{
  "fixes": {
    "slug": "trigger-dev",
    "name": "Trigger.dev",
    "listing": "https://www.anchorterminal.com/tools/trigger-dev",
    "markdown": "# Fix list: Trigger.dev\n\nFrom Anchor Terminal's listing at https://www.anchorterminal.com/tools/trigger-dev, the October 2026 research run, assessed 1 October 2026. Grade BB, 74.8 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 Trigger.dev: 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, 40 out of 100, up to 7.5 more on the total\n\nWhy it scored 40: No machine payment protocol (0). Per-unit prices published without a login, $0.0000338 a second for the default Small 1x machine (0.5 vCPU) up to $0.00068 for Large 2x, plus $0.25 per 10,000 runs (20). Free plan at $0 with $5 of monthly usage, 20 concurrent runs and 1-day logs, and the pricing page asks for no card (20). A person signs up in the browser (0).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-payments):\n\nThe published rubric, also on the [x402 page](https://www.anchorterminal.com/x402/).\n\n- 40, a machine payment protocol (x402, MPP or L402) on the tool's own endpoints. 10 to 30 when it covers only some endpoints or only goes through a third party, and the note says which.\n- 20, per-call or per-unit pricing published without a login. 10 for public plan-only pricing, 0 for \"contact sales\" or prices behind a login.\n- 20, a free tier or trial that doesn't need a card.\n- 20, autonomous onboarding, meaning an agent can get access without a person signing up in a browser (keyless use, x402, a programmatic key API).\n\nPayment platforms and agent wallets rarely charge for their own API over a machine protocol, so the first line has steps for them, and the highest one that applies counts. 40 when x402, MPP or L402 runs on all their own endpoints, 30 when it runs on part of their own API, 25 when their merchants can accept one, 20 for running a facilitator, 15 for paying as a buyer, and 0 when the only protocol is their own. Merchant acceptance sits above a facilitator because the platform's own customers can charge agents through it, while a facilitator settles for sellers who wire up the protocol themselves. The counter-argument (a facilitator does more for the protocol as a whole) has a point. Each note says which step applied.\n\nOpen-source software you run yourself is scored on its hosted or paid option if it has one. A free, self-hosted package with nothing to buy gets 20, 20 and 20 for the last three lines, and 0 to 40 for the first only if it ships a payment protocol.\n\n## 2. Reliability, 75 out of 100, up to 5 more on the total\n\nWhy it scored 75: Status page at status.trigger.dev (Better Stack) with components per region and incident history (20). Since 3 July it shows degraded runs listing and logs on 15 and 16 July (49 minutes and 1 hour 9 minutes), the dashboard down for 7 minutes on 15 July, runs list and logs degraded for 1 hour 24 minutes on 24 August, a related entry on 3 September, and run logs dropped for 30 minutes on 28 September. None hit task execution, so we count them as minor (20 of 30). API limit of 1,500 requests a minute, batch triggers on a token bucket (1,200 runs then 100 every 10 seconds on Free), concurrency and queue sizes by plan (15). The docs name the usual cause of 429s and the fix (batch triggers), and tokens and triggers take idempotency keys, with no Retry-After guidance for the Trigger.dev API itself (10 of 15). No SLA found (0). Waitpoint tokens are GA in v4 (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, 73 out of 100, up to 4.7 more on the total\n\nWhy it scored 73: Secret keys per environment, personal access tokens for the CLI and MCP, and a public access token scoped to one waitpoint for browser completion. The callback URL carries a per-token hash in its path, which is a single-use capability rather than an account secret, so no deduction (25 of 30). MCP read-only and dev-only modes, project scoping, and RBAC on Cloud (the OSS build falls back to permissive roles, as SECURITY.md says) (15 of 20). It returns your own run data and the completion payload (10). Runs, traces and tokens are listed by status, with no audit log of who completed a token that we found (8 of 15). SECURITY.md with private GitHub advisories, security@trigger.dev and acknowledgement within 3 business days, and a SOC 2 report and penetration test on Enterprise per the pricing page. We didn't check security.txt (15 of 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. Agent ergonomics, 79 out of 100, up to 3.4 more on the total\n\nWhy it scored 79: The MCP server has 31 tools (5), plus `--readonly` and `--dev-only` modes and project scoping (8), so 13 for MCP. The REST API pages and filters (20). We average the two surfaces to 16 of 25. Tokens list by status and tags, runs list with filters and cursors (20). `wait.forToken()` returns `ok: false` with an error on timeout, `.unwrap()` throws, and the spec documents errors (15 of 20). Idempotency keys on tokens and triggers, and the MCP tools set `readOnlyHint` and `destructiveHint` in source (20). Every `createToken` option is optional, but the official SDK is TypeScript only (8 of 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## 5. Transparency \u0026 trust, 74 out of 100, up to 2.3 more on the total\n\nMade of editorial 73, provenance 75.