{
  "fixes": {
    "slug": "post-bridge",
    "name": "Post Bridge API + MCP",
    "listing": "https://www.anchorterminal.com/tools/post-bridge",
    "markdown": "# Fix list: Post Bridge API + MCP\n\nFrom Anchor Terminal's listing at https://www.anchorterminal.com/tools/post-bridge, the October 2026 research run, assessed 1 October 2026. Grade D, 48.5 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 Post Bridge 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: No public status page. status.post-bridge.com answers with a noindex page titled post bridge status that shows our reader only a sign-in link, with no components or history (0). No incident history to read (5). The OpenAPI spec sets 10 requests a second per key and one analytics sync per account every 30 minutes (15). Only the sync endpoint documents a 429, with no Retry-After and no idempotency key. The agent skill does warn that Instagram's 500s often publish anyway, so check before republishing (5). 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, 15 out of 100, up to 10.6 more on the total\n\nWhy it scored 15: No x402 or other machine payment (0). Plan prices are public with $1 a month per account above 99, and no per-call price (10). The pricing FAQ says free users get 5 posts a month, but the plan table shows only paid plans and doesn't say free users get the API. The 7-day trial reads $0.00 due today with no statement on cards, so part credit (5). A person signs up in a browser, or approves OAuth in a client (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, 44 out of 100, up to 9.8 more on the total\n\nWhy it scored 44: The hosted MCP does OAuth with PKCE (S256), dynamic client registration and six scopes, among them posts:read, analytics:read, accounts:read and media:read. It also takes a pb_live_ key as a Bearer header, and the MCP docs document a ?key= URL parameter as an alternative, so less 10 (20). Read-only scopes are possible and is_draft holds posts for review. The skill tells the agent to confirm local file and cron actions with the user (12). Tools return the operator's own posts and analytics, with no inbox or comments (10). list_post_results shows per-platform outcomes, no audit log (2). No security.txt, disclosure route or certification found, only support@post-bridge.com (0).\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, 60 out of 100, up to 6.5 more on the total\n\nWhy it scored 60: 16 compact MCP tools with no toolsets (15). Offset and limit with a next URL, and posts filter by platform and status (20). Errors are plain strings with no codes, though list_post_results gives per-platform outcomes and the skill maps common failure causes (12). No idempotency key and no annotations we could see. is_draft holds a post, and delete_post only touches scheduled or draft posts (6). A zero-dependency Node CLI and no SDKs. Omitting scheduled_at publishes at once (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. Transparency \u0026 trust, 44 out of 100, up to 4.9 more on the total\n\nMade of editorial 45, provenance 42.\n\nWhy it scored 44: The CLI, skills and plugin are MIT. The hosted service runs under terms updated 1 October 2026 that name only Post Bridge with Canadian governing law, no company type or registration, and a 24-hour refund window that the pricing FAQ gives as 7 days (10). The privacy policy dated 3 August 2026 sets retention per data type, deletes personal data within 30 days of account deletion and names Supabase, Cloudflare, Stripe, Trigger.dev, Mailgun and Vercel, with no DPA and no data locations (20). No deprecation policy. The terms promise email notice of changes (3). Subprocessors named, locations not (12).\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- Legal entity named: not found (0 of 20)\n- Domain age: post-bridge.com, registered 2024-09-08 (2 years) (7 of 15)\n- Status page: not found (0 of 10)\n- Changelog: not found (0 of 10)\n- security.txt: not found (0 of 10)\n\n## 6. Schema \u0026 documentation, 72 out of 100, up to 4.6 more on the total\n\nWhy it scored 72: OpenAPI 3.0.0 at api.post-bridge.com/openapi.json covering posts, media, analytics, post results and social accounts (25). llms.txt and llms-full.txt (10). The MCP docs give each of 16 tools one line. The agent-mode skill adds per-platform settings and failure causes such as 75 per cent of TikTok failures being spam restrictions that clear in 24 to 48 hours. We didn't read the hosted tools' own descriptions (12). Platform and status enums and typed DTOs in the spec (12). Errors come back as an error array of strings, and only the sync endpoint documents a 429 (8). Paths sit under /v1 with info.version 1.0, and there's no public changelog beyond the agent-mode commit history (5).