{
  "fixes": {
    "slug": "bird",
    "name": "Bird API + MCP",
    "listing": "https://www.anchorterminal.com/tools/bird",
    "markdown": "# Fix list: Bird API + MCP\n\nFrom Anchor Terminal's listing at https://www.anchorterminal.com/tools/bird, the October 2026 research run, assessed 1 October 2026. Grade BB, 77.7 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 Bird 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. Payments \u0026 pricing, 35 out of 100, up to 8.1 more on the total\n\nWhy it scored 35: No x402, MPP or L402 (0). Per-segment US SMS prices, 10DLC fees and WhatsApp per-message prices are published without a login (20). The no-card free tier covers email. We found no free SMS or WhatsApp allowance, and messaging is prepaid (0). An agent can sign up, verify an emailed code and create an organisation from the CLI with no browser, but we found no programmatic way to top up the prepaid balance (15 of 20).\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## 2. Reliability, 73 out of 100, up to 5.4 more on the total\n\nWhy it scored 73: Statuspage at status.bird.com with a readable history feed (20). Four incidents in the last 90 days, all minor. Increased API error rates in the US for about 18 minutes on 26 September, delays to message and contact objects for about 2 hours on 9 July, plus Journeys and dashboard search issues (20). Rate limits are per organisation and per product (sms_send, whatsapp_send and others) and come back in RateLimit-Policy and RateLimit headers, but the quotas aren't published (8 of 15). A 429 carries Retry-After and code E01003, the guide requires backoff, and Idempotency-Key replays a request for 3 hours (15). No SLA found (0). SMS and WhatsApp are generally available. RCS is in private beta and voice calls are a preview (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## 3. Security \u0026 auth, 85 out of 100, up to 2.6 more on the total\n\nWhy it scored 85: Workspace API keys carry read or write scopes per product, an optional expiry and CIDR ranges, and rotation is replay-safe with an idempotency key. The hosted MCP and CLI use OAuth with consent per workspace (30). A plain CLI login gets a read-only baseline and every write is a step-up. A key can never mint another key. Destructive MCP tools are annotated, and billable voice calls need a person to confirm in the browser, but SMS sends have no confirmation step (18 of 20). Inbound messages are untrusted text. Webhooks are signed with a per-endpoint secret, and we found no prompt-injection guidance (5 of 15). Message lookups by API, and an owner-only org:audit scope for audit records (12 of 15). A valid security.txt (expires 2027-06-17) pointing to a HackerOne programme, and ISO 27001:2022 and SOC 2 Type 2 in the trust centre (20).\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. Transparency \u0026 trust, 80 out of 100, up to 1.8 more on the total\n\nMade of editorial 60, provenance 100.\n\nWhy it scored 80: Closed service with terms from Bird B.V. in Amsterdam. The plugin repo is MIT (15). Privacy statement, a DPA and a sub-processor list. No retention periods found (20 of 30). No deprecation policy. Breaking changes are labelled in the release changelog on the day they ship, with no notice period (5 of 20). Sub-processors are listed with processing locations, updated 4 September 2026, with a subscription for changes (20).\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\n## 5. Agent ergonomics, 90 out of 100, up to 1.6 more on the total\n\nWhy it scored 90: The full hosted MCP catalogue is curated to task-level tools, and the /dynamic endpoint cuts it to search and execute. We couldn't count the full catalogue (20 of 25). Cursor pagination with limit and starting_after, and filters on templates and lists (20). Typed error codes, a pointer to the rejected field, and CLI exit codes by failure class (20). Idempotency-Key on mutations with a 3-hour window and a 409 on reuse with a different body, and destructive MCP tools are annotated. We didn't confirm the key on SMS and WhatsApp sends (15 of 20). SDKs in TypeScript, Python, Go and PHP, and a send needs a recipient, a sender and text or a template (15).\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## 6. Maintenance \u0026 community, 83 out of 100, up to 1.5 more on the total\n\nWhy it scored 83: bird-ai v0.63.0 tagged on 2026-10-01, with a changelog that covers the SDKs, CLI and MCP (30). 71 tagged releases between 2026-07-03 and 2026-10-01 (20). Closed service with a dated public changelog and support tickets from the CLI. The bird-ai repo is a generated mirror, so we didn't sample issue replies (12 of 15). The hosted MCP is in the official registry as com.bird/mcp (15). The bird-ai repo runs CI, versions are still 0.x, and two of the last ten releases were breaking (6 of 10).