\n\nWhy it scored 74: Apache-2.0 (30). The privacy policy (updated 2025-12-23) keeps personal data 'no longer than necessary', links a public DPA and a subprocessors page, and the docs say payloads over 512 KB sit in object storage, queued runs expire after 14 days and logs are kept 1 to 30 days by plan. No retention period for run data in the policy itself (18 of 30). The v3 retirement notice lists deprecations and the version cut-off for self-hosters but no dates (10 of 20). Self-hosted webapp telemetry and MCP telemetry are disclosed with `TRIGGER_TELEMETRY_DISABLED` and `--skip-telemetry` opt-outs, and the privacy policy points to a subprocessors page we didn't read (15 of 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\nProvenance checks not met in full (half of this category, computed from checked facts):\n\n- Domain age: trigger.dev, no registry record we could read (0 of 15)\n- security.txt: could not be fetched (0 of 10)\n\n## 6. Schema \u0026 documentation, 91 out of 100, up to 1.5 more on the total\n\nWhy it scored 91: OpenAPI 3.1 for the REST API, including create, list, complete and callback endpoints for waitpoint tokens (25). llms.txt and llms-full.txt under trigger.dev/docs (10). The token docs say what tokens are for, when to use input streams instead and not to call the callback URL from a browser (15 of 20). Typed SDK generics for the token output, typed OpenAPI schemas (13 of 15). Examples for each completion path, and error responses in the spec such as a callback hash mismatch (13 of 15). Changesets changelog per package, a public changelog page and a dated API version (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## 7. Maintenance \u0026 community, 90 out of 100, up to 0.9 more on the total\n\nWhy it scored 90: v4.7.0 released on 2026-10-01 (30). v4.5.10 on 2026-08-07, v4.6.0 to v4.6.4 between 14 and 22 September, and v4.7.0 (20). Large, active repository, and we didn't sample reply times (15 of 25). Current official TypeScript SDK, and the REST API from any language (15). CI workflows, tests and changesets (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## 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 Free plan ever asks for a card at sign-up. The pricing page doesn't say.\n- Whether Trigger.dev publishes a security.txt.\n- Whether the MCP registry serves a current record for io.github.triggerdotdev/trigger.dev, since server.json still says 4.0.3.\n\n## Weaknesses\n\n- 10-minute default timeout on tokens\n- No built-in reviewer UI, notifications, routing or record of who completed a token\n- Tasks are written in TypeScript, though any language can complete a token over HTTP\n- Short time waits hold a concurrency slot until the checkpoint 60 seconds in\n- The MCP server's 31 tools don't cover waitpoint tokens\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- Pass an explicit `timeout` to `wait.createToken()` and handle `ok: false` as a timeout\n- Use an idempotency key when creating the token so a retried step doesn't send the reviewer a second request\n- Give the browser the `publicAccessToken`, never the secret key, and don't call `token.url` from client code\n- Tag tokens with the user or task ID so pending approvals can be listed per reviewer\n- Start the MCP server with `--readonly` when the agent only needs to inspect runs\n\n## What the review panel asked for\n\n- MCP waitpoint tools (2 reviews)\n- State card need\n- Completion audit trail\n- document cap behaviour\n- MCP parameter tables\n- a completed-by field\n- waitpoint tools in the MCP\n- Add Retry-After to 429s\n- dates on the v3 retirement\n- server.json kept current\n- approver identity on completion\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": 74.8,
    "assessed": "2026-10-01",
    "run": "October 2026 research run",
    "categories": [
      {
        "key": "payments",
        "name": "Payments \u0026 pricing",
        "score": 40,
        "maxGain": 7.5,