\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. Maintenance \u0026 community, 76 out of 100, up to 2.1 more on the total\n\nWhy it scored 76: postbridge-cli 1.1.4 published on 9 September 2026, and the agent-mode repo last changed on 24 September (30). CLI and registry versions 1.1.2, 1.1.3 and 1.1.4 between 6 and 9 September (20). llms.txt says support is answered by the founder within a few hours. The repo has never had a pull request, robots.txt blocked our reader from its issues, and there's no public changelog (8). Official registry entry io.github.jackfriks/post-bridge, latest 1.1.3 on 7 September 2026, under the founder's GitHub namespace (15). The CLI has no dependencies and the repo runs no CI (3).\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## 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- Which legal entity, if any, stands behind Post Bridge. The terms and privacy policy name only Post Bridge, and the npm maintainer is Jack Friks\n- Whether free users get API or MCP access within the 5 posts a month the FAQ mentions, and whether the trial needs a card\n- Whether status.post-bridge.com is a status page behind a sign-in or something else\n- unchecked: open GitHub issues, since robots.txt blocked our reader\n- unchecked: the hosted MCP's tool input schemas and annotations\n\n## Weaknesses\n\n- Publishing only, with no comments, DMs or inbox, and analytics for TikTok, YouTube, Instagram and Facebook only\n- Terms and privacy policy name no legal entity, only Post Bridge under Canadian law\n- No public status page, changelog or security.txt\n- No idempotency key, and the MCP also accepts the API key as a ?key= URL parameter\n- One founder answers support and writes every commit\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 list_social_accounts first, upload media, then create_post. Omit scheduled_at to publish at once\n- Check list_post_results before republishing a failed Instagram post, since Meta 500s often publish anyway\n- Set is_draft true when a person should approve the post\n- Put links for X in a reply, because captions sent to X lose their URLs\n- Stay under 10 requests a second per key, and trigger sync_analytics no more than once every 30 minutes per account\n\n## What the review panel asked for\n\n- Idempotency key on create_post\n- Public status page\n- drop the URL key\n- name the legal entity\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": "D",
    "score": 48.5,
    "assessed": "2026-10-01",
    "run": "October 2026 research run",
    "categories": [
      {
        "key": "reliability",
        "name": "Reliability",
        "score": 35,
        "maxGain": 13,
        "reason": "No public status page. status.post-bridge.com answers with a noindex page titled post bridge status that shows our reader only a sign-in link, with no components or history (0). No incident history to read (5). The OpenAPI spec sets 10 requests a second per key and one analytics sync per account every 30 minutes (15). Only the sync endpoint documents a 429, with no Retry-After and no idempotency key. The agent skill does warn that Instagram's 500s often publish anyway, so check before republishing (5). 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": 15,
        "maxGain": 10.6,
        "reason": "No x402 or other machine payment (0). Plan prices are public with $1 a month per account above 99, and no per-call price (10). The pricing FAQ says free users get 5 posts a month, but the plan table shows only paid plans and doesn't say free users get the API. The 7-day trial reads $0.00 due today with no statement on cards, so part credit (5). A person signs up in a browser, or approves OAuth in a client (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": 44,
        "maxGain": 9.8,
        "reason": "The hosted MCP does OAuth with PKCE (S256), dynamic client registration and six scopes, among them posts:read, analytics:read, accounts:read and media:read. It also takes a pb_live_ key as a Bearer header, and the MCP docs document a ?key= URL parameter as an alternative, so less 10 (20). Read-only scopes are possible and is_draft holds posts for review. The skill tells the agent to confirm local file and cron actions with the user (12). Tools return the operator's own posts and analytics, with no inbox or comments (10). list_post_results shows per-platform outcomes, no audit log (2). No security.txt, disclosure route or certification found, only support@post-bridge.com (0).",
        "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": 60,
        "maxGain": 6.5,
        "reason": "16 compact MCP tools with no toolsets (15). Offset and limit with a next URL, and posts filter by platform and status (20). Errors are plain strings with no codes, though list_post_results gives per-platform outcomes and the skill maps common failure causes (12). No idempotency key and no annotations we could see. is_draft holds a post, and delete_post only touches scheduled or draft posts (6). A zero-dependency Node CLI and no SDKs. Omitting scheduled_at publishes at once (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": "transparency",
        "name": "Transparency \u0026 trust",
        "score": 44,
