{
  "fixes": {
    "slug": "buffer",
    "name": "Buffer API + MCP",
    "listing": "https://www.anchorterminal.com/tools/buffer",
    "markdown": "# Fix list: Buffer API + MCP\n\nFrom Anchor Terminal's listing at https://www.anchorterminal.com/tools/buffer, the October 2026 research run, assessed 1 October 2026. Grade B, 62.3 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 Buffer 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, 55 out of 100, up to 9 more on the total\n\nWhy it scored 55: Status page at status.buffer.com with publishing, login, dashboard, analytics and Buffer MCP components (20). It logged 22 incidents between 6 July and 25 September 2026, several of them major. Facebook publishing failed for about 24 hours from 30 July, logins broke for about 4 hours on 10 August and 3 hours on 27 August, the MCP returned 404 for about 7 hours on 6 July, and a service disruption hit on 22 September (0). Limits published per plan, 100 requests per 15 minutes, 250 or 500 a day and 3,000 to 15,000 per 30 days, plus GraphQL complexity and depth caps (15). 429 carries an exact Retry-After, doesn't consume quota, and the docs advise adding jitter. No idempotency key for creating posts, though a DuplicateError type arrived on 29 September (10). 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. 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). Per-channel plan prices are public, with request quotas per plan rather than per-call prices (10). The free plan includes the API, 1 key and 3,000 requests a month with no card (20). A person has to sign up in a browser to get a key (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## 3. Security \u0026 auth, 56 out of 100, up to 7.7 more on the total\n\nWhy it scored 56: Hosted MCP and App Clients use OAuth 2.0 with PKCE and 11 scopes, among them posts:read and insights:read. Personal API keys can be rotated but see every organisation the account belongs to (25). Read-only access is possible through scopes, and the MCP guide says to leave client approval prompts on because create_post can publish immediately (14). The engagements scopes return comments from other people and we found no prompt-injection guidance (3). No audit log or key usage view found (0). buffer.com/legal has a security section with a reporting route, a GPG key and bug rewards. No security.txt per the 30 September check (14).\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. Agent ergonomics, 65 out of 100, up to 5.7 more on the total\n\nWhy it scored 65: 20 MCP tools with no toolsets (15), and GraphQL field selection lets an agent size each response (3). Tag queries are paginated and filterable, and posts can be listed by channel (16). Typed union errors such as InvalidInputError and LimitReachedError say what to fix (18). No idempotency key and, per the docs, no readOnly or destructive annotations. saveToDraft and addToQueue modes keep posts from going out by accident (6). No official SDK in two languages, only the npm CLI (7).\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## 5. Maintenance \u0026 community, 73 out of 100, up to 2.4 more on the total\n\nWhy it scored 73: Last schema change on 30 September 2026 (30). More than 20 dated changelog entries since 27 August (20). Public changelog and email support (12). No official SDKs, only @bufferapp/cli 1.2.2, published on 28 September 2026 (5). The CLI ships from GitHub Actions with npm trusted publishing (6).\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, 86 out of 100, up to 2.3 more on the total\n\nWhy it scored 86: Typed GraphQL schema open to introspection, and the MCP has an introspect_schema tool (25). llms.txt and Markdown versions of every guide (10). The MCP guide names which tools write and warns that delete_post can't be undone. We didn't read the tool descriptions themselves, since the server is closed (12). Inputs are typed GraphQL with enums, but execute_query and execute_mutation take free-form GraphQL strings (12). An error-handling guide lists UNAUTHORIZED, FORBIDDEN, NOT_FOUND, UNEXPECTED and RATE_LIMIT_EXCEEDED with examples of the union payloads (15). Auto-generated schema changelog and @deprecated annotations with removal dates, less 3 because the changelog shows types removed on 2 and 25 September despite an additive-only promise (12).\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, 78 out of 100, up to 1.9 more on the total\n\nMade of editorial 66, provenance 90.\n\nWhy it scored 78: Closed service with published terms (15). Buffer, Inc. of San Francisco. Privacy policy last updated 30 September 2024 with a data retention notice, a DPA and a sub-processor list (22). @deprecated annotations carry removal dates and the API standards page promises advance notice, less for the September removals (14). Sub-processors listed in the GDPR section (15).\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- security.txt: not found (0 of 10)\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- Whether the types removed on 2 and 25 September 2026 were ever usable by API clients\n- Whether the 14-day paid trial needs a card. The pricing page read as yes\n- unchecked: the MCP tool definitions and any annotations, since the server isn't open source\n- The MCP guide documents only the API key, while the server's OAuth metadata lists 11 scopes. We didn't complete an OAuth flow\n\n## Weaknesses\n\n- 22 status incidents between 6 July and 25 September 2026, several of them hours long\n- Low quotas, 100 requests per 15 minutes and 3,000 to 15,000 a month\n- No media upload, every file has to sit at a public URL you host\n- The changelog shows types removed on 2 and 25 September 2026 despite the additive-only promise\n- No official SDKs, no tool annotations and no idempotency keys\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- Call `{ account { organizations { id } } }` first, then list channels for an organisation before posting\n- Include `... on MutationError` in every mutation, since errors come back with HTTP 200\n- On 429, wait Retry-After plus a few seconds of jitter. The 429 itself doesn't cost quota\n- Pass images and video as public direct URLs, not preview or login-gated links\n- Use saveToDraft or addToQueue so nothing publishes by accident, because delete_post can't be undone\n\n## What the review panel asked for\n\n- Upload endpoint\n- Idempotency key on posts\n- document the OAuth path\n- per-organisation keys\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": "B",
    "score": 62.3,
    "assessed": "2026-10-01",
    "run": "October 2026 research run",
    "categories": [
      {