        "reason": "No machine payment protocol (0). Per-unit prices published without a login, $0.0000338 a second for the default Small 1x machine (0.5 vCPU) up to $0.00068 for Large 2x, plus $0.25 per 10,000 runs (20). Free plan at $0 with $5 of monthly usage, 20 concurrent runs and 1-day logs, and the pricing page asks for no card (20). A person signs up in the browser (0).",
        "checklist": [
          "The published rubric, also on the [x402 page](https://www.anchorterminal.com/x402/).",
          "- 40, a machine payment protocol (x402, MPP or L402) on the tool's own endpoints. 10 to 30 when it covers only some endpoints or only goes through a third party, and the note says which.\n- 20, per-call or per-unit pricing published without a login. 10 for public plan-only pricing, 0 for \"contact sales\" or prices behind a login.\n- 20, a free tier or trial that doesn't need a card.\n- 20, autonomous onboarding, meaning an agent can get access without a person signing up in a browser (keyless use, x402, a programmatic key API).",
          "Payment platforms and agent wallets rarely charge for their own API over a machine protocol, so the first line has steps for them, and the highest one that applies counts. 40 when x402, MPP or L402 runs on all their own endpoints, 30 when it runs on part of their own API, 25 when their merchants can accept one, 20 for running a facilitator, 15 for paying as a buyer, and 0 when the only protocol is their own. Merchant acceptance sits above a facilitator because the platform's own customers can charge agents through it, while a facilitator settles for sellers who wire up the protocol themselves. The counter-argument (a facilitator does more for the protocol as a whole) has a point. Each note says which step applied.",
          "Open-source software you run yourself is scored on its hosted or paid option if it has one. A free, self-hosted package with nothing to buy gets 20, 20 and 20 for the last three lines, and 0 to 40 for the first only if it ships a payment protocol."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-payments"
      },
      {
        "key": "reliability",
        "name": "Reliability",
        "score": 75,
        "maxGain": 5,
        "reason": "Status page at status.trigger.dev (Better Stack) with components per region and incident history (20). Since 3 July it shows degraded runs listing and logs on 15 and 16 July (49 minutes and 1 hour 9 minutes), the dashboard down for 7 minutes on 15 July, runs list and logs degraded for 1 hour 24 minutes on 24 August, a related entry on 3 September, and run logs dropped for 30 minutes on 28 September. None hit task execution, so we count them as minor (20 of 30). API limit of 1,500 requests a minute, batch triggers on a token bucket (1,200 runs then 100 every 10 seconds on Free), concurrency and queue sizes by plan (15). The docs name the usual cause of 429s and the fix (batch triggers), and tokens and triggers take idempotency keys, with no Retry-After guidance for the Trigger.dev API itself (10 of 15). No SLA found (0). Waitpoint tokens are GA in v4 (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": 73,
        "maxGain": 4.7,
        "reason": "Secret keys per environment, personal access tokens for the CLI and MCP, and a public access token scoped to one waitpoint for browser completion. The callback URL carries a per-token hash in its path, which is a single-use capability rather than an account secret, so no deduction (25 of 30). MCP read-only and dev-only modes, project scoping, and RBAC on Cloud (the OSS build falls back to permissive roles, as SECURITY.md says) (15 of 20). It returns your own run data and the completion payload (10). Runs, traces and tokens are listed by status, with no audit log of who completed a token that we found (8 of 15). SECURITY.md with private GitHub advisories, security@trigger.dev and acknowledgement within 3 business days, and a SOC 2 report and penetration test on Enterprise per the pricing page. We didn't check security.txt (15 of 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": "ergonomics",
        "name": "Agent ergonomics",
        "score": 79,
        "maxGain": 3.4,
        "reason": "The MCP server has 31 tools (5), plus `--readonly` and `--dev-only` modes and project scoping (8), so 13 for MCP. The REST API pages and filters (20). We average the two surfaces to 16 of 25. Tokens list by status and tags, runs list with filters and cursors (20). `wait.forToken()` returns `ok: false` with an error on timeout, `.unwrap()` throws, and the spec documents errors (15 of 20). Idempotency keys on tokens and triggers, and the MCP tools set `readOnlyHint` and `destructiveHint` in source (20). Every `createToken` option is optional, but the official SDK is TypeScript only (8 of 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": "transparency",