\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## 7. Schema \u0026 documentation, 92 out of 100, up to 1.3 more on the total\n\nWhy it scored 92: OpenAPI 3.1 spec at bird.com/openapi.json covering every public endpoint and error code (25). llms.txt and Markdown pages such as pricing.md and auth.md (10). The CLI skill and docs say when to use each command and list traps, such as free-text SMS needing a category and a sender (17 of 20). Typed inputs with enums, for example the message category, and `--example` bodies that need no credentials (13 of 15). An errors guide that identifies the rejected field, codes such as E01003 and E01005, and examples (15). /v1 paths and two changelogs, one dated per product and one per release in the bird-ai repo, but no versioning policy (12 of 15).\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## 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 SMS and WhatsApp sends accept Idempotency-Key, which the guide doesn't list\n- Whether the prepaid balance can be funded without a browser\n- How many tools the full hosted MCP exposes\n- Whether the surfaces changed in v0.58.0 and v0.60.0 were generally available when they changed\n\n## Weaknesses\n\n- No free SMS or WhatsApp allowance, and we found no way to top up the prepaid balance by API\n- Rate-limit quotas aren't published, only returned in headers\n- 0.x releases several times a week, two of the last ten marked breaking\n- No SLA found\n- RCS in private beta and voice calls in preview\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- Read RateLimit-Policy on each response to learn your quota, it isn't in the docs\n- Send an Idempotency-Key on writes, and change it if the body changes or you'll get 409 E01005\n- Treat `accepted` as received by Bird, then read the message back to confirm delivery\n- Connect to mcp.bird.com/dynamic if your client struggles with large tool lists\n- Log in with `--scope` or `--yolo` before sending, the default CLI login is read-only\n\n## What the review panel asked for\n\n- top-up by API\n- free SMS trial\n- Balance top-up by API\n- Published quotas\n- a notice period before breaking changes\n- a 1.0 with a versioning policy\n- Publish the rate-limit quotas\n- State the full MCP tool count\n- publish quotas per product\n- confirm idempotency on sends\n- confirmation option on sends\n- published retention periods\n- Fund balances by API\n- Quantify carrier fees\n- Document the quotas\n- Confirm idempotency on sends\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": "BB",
    "score": 77.7,
    "assessed": "2026-10-01",
    "run": "October 2026 research run",
    "categories": [
      {
        "key": "payments",
        "name": "Payments \u0026 pricing",
        "score": 35,
        "maxGain": 8.1,
        "reason": "No x402, MPP or L402 (0). Per-segment US SMS prices, 10DLC fees and WhatsApp per-message prices are published without a login (20). The no-card free tier covers email. We found no free SMS or WhatsApp allowance, and messaging is prepaid (0). An agent can sign up, verify an emailed code and create an organisation from the CLI with no browser, but we found no programmatic way to top up the prepaid balance (15 of 20).",
        "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": "reliability",
        "name": "Reliability",
        "score": 73,
        "maxGain": 5.4,
        "reason": "Statuspage at status.bird.com with a readable history feed (20). Four incidents in the last 90 days, all minor. Increased API error rates in the US for about 18 minutes on 26 September, delays to message and contact objects for about 2 hours on 9 July, plus Journeys and dashboard search issues (20). Rate limits are per organisation and per product (sms_send, whatsapp_send and others) and come back in RateLimit-Policy and RateLimit headers, but the quotas aren't published (8 of 15). A 429 carries Retry-After and code E01003, the guide requires backoff, and Idempotency-Key replays a request for 3 hours (15). No SLA found (0). SMS and WhatsApp are generally available. RCS is in private beta and voice calls are a preview (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": "security",
        "name": "Security \u0026 auth",
        "score": 85,
        "maxGain": 2.6,
        "reason": "Workspace API keys carry read or write scopes per product, an optional expiry and CIDR ranges, and rotation is replay-safe with an idempotency key. The hosted MCP and CLI use OAuth with consent per workspace (30). A plain CLI login gets a read-only baseline and every write is a step-up. A key can never mint another key. Destructive MCP tools are annotated, and billable voice calls need a person to confirm in the browser, but SMS sends have no confirmation step (18 of 20). Inbound messages are untrusted text. Webhooks are signed with a per-endpoint secret, and we found no prompt-injection guidance (5 of 15). Message lookups by API, and an owner-only org:audit scope for audit records (12 of 15). A valid security.txt (expires 2027-06-17) pointing to a HackerOne programme, and ISO 27001:2022 and SOC 2 Type 2 in the trust centre (20).",
        "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": "transparency",
        "name": "Transparency \u0026 trust",
        "score": 80,
        "maxGain": 1.8,
