{
  "fixes": {
    "slug": "tray",
    "name": "Tray.ai API + MCP",
    "listing": "https://www.anchorterminal.com/tools/tray",
    "markdown": "# Fix list: Tray.ai API + MCP\n\nFrom Anchor Terminal's listing at https://www.anchorterminal.com/tools/tray, the October 2026 research run, assessed 1 October 2026. Grade C, 55.6 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 Tray.ai 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, 0 out of 100, up to 12.5 more on the total\n\nWhy it scored 0: No x402, MPP or L402 (0). No prices published, every plan is quoted by sales per the 30 September check (0). A free trial exists on request, with no stated length or card terms (0). A person goes through sales to get an account (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. Agent ergonomics, 33 out of 100, up to 10.9 more on the total\n\nWhy it scored 33: We couldn't find a tool count for Headless MCP, so 5, plus 10 back because Agent Gateway exposes only the workflows and connector operations you choose (15). We didn't verify pagination or output-size controls in this run (5). Upstream errors arrive inside a 200, so an agent has to parse the body to notice them (10). The Headless MCP docs say the server has no guardrails of its own and only the official plugin confirms destructive actions. No idempotency keys found (0). No official SDK (3).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-ergonomics):\n\n- 0 to 25, context cost. For MCP, the number and size of the tool definitions (25 for ten or fewer compact tools, 15 for 11 to 30, 5 for more than 30, plus up to 10 back for toolsets, dynamic loading or read-only subsets). For APIs, whether responses can be sized (field selection, limits, summaries).\n- 20, pagination, filtering and output-size controls.\n- 20, actionable, documented error responses, codes and messages an agent can recover from.\n- 20, idempotency or safe retries, and for MCP the `readOnlyHint` and `destructiveHint` annotations.\n- 15, sensible defaults, few required parameters, and official SDKs in at least two languages.\n\nModels are read for tool use, structured output, prompt caching, context length, batch and SDKs. Frameworks for how much code and how many defaults a tool-calling agent with MCP needs.\n\n## 3. Security \u0026 auth, 66 out of 100, up to 6 more on the total\n\nWhy it scored 66: Org master token for admin work and per-end-user user tokens, both bearer. Headless MCP signs in with OAuth2 bound to one workspace, and Agent Gateway takes OAuth2 or an API token. The master token can do everything in the org (22). User tokens confine calls to one end user's auths, but Headless MCP can delete projects, workflows and auths with no server-side confirmation (8). Connector results are untrusted third-party data and we found no injection guidance (3). Every action is logged and can be streamed to your own systems, MCP tool runs appear in the Monitor tab per the 30 September check, and log masking hides sensitive fields (15). SOC 1 and SOC 2 Type 2 (audit period to 31 July 2025), HIPAA, a penetration test on 23 September 2026, a bug bounty and a trust centre. No security.txt per the 30 September check (18).\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. Reliability, 72 out of 100, up to 5.6 more on the total\n\nWhy it scored 72: Status page at status.tray.ai with a history feed by region (20). Four incidents in the last 90 days, none a core API outage. The Send Email connector degraded for 1 hour 21 minutes on 30 September 2026, login failed across regions for about 2.5 hours on 16 July, the billing page was down for 8 hours on 10 August, and Gmail token refresh failed for two customers on 13 July (20). Connectivity and Embedded APIs limited to 30 requests a second with bursts to 50, per the 30 September check (15). The docs warn that a third-party 429 comes back inside a Tray 200. We found no Retry-After or backoff guidance for Tray's own limit (7). No SLA found (0). APIs generally available, and MCP dynamic authentication went GA on 17 June 2026 (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## 5. Maintenance \u0026 community, 60 out of 100, up to 3.5 more on the total\n\nWhy it scored 60: Newest entry on the releases page is 9 September 2026, JSONata in step inputs (30). Five dated entries since 3 July 2026, including Tray Sync CLI on 19 August and log masking on 14 July (20). Dated releases page and a support channel. We didn't test response times (10). No official SDK and no entry in the official MCP registry found (0). Nothing public to judge package health (0).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-maintenance):\n\n- 0 to 30, time since the last release, or the last published model or API change for a closed service. 30 within 30 days, 20 within 90, 10 within 180, 0 older.\n- 20, at least three releases or dated changelog entries in the last 90 days.\n- 0 to 25, responsiveness. Issues and pull requests answered on GitHub (the open issues and how recent the replies are). For closed services, a public changelog and a support or community channel that answers, 0 to 15.\n- 15, presence in the official MCP registry under a verified namespace (MCP servers), or current official SDKs (APIs and models).\n- 10, package health, current dependencies and CI.\n\nModels are read for deprecation notice periods and model churn rather than release counts.\n\n## 6. Schema \u0026 documentation, 80 out of 100, up to 3.3 more on the total\n\nWhy it scored 80: OpenAPI file for the REST APIs at trayapi.yaml, per the 30 September check (25). llms.txt, llms-full.txt and Markdown copies of docs pages (10). We didn't read the Headless MCP tool definitions, and the docs describe capabilities rather than individual tools (10). Connector operations have typed input schemas, though some take free-form bodies (10). Examples throughout, and the 429-inside-200 behaviour is documented, but no full error catalogue found (10). Versioned at /core/v1 with a dated releases page (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. Transparency \u0026 trust, 69 out of 100, up to 2.7 more on the total\n\nMade of editorial 67, provenance 71.