/servers, last updated 13 May 2025 (0).",
        "checklist": [
          "- 0 to 30, time since the last release, or the last published model or API change for a closed service. 30 within 30 days, 20 within 90, 10 within 180, 0 older.\n- 20, at least three releases or dated changelog entries in the last 90 days.\n- 0 to 25, responsiveness. Issues and pull requests answered on GitHub (the open issues and how recent the replies are). For closed services, a public changelog and a support or community channel that answers, 0 to 15.\n- 15, presence in the official MCP registry under a verified namespace (MCP servers), or current official SDKs (APIs and models).\n- 10, package health, current dependencies and CI.",
          "Models are read for deprecation notice periods and model churn rather than release counts."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-maintenance"
      },
      {
        "key": "schema",
        "name": "Schema \u0026 documentation",
        "score": 56,
        "maxGain": 7.2,
        "reason": "OpenAPI 3.0 at app.metricool.com/api/swagger.json covering 553 paths, per the 30 September check. On 1 and 2 October app.metricool.com answered our reader's robots.txt request with an HTTP 500, so neither the spec nor the API docs page could be re-read (25). llms.txt on the help centre, re-read on 2 October (10). The help centre explains what the MCP can and can't do, and the MCP tools are closed source, so we didn't read their descriptions (8). Typed parameters per the spec, but every call also needs userId and blogId (8). The errors page documents two cases, access denied and posts scheduled without media (5). No API or MCP changelog. The only changelog in the help centre's llms.txt is for the Looker Studio connector (0).",
        "checklist": [
          "APIs and MCP servers.",
          "- 25, a machine-readable contract (a public OpenAPI file or similar; for MCP, typed JSON Schema inputs on every tool).\n- 10, llms.txt or Markdown docs served for agents.\n- 0 to 20, descriptions that say what a tool is for, when to use it and when not to, read from the tool definitions in the source or the API reference.\n- 0 to 15, typed inputs with enums, constraints and required fields, and no free-form JSON blobs.\n- 0 to 15, examples and documented error responses.\n- 15, versioning and a public changelog.",
          "Models are read from the API reference, the OpenAPI file, llms.txt, the structured-output and tool-use docs and the model cards. Frameworks from docs a model can follow, typed interfaces, examples and the API reference."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-schema"
      },
      {
        "key": "transparency",
        "name": "Transparency \u0026 trust",
        "score": 64,
        "maxGain": 3.2,
        "reason": "Closed service with published terms from METRICOOL SOFTWARE, SL of Madrid, part of the team.blue group (15). Privacy policy says all data sits on EU servers, gives statutory retention periods of 4 to 6 years and folds a DPA into the service terms. A signed DPA is available on request from legal@metricool.com, with deletion or return of data when the contract ends. Processors are named only by category (22). No deprecation policy or dated notices found (0). Data location stated, subprocessors not named (10).",
        "blend": "editorial 47, provenance 80",
        "checklist": [
          "- 0 to 30, source availability and licence clarity. 30 for open source under an OSI licence, 15 for closed with clear terms, 0 for unclear terms.\n- 0 to 30, data handling and retention statements that agree with each other (privacy policy, DPA, retention periods, subprocessors).\n- 0 to 20, a deprecation policy or notices with dates.\n- 0 to 20, telemetry disclosed with an opt-out (local software), or subprocessors and data locations disclosed (hosted).",
          "The other half of Transparency and trust is the provenance score, computed from checked facts (below). The category score is the mean of the two."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-transparency"
      }
    ],
    "provenance": [
      {
        "label": "Changelog",
        "value": "not found",
        "points": 0,
        "max": 10
      },
      {
        "label": "security.txt",
        "value": "not found",
        "points": 0,
        "max": 10
      }
    ],
    "deductions": [
      "2026-10-01. The help centre says the Metricool MCP server is public at metricool/mcp-metricool on GitHub. That repo returned 404 on 30 September and asked for credentials on 1 and 2 October, and the metricool organisation page lists one public repository, a fork of modelcontextprotocol/servers. The open-source claim doesn't hold for readers. -2 (https://help.metricool.com/faqs-about-the-metricool-mcp-1i3w0, https://github.com/metricool)"
    ],
    "unchecked": [
      "unchecked: status history. status.metricool.com and metricool.statuspage.io both block our reader through robots.txt, and IsDown's page doesn't mirror the official components, so reliability counts 5 for history",
      "unchecked: the OpenAPI spec, still unreadable on 2 October because app.metricool.com answers robots.txt with HTTP 500, so path count and error schemas rely on the 30 September check",
      "unchecked: the hosted MCP's tool definitions and annotations, which need an OAuth session. The help centre names six tools",
      "The help centre still calls metricool/mcp-metricool a public repo. It isn't public on 2 October, whether private, deleted or moved"
    ],
    "weaknesses": [
      "REST API only on Advanced ($67 a month) and Custom",
      "No published rate limits, 429 guidance or API changelog",
      "Three values on every REST call (the X-Mc-Auth token, userId and blogId)",
      "PyPI MCP package still at 1.1.9 from 7 October 2025, and the GitHub repo the help centre names isn't public",
      "No security disclosure route or certification found"
    ],
    "agentNotes": [
      "Connect the hosted MCP at https://ai.metricool.com/mcp with OAuth, and ask only for mcp:read when the job is reporting",
      "Call admin/simpleProfiles with your userId to list brands and their blogId values",
      "Normalise media through `actions/normalize/image/url` first, or the post goes out without it",
      "Give publicationDate a dateTime and an IANA timezone, in the future",
      "Back off on your own, since no rate limits or Retry-After are documented"
    ],
    "requests": [
      {
        "text": "Reject un-normalised media",
        "reviews": 1
      },
      {
        "text": "Publish rate limits",
        "reviews": 1
      },
      {
        "text": "publish the MCP source",
        "reviews": 1
      },
      {
        "text": "publish a security.txt",
        "reviews": 1
      }
    ],
    "recheck": "https://www.anchorterminal.com/builders/#disputes"
  },
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-10-04",
    "license": "CC-BY-4.0",
    "method": "https://www.anchorterminal.com/benchmark/",
    "methodology": "0.3",
    "openapi": "https://www.anchorterminal.com/openapi.json",
    "preview": false,
    "run": "2026-10-01",
    "runLabel": "October 2026 research run"
  }
}