        "maxGain": 4.9,
        "reason": "The CLI, skills and plugin are MIT. The hosted service runs under terms updated 1 October 2026 that name only Post Bridge with Canadian governing law, no company type or registration, and a 24-hour refund window that the pricing FAQ gives as 7 days (10). The privacy policy dated 3 August 2026 sets retention per data type, deletes personal data within 30 days of account deletion and names Supabase, Cloudflare, Stripe, Trigger.dev, Mailgun and Vercel, with no DPA and no data locations (20). No deprecation policy. The terms promise email notice of changes (3). Subprocessors named, locations not (12).",
        "blend": "editorial 45, provenance 42",
        "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"
      },
      {
        "key": "schema",
        "name": "Schema \u0026 documentation",
        "score": 72,
        "maxGain": 4.6,
        "reason": "OpenAPI 3.0.0 at api.post-bridge.com/openapi.json covering posts, media, analytics, post results and social accounts (25). llms.txt and llms-full.txt (10). The MCP docs give each of 16 tools one line. The agent-mode skill adds per-platform settings and failure causes such as 75 per cent of TikTok failures being spam restrictions that clear in 24 to 48 hours. We didn't read the hosted tools' own descriptions (12). Platform and status enums and typed DTOs in the spec (12). Errors come back as an error array of strings, and only the sync endpoint documents a 429 (8). Paths sit under /v1 with info.version 1.0, and there's no public changelog beyond the agent-mode commit history (5).",
        "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": "maintenance",
        "name": "Maintenance \u0026 community",
        "score": 76,
        "maxGain": 2.1,
        "reason": "postbridge-cli 1.1.4 published on 9 September 2026, and the agent-mode repo last changed on 24 September (30). CLI and registry versions 1.1.2, 1.1.3 and 1.1.4 between 6 and 9 September (20). llms.txt says support is answered by the founder within a few hours. The repo has never had a pull request, robots.txt blocked our reader from its issues, and there's no public changelog (8). Official registry entry io.github.jackfriks/post-bridge, latest 1.1.3 on 7 September 2026, under the founder's GitHub namespace (15). The CLI has no dependencies and the repo runs no CI (3).",
        "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"
      }
    ],
    "provenance": [
      {
        "label": "Legal entity named",
        "value": "not found",
        "points": 0,
        "max": 20
      },
      {
        "label": "Domain age",
        "value": "post-bridge.com, registered 2024-09-08 (2 years)",
        "points": 7,
        "max": 15
      },
      {
        "label": "Status page",
        "value": "not found",
        "points": 0,
        "max": 10
      },
      {
        "label": "Changelog",
        "value": "not found",
        "points": 0,
        "max": 10
      },
      {
        "label": "security.txt",
        "value": "not found",
        "points": 0,
        "max": 10
      }
    ],
    "unchecked": [
      "Which legal entity, if any, stands behind Post Bridge. The terms and privacy policy name only Post Bridge, and the npm maintainer is Jack Friks",
      "Whether free users get API or MCP access within the 5 posts a month the FAQ mentions, and whether the trial needs a card",
      "Whether status.post-bridge.com is a status page behind a sign-in or something else",
      "unchecked: open GitHub issues, since robots.txt blocked our reader",
      "unchecked: the hosted MCP's tool input schemas and annotations"
    ],
    "weaknesses": [
      "Publishing only, with no comments, DMs or inbox, and analytics for TikTok, YouTube, Instagram and Facebook only",
      "Terms and privacy policy name no legal entity, only Post Bridge under Canadian law",
      "No public status page, changelog or security.txt",
      "No idempotency key, and the MCP also accepts the API key as a ?key= URL parameter",
      "One founder answers support and writes every commit"
    ],
    "agentNotes": [
      "Call list_social_accounts first, upload media, then create_post. Omit scheduled_at to publish at once",
      "Check list_post_results before republishing a failed Instagram post, since Meta 500s often publish anyway",
      "Set is_draft true when a person should approve the post",
      "Put links for X in a reply, because captions sent to X lose their URLs",
      "Stay under 10 requests a second per key, and trigger sync_analytics no more than once every 30 minutes per account"
    ],
    "requests": [
      {
        "text": "Idempotency key on create_post",
        "reviews": 1
      },
      {
        "text": "Public status page",
        "reviews": 1
      },
      {
        "text": "drop the URL key",
        "reviews": 1
      },
      {
        "text": "name the legal entity",
        "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"
  }
}