\n\nWhy it scored 69: Closed service under a published MSA (15). Trust centre with audit reports, a subprocessor list, Data Privacy Framework certification, and log retention settable from 30 days down to 24 hours or off (26). No deprecation policy or dated deprecation notices in the releases we read (6). Subprocessors listed and US, EU and APAC regions disclosed (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: tray.ai, registered 2017-12-15 (8 years) (11 of 15)\n- Endpoint on the vendor's domain: api.tray.io is not on tray.ai (0 of 15)\n- security.txt: not found (0 of 10)\n\n## What we couldn't check\n\nWhat we couldn't read counted as absent. Publishing it on a page a plain HTTP fetch can read (not only in a browser) lets the next check count it.\n\n- unchecked: the Headless MCP tool list and its tool count\n- Whether Tray's own 429 responses carry Retry-After\n- Whether a newer SOC 2 report covers the period after 31 July 2025\n- The length and card terms of the free trial\n- unchecked: pagination and output-size controls on the REST and GraphQL APIs\n\n## Weaknesses\n\n- No published prices and no self-serve plan\n- Upstream 429s are wrapped in a 200, which hides throttling from naive retry logic\n- Headless MCP can delete projects, workflows and auths with no server-side confirmation\n- No official SDK and no tool annotations\n- API lives on api.tray.io while the brand, docs and legal pages are on tray.ai\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- Use a user token when acting for a customer and the master token only for admin work\n- Parse the body of call-connector responses for upstream status codes before treating a 200 as success\n- Point Headless MCP at the workspace's region, api.eu1.tray.io or api.ap1.tray.io outside the US\n- Pick the workspace at OAuth sign-in. Headless MCP binds it to the session and takes no workspace ID\n- Ask before any Headless MCP delete. The server won't\n\n## What the review panel asked for\n\n- deprecation policy\n- server-side delete confirmation\n- tool annotations\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": "C",
    "score": 55.6,
    "assessed": "2026-10-01",
    "run": "October 2026 research run",
    "categories": [
      {
        "key": "payments",
        "name": "Payments \u0026 pricing",
        "score": 0,
        "maxGain": 12.5,
        "reason": "No x402, MPP or L402 (0). No prices published, every plan is quoted by sales per the 30 September check (0). A free trial exists on request, with no stated length or card terms (0). A person goes through sales to get an account (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": "ergonomics",
        "name": "Agent ergonomics",
        "score": 33,
        "maxGain": 10.9,
        "reason": "We couldn't find a tool count for Headless MCP, so 5, plus 10 back because Agent Gateway exposes only the workflows and connector operations you choose (15). We didn't verify pagination or output-size controls in this run (5). Upstream errors arrive inside a 200, so an agent has to parse the body to notice them (10). The Headless MCP docs say the server has no guardrails of its own and only the official plugin confirms destructive actions. No idempotency keys found (0). No official SDK (3).",
        "checklist": [
          "- 0 to 25, context cost. For MCP, the number and size of the tool definitions (25 for ten or fewer compact tools, 15 for 11 to 30, 5 for more than 30, plus up to 10 back for toolsets, dynamic loading or read-only subsets). For APIs, whether responses can be sized (field selection, limits, summaries).\n- 20, pagination, filtering and output-size controls.\n- 20, actionable, documented error responses, codes and messages an agent can recover from.\n- 20, idempotency or safe retries, and for MCP the `readOnlyHint` and `destructiveHint` annotations.\n- 15, sensible defaults, few required parameters, and official SDKs in at least two languages.",
          "Models are read for tool use, structured output, prompt caching, context length, batch and SDKs. Frameworks for how much code and how many defaults a tool-calling agent with MCP needs."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-ergonomics"
      },
      {
        "key": "security",
        "name": "Security \u0026 auth",
        "score": 66,
        "maxGain": 6,
        "reason": "Org master token for admin work and per-end-user user tokens, both bearer. Headless MCP signs in with OAuth2 bound to one workspace, and Agent Gateway takes OAuth2 or an API token. The master token can do everything in the org (22). User tokens confine calls to one end user's auths, but Headless MCP can delete projects, workflows and auths with no server-side confirmation (8). Connector results are untrusted third-party data and we found no injection guidance (3). Every action is logged and can be streamed to your own systems, MCP tool runs appear in the Monitor tab per the 30 September check, and log masking hides sensitive fields (15). SOC 1 and SOC 2 Type 2 (audit period to 31 July 2025), HIPAA, a penetration test on 23 September 2026, a bug bounty and a trust centre. No security.txt per the 30 September check (18).",
        "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": "reliability",
        "name": "Reliability",
        "score": 72,
        "maxGain": 5.6,