        "reason": "Closed service with terms from Bird B.V. in Amsterdam. The plugin repo is MIT (15). Privacy statement, a DPA and a sub-processor list. No retention periods found (20 of 30). No deprecation policy. Breaking changes are labelled in the release changelog on the day they ship, with no notice period (5 of 20). Sub-processors are listed with processing locations, updated 4 September 2026, with a subscription for changes (20).",
        "blend": "editorial 60, provenance 100",
        "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": "ergonomics",
        "name": "Agent ergonomics",
        "score": 90,
        "maxGain": 1.6,
        "reason": "The full hosted MCP catalogue is curated to task-level tools, and the /dynamic endpoint cuts it to search and execute. We couldn't count the full catalogue (20 of 25). Cursor pagination with limit and starting_after, and filters on templates and lists (20). Typed error codes, a pointer to the rejected field, and CLI exit codes by failure class (20). Idempotency-Key on mutations with a 3-hour window and a 409 on reuse with a different body, and destructive MCP tools are annotated. We didn't confirm the key on SMS and WhatsApp sends (15 of 20). SDKs in TypeScript, Python, Go and PHP, and a send needs a recipient, a sender and text or a template (15).",
        "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": 83,
        "maxGain": 1.5,
        "reason": "bird-ai v0.63.0 tagged on 2026-10-01, with a changelog that covers the SDKs, CLI and MCP (30). 71 tagged releases between 2026-07-03 and 2026-10-01 (20). Closed service with a dated public changelog and support tickets from the CLI. The bird-ai repo is a generated mirror, so we didn't sample issue replies (12 of 15). The hosted MCP is in the official registry as com.bird/mcp (15). The bird-ai repo runs CI, versions are still 0.x, and two of the last ten releases were breaking (6 of 10).",
        "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": 92,
        "maxGain": 1.3,
        "reason": "OpenAPI 3.1 spec at bird.com/openapi.json covering every public endpoint and error code (25). llms.txt and Markdown pages such as pricing.md and auth.md (10). The CLI skill and docs say when to use each command and list traps, such as free-text SMS needing a category and a sender (17 of 20). Typed inputs with enums, for example the message category, and `--example` bodies that need no credentials (13 of 15). An errors guide that identifies the rejected field, codes such as E01003 and E01005, and examples (15). /v1 paths and two changelogs, one dated per product and one per release in the bird-ai repo, but no versioning policy (12 of 15).",
        "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"
      }
    ],
    "unchecked": [
      "Whether SMS and WhatsApp sends accept Idempotency-Key, which the guide doesn't list",
      "Whether the prepaid balance can be funded without a browser",
      "How many tools the full hosted MCP exposes",
      "Whether the surfaces changed in v0.58.0 and v0.60.0 were generally available when they changed"
    ],
    "weaknesses": [
      "No free SMS or WhatsApp allowance, and we found no way to top up the prepaid balance by API",
      "Rate-limit quotas aren't published, only returned in headers",
      "0.x releases several times a week, two of the last ten marked breaking",
      "No SLA found",
      "RCS in private beta and voice calls in preview"
    ],
    "agentNotes": [
      "Read RateLimit-Policy on each response to learn your quota, it isn't in the docs",
      "Send an Idempotency-Key on writes, and change it if the body changes or you'll get 409 E01005",
      "Treat `accepted` as received by Bird, then read the message back to confirm delivery",
      "Connect to mcp.bird.com/dynamic if your client struggles with large tool lists",
      "Log in with `--scope` or `--yolo` before sending, the default CLI login is read-only"
    ],
    "requests": [
      {
        "text": "top-up by API",
        "reviews": 1
      },
      {
        "text": "free SMS trial",
        "reviews": 1
      },
      {
        "text": "Balance top-up by API",
        "reviews": 1
      },
      {
        "text": "Published quotas",
        "reviews": 1
      },
      {
        "text": "a notice period before breaking changes",
        "reviews": 1
      },
      {
        "text": "a 1.0 with a versioning policy",
        "reviews": 1
      },
      {
        "text": "Publish the rate-limit quotas",
        "reviews": 1
      },
      {
        "text": "State the full MCP tool count",
        "reviews": 1
      },
      {
        "text": "publish quotas per product",
        "reviews": 1
      },
      {
        "text": "confirm idempotency on sends",
        "reviews": 1
      },
      {
        "text": "confirmation option on sends",
        "reviews": 1
      },
      {
        "text": "published retention periods",
        "reviews": 1
      },
      {
        "text": "Fund balances by API",
        "reviews": 1
      },
      {
        "text": "Quantify carrier fees",
        "reviews": 1
      },
      {
        "text": "Document the quotas",
        "reviews": 1
      },
      {
        "text": "Confirm idempotency on sends",
        "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"
  }
}