        "name": "Transparency \u0026 trust",
        "score": 74,
        "maxGain": 2.3,
        "reason": "Apache-2.0 (30). The privacy policy (updated 2025-12-23) keeps personal data 'no longer than necessary', links a public DPA and a subprocessors page, and the docs say payloads over 512 KB sit in object storage, queued runs expire after 14 days and logs are kept 1 to 30 days by plan. No retention period for run data in the policy itself (18 of 30). The v3 retirement notice lists deprecations and the version cut-off for self-hosters but no dates (10 of 20). Self-hosted webapp telemetry and MCP telemetry are disclosed with `TRIGGER_TELEMETRY_DISABLED` and `--skip-telemetry` opt-outs, and the privacy policy points to a subprocessors page we didn't read (15 of 20).",
        "blend": "editorial 73, provenance 75",
        "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": 91,
        "maxGain": 1.5,
        "reason": "OpenAPI 3.1 for the REST API, including create, list, complete and callback endpoints for waitpoint tokens (25). llms.txt and llms-full.txt under trigger.dev/docs (10). The token docs say what tokens are for, when to use input streams instead and not to call the callback URL from a browser (15 of 20). Typed SDK generics for the token output, typed OpenAPI schemas (13 of 15). Examples for each completion path, and error responses in the spec such as a callback hash mismatch (13 of 15). Changesets changelog per package, a public changelog page and a dated API version (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"
      },
      {
        "key": "maintenance",
        "name": "Maintenance \u0026 community",
        "score": 90,
        "maxGain": 0.9,
        "reason": "v4.7.0 released on 2026-10-01 (30). v4.5.10 on 2026-08-07, v4.6.0 to v4.6.4 between 14 and 22 September, and v4.7.0 (20). Large, active repository, and we didn't sample reply times (15 of 25). Current official TypeScript SDK, and the REST API from any language (15). CI workflows, tests and changesets (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"
      }
    ],
    "provenance": [
      {
        "label": "Domain age",
        "value": "trigger.dev, no registry record we could read",
        "points": 0,
        "max": 15
      },
      {
        "label": "security.txt",
        "value": "could not be fetched",
        "points": 0,
        "max": 10
      }
    ],
    "unchecked": [
      "Whether the Free plan ever asks for a card at sign-up. The pricing page doesn't say.",
      "Whether Trigger.dev publishes a security.txt.",
      "Whether the MCP registry serves a current record for io.github.triggerdotdev/trigger.dev, since server.json still says 4.0.3."
    ],
    "weaknesses": [
      "10-minute default timeout on tokens",
      "No built-in reviewer UI, notifications, routing or record of who completed a token",
      "Tasks are written in TypeScript, though any language can complete a token over HTTP",
      "Short time waits hold a concurrency slot until the checkpoint 60 seconds in",
      "The MCP server's 31 tools don't cover waitpoint tokens"
    ],
    "agentNotes": [
      "Pass an explicit `timeout` to `wait.createToken()` and handle `ok: false` as a timeout",
      "Use an idempotency key when creating the token so a retried step doesn't send the reviewer a second request",
      "Give the browser the `publicAccessToken`, never the secret key, and don't call `token.url` from client code",
      "Tag tokens with the user or task ID so pending approvals can be listed per reviewer",
      "Start the MCP server with `--readonly` when the agent only needs to inspect runs"
    ],
    "requests": [
      {
        "text": "MCP waitpoint tools",
        "reviews": 2
      },
      {
        "text": "State card need",
        "reviews": 1
      },
      {
        "text": "Completion audit trail",
        "reviews": 1
      },
      {
        "text": "document cap behaviour",
        "reviews": 1
      },
      {
        "text": "MCP parameter tables",
        "reviews": 1
      },
      {
        "text": "a completed-by field",
        "reviews": 1
      },
      {
        "text": "waitpoint tools in the MCP",
        "reviews": 1
      },
      {
        "text": "Add Retry-After to 429s",
        "reviews": 1
      },
      {
        "text": "dates on the v3 retirement",
        "reviews": 1
      },
      {
        "text": "server.json kept current",
        "reviews": 1
      },
      {
        "text": "approver identity on completion",
        "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"
  }
}