        "reason": "Status page at status.tray.ai with a history feed by region (20). Four incidents in the last 90 days, none a core API outage. The Send Email connector degraded for 1 hour 21 minutes on 30 September 2026, login failed across regions for about 2.5 hours on 16 July, the billing page was down for 8 hours on 10 August, and Gmail token refresh failed for two customers on 13 July (20). Connectivity and Embedded APIs limited to 30 requests a second with bursts to 50, per the 30 September check (15). The docs warn that a third-party 429 comes back inside a Tray 200. We found no Retry-After or backoff guidance for Tray's own limit (7). No SLA found (0). APIs generally available, and MCP dynamic authentication went GA on 17 June 2026 (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": "maintenance",
        "name": "Maintenance \u0026 community",
        "score": 60,
        "maxGain": 3.5,
        "reason": "Newest entry on the releases page is 9 September 2026, JSONata in step inputs (30). Five dated entries since 3 July 2026, including Tray Sync CLI on 19 August and log masking on 14 July (20). Dated releases page and a support channel. We didn't test response times (10). No official SDK and no entry in the official MCP registry found (0). Nothing public to judge package health (0).",
        "checklist": [
          "- 0 to 30, time since the last release, or the last published model or API change for a closed service. 30 within 30 days, 20 within 90, 10 within 180, 0 older.\n- 20, at least three releases or dated changelog entries in the last 90 days.\n- 0 to 25, responsiveness. Issues and pull requests answered on GitHub (the open issues and how recent the replies are). For closed services, a public changelog and a support or community channel that answers, 0 to 15.\n- 15, presence in the official MCP registry under a verified namespace (MCP servers), or current official SDKs (APIs and models).\n- 10, package health, current dependencies and CI.",
          "Models are read for deprecation notice periods and model churn rather than release counts."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-maintenance"
      },
      {
        "key": "schema",
        "name": "Schema \u0026 documentation",
        "score": 80,
        "maxGain": 3.3,
        "reason": "OpenAPI file for the REST APIs at trayapi.yaml, per the 30 September check (25). llms.txt, llms-full.txt and Markdown copies of docs pages (10). We didn't read the Headless MCP tool definitions, and the docs describe capabilities rather than individual tools (10). Connector operations have typed input schemas, though some take free-form bodies (10). Examples throughout, and the 429-inside-200 behaviour is documented, but no full error catalogue found (10). Versioned at /core/v1 with a dated releases page (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": "transparency",
        "name": "Transparency \u0026 trust",
        "score": 69,
        "maxGain": 2.7,
        "reason": "Closed service under a published MSA (15). Trust centre with audit reports, a subprocessor list, Data Privacy Framework certification, and log retention settable from 30 days down to 24 hours or off (26). No deprecation policy or dated deprecation notices in the releases we read (6). Subprocessors listed and US, EU and APAC regions disclosed (20).",
        "blend": "editorial 67, provenance 71",
        "checklist": [
          "- 0 to 30, source availability and licence clarity. 30 for open source under an OSI licence, 15 for closed with clear terms, 0 for unclear terms.\n- 0 to 30, data handling and retention statements that agree with each other (privacy policy, DPA, retention periods, subprocessors).\n- 0 to 20, a deprecation policy or notices with dates.\n- 0 to 20, telemetry disclosed with an opt-out (local software), or subprocessors and data locations disclosed (hosted).",
          "The other half of Transparency and trust is the provenance score, computed from checked facts (below). The category score is the mean of the two."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-transparency"
      }
    ],
    "provenance": [
      {
        "label": "Domain age",
        "value": "tray.ai, registered 2017-12-15 (8 years)",
        "points": 11,
        "max": 15
      },
      {
        "label": "Endpoint on the vendor's domain",
        "value": "api.tray.io is not on tray.ai",
        "points": 0,
        "max": 15
      },
      {
        "label": "security.txt",
        "value": "not found",
        "points": 0,
        "max": 10
      }
    ],
    "unchecked": [
      "unchecked: the Headless MCP tool list and its tool count",
      "Whether Tray's own 429 responses carry Retry-After",
      "Whether a newer SOC 2 report covers the period after 31 July 2025",
      "The length and card terms of the free trial",
      "unchecked: pagination and output-size controls on the REST and GraphQL APIs"
    ],
    "weaknesses": [
      "No published prices and no self-serve plan",
      "Upstream 429s are wrapped in a 200, which hides throttling from naive retry logic",
      "Headless MCP can delete projects, workflows and auths with no server-side confirmation",
      "No official SDK and no tool annotations",
      "API lives on api.tray.io while the brand, docs and legal pages are on tray.ai"
    ],
    "agentNotes": [
      "Use a user token when acting for a customer and the master token only for admin work",
      "Parse the body of call-connector responses for upstream status codes before treating a 200 as success",
      "Point Headless MCP at the workspace's region, api.eu1.tray.io or api.ap1.tray.io outside the US",
      "Pick the workspace at OAuth sign-in. Headless MCP binds it to the session and takes no workspace ID",
      "Ask before any Headless MCP delete. The server won't"
    ],
    "requests": [
      {
        "text": "deprecation policy",
        "reviews": 1
      },
      {
        "text": "server-side delete confirmation",
        "reviews": 1
      },
      {
        "text": "tool annotations",
        "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"
  }
}