{
  "fixes": {
    "slug": "crustdata",
    "name": "Crustdata API + MCP",
    "listing": "https://www.anchorterminal.com/tools/crustdata",
    "markdown": "# Fix list: Crustdata API + MCP\n\nFrom Anchor Terminal's listing at https://www.anchorterminal.com/tools/crustdata, the October 2026 research run, assessed 1 October 2026. Grade D, 53.5 out of 100.\n\nThis is everything the published grade says the listing lacks, the biggest possible gain to the total first. It comes from the reason given for each score, the checklist each category was scored against (https://www.anchorterminal.com/benchmark/#checklist), the provenance checks, the deductions, what we couldn't check and what the review panel asked for. A fix counts at the next check, once it's public.\n\nFor a coding agent working on Crustdata 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, 5 out of 100, up to 11.9 more on the total\n\nWhy it scored 5: No x402, MPP or L402 (0). Credit costs per endpoint and field are public, but no dollar price per credit or plan is, and the pricing page sends larger buyers to sales. We gave 5 rather than 0 because an agent can work out relative cost from the public credit table (5). Free trial on request, no self-serve free tier (0). A person signs up and talks to the vendor (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, 45 out of 100, up to 11 more on the total\n\nWhy it scored 45: No status page found. status.crustdata.com doesn't resolve and the docs link none (0). No readable incident history (5). Default rate limits published per endpoint group, 15 a minute on enrich, 30 on search, 10 on live lookups, 300 on autocomplete (15). 429s return a typed `rate_limit_error` with `X-RateLimit-Limit`, `-Remaining` and `-Reset` headers, `Retry-After` on batch concurrency limits, back-off with jitter recommended, and batch guidance to poll before resubmitting (15). No SLA found, and the published terms cover the website only (0). The API is generally available. Natural-language person search is labelled beta, but the core endpoints aren't (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, 56 out of 100, up to 7.7 more on the total\n\nWhy it scored 56: Bearer keys, several named keys per account with active, inactive and deleted states, per-key endpoint restrictions and monthly credit caps since July 2026. OAuth for the MCP (28 of 30). Per-key endpoint limits give least privilege. Watchers create standing jobs, and the MCP docs don't separate read and write tools or ask for confirmation (12 of 20). Live web fetch, web search and social posts return untrusted text, and we found no prompt-injection guidance (2 of 15). Usage and logs filterable by key, a usage events API from October 2026, and `X-Credits-Used` on every response (14 of 15). No security.txt, bug bounty, disclosure policy or certification found (0 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, 73 out of 100, up to 4.4 more on the total\n\nWhy it scored 73: Premium field groups are opt-in and billed per group, cursor pagination, and the MCP publishes its tool catalogue as a resource instead of a long tools/list (22 of 25). Cursor pagination and rich filters (20). Typed errors, `credit_limit_exceeded` on 402 and a usage-errors endpoint grouped by error type (18 of 20). Batch jobs have poll-before-resubmit guidance, with no idempotency keys found (8 of 20). Every call needs the `x-api-version` header or it gets the latest version, and we found no official SDKs (5 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, 56 out of 100, up to 3.9 more on the total\n\nMade of editorial 36, provenance 76.\n\nWhy it scored 56: Closed service. The terms are a website-use notice naming CrustData Inc. (California), while the privacy policy names Crustdata Technologies Inc., and we found no API terms (8 of 30). The privacy policy (updated 19 May 2025) covers people in the datasets, cites consent, contract and legitimate interests, and runs an opt-out portal that removes data within 30 days and blocks it from coming back. Retention has no periods and no DPA is mentioned (15 of 30). Date-pinned versions and migration guides, but breaking changes inside the pinned version with no dated notice (8 of 20). US transfers stated, no subprocessor list (5 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: crustdata.com, registered 2019-03-18 (7 years) (11 of 15)\n- Status page: not found (0 of 10)\n- security.txt: not found (0 of 10)\n\n## 6. Maintenance \u0026 community, 67 out of 100, up to 2.9 more on the total\n\nWhy it scored 67: Newest changelog entry is the Usage API in October 2026 (30). Over twenty dated entries since July (20). Detailed public changelog, and we didn't test support (12 of 15). The only registry entry, io.github.mhimed-crustdata/crustdata, sits under a personal GitHub namespace, and we found no official SDKs (0). Versioned specs are current. No packages to judge (5 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, 89 out of 100, up to 1.8 more on the total\n\nWhy it scored 89: Eight OpenAPI YAML files for version 2025-11-01, one per API group (account, batch, company, job, person, social_post, watch, web) (25). llms.txt with Markdown twins (10). Endpoint pages explain cost and when to search versus enrich (17 of 20). Typed filter trees with documented operators (12 of 15). Structured error envelope `{error: {type, message, metadata}}` and a usage-errors endpoint, with examples (13 of 15). Date-pinned API versions and a detailed changelog. Three changelog entries since August are flagged breaking inside the same pinned version, which undercuts the pin (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## Deductions\n\nEach comes off the total. A fixed and documented problem counts for less at the next check.\n\n- In September 2026 the changelog flags `config.refresh_frequency_days` as refused on indexed discovery watches, a breaking change shipped inside the pinned version 2025-11-01 with no advance notice found (https://docs.crustdata.com/openapi-specs/2025-11-01/changelog.md)\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- The dollar price of a credit on any plan\n- Which legal entity contracts for the API, since