        "key": "reliability",
        "name": "Reliability",
        "score": 55,
        "maxGain": 9,
        "reason": "Status page at status.buffer.com with publishing, login, dashboard, analytics and Buffer MCP components (20). It logged 22 incidents between 6 July and 25 September 2026, several of them major. Facebook publishing failed for about 24 hours from 30 July, logins broke for about 4 hours on 10 August and 3 hours on 27 August, the MCP returned 404 for about 7 hours on 6 July, and a service disruption hit on 22 September (0). Limits published per plan, 100 requests per 15 minutes, 250 or 500 a day and 3,000 to 15,000 per 30 days, plus GraphQL complexity and depth caps (15). 429 carries an exact Retry-After, doesn't consume quota, and the docs advise adding jitter. No idempotency key for creating posts, though a DuplicateError type arrived on 29 September (10). 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": "payments",
        "name": "Payments \u0026 pricing",
        "score": 30,
        "maxGain": 8.8,
        "reason": "No x402 or other machine payment (0). Per-channel plan prices are public, with request quotas per plan rather than per-call prices (10). The free plan includes the API, 1 key and 3,000 requests a month with no card (20). A person has to sign up in a browser to get a key (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": "security",
        "name": "Security \u0026 auth",
        "score": 56,
        "maxGain": 7.7,
        "reason": "Hosted MCP and App Clients use OAuth 2.0 with PKCE and 11 scopes, among them posts:read and insights:read. Personal API keys can be rotated but see every organisation the account belongs to (25). Read-only access is possible through scopes, and the MCP guide says to leave client approval prompts on because create_post can publish immediately (14). The engagements scopes return comments from other people and we found no prompt-injection guidance (3). No audit log or key usage view found (0). buffer.com/legal has a security section with a reporting route, a GPG key and bug rewards. No security.txt per the 30 September check (14).",
        "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": "ergonomics",
        "name": "Agent ergonomics",
        "score": 65,
        "maxGain": 5.7,
        "reason": "20 MCP tools with no toolsets (15), and GraphQL field selection lets an agent size each response (3). Tag queries are paginated and filterable, and posts can be listed by channel (16). Typed union errors such as InvalidInputError and LimitReachedError say what to fix (18). No idempotency key and, per the docs, no readOnly or destructive annotations. saveToDraft and addToQueue modes keep posts from going out by accident (6). No official SDK in two languages, only the npm CLI (7).",
        "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": "maintenance",
        "name": "Maintenance \u0026 community",
        "score": 73,
        "maxGain": 2.4,
        "reason": "Last schema change on 30 September 2026 (30). More than 20 dated changelog entries since 27 August (20). Public changelog and email support (12). No official SDKs, only @bufferapp/cli 1.2.2, published on 28 September 2026 (5). The CLI ships from GitHub Actions with npm trusted publishing (6).",
        "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": 86,
        "maxGain": 2.3,
        "reason": "Typed GraphQL schema open to introspection, and the MCP has an introspect_schema tool (25). llms.txt and Markdown versions of every guide (10). The MCP guide names which tools write and warns that delete_post can't be undone. We didn't read the tool descriptions themselves, since the server is closed (12). Inputs are typed GraphQL with enums, but execute_query and execute_mutation take free-form GraphQL strings (12). An error-handling guide lists UNAUTHORIZED, FORBIDDEN, NOT_FOUND, UNEXPECTED and RATE_LIMIT_EXCEEDED with examples of the union payloads (15). Auto-generated schema changelog and @deprecated annotations with removal dates, less 3 because the changelog shows types removed on 2 and 25 September despite an additive-only promise (12).",
        "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": 78,
        "maxGain": 1.9,
        "reason": "Closed service with published terms (15). Buffer, Inc. of San Francisco. Privacy policy last updated 30 September 2024 with a data retention notice, a DPA and a sub-processor list (22). @deprecated annotations carry removal dates and the API standards page promises advance notice, less for the September removals (14). Sub-processors listed in the GDPR section (15).",
        "blend": "editorial 66, provenance 90",
        "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": "security.txt",
        "value": "not found",
        "points": 0,
        "max": 10
      }
    ],
    "unchecked": [
      "Whether the types removed on 2 and 25 September 2026 were ever usable by API clients",
      "Whether the 14-day paid trial needs a card. The pricing page read as yes",
      "unchecked: the MCP tool definitions and any annotations, since the server isn't open source",
      "The MCP guide documents only the API key, while the server's OAuth metadata lists 11 scopes. We didn't complete an OAuth flow"
    ],
    "weaknesses": [
      "22 status incidents between 6 July and 25 September 2026, several of them hours long",
      "Low quotas, 100 requests per 15 minutes and 3,000 to 15,000 a month",
      "No media upload, every file has to sit at a public URL you host",
      "The changelog shows types removed on 2 and 25 September 2026 despite the additive-only promise",
      "No official SDKs, no tool annotations and no idempotency keys"
    ],
    "agentNotes": [
      "Call `{ account { organizations { id } } }` first, then list channels for an organisation before posting",
      "Include `... on MutationError` in every mutation, since errors come back with HTTP 200",
      "On 429, wait Retry-After plus a few seconds of jitter. The 429 itself doesn't cost quota",
      "Pass images and video as public direct URLs, not preview or login-gated links",
      "Use saveToDraft or addToQueue so nothing publishes by accident, because delete_post can't be undone"
    ],
    "requests": [
      {
        "text": "Upload endpoint",
        "reviews": 1
      },
      {
        "text": "Idempotency key on posts",
        "reviews": 1
      },
      {
        "text": "document the OAuth path",
        "reviews": 1
      },
      {
        "text": "per-organisation keys",
        "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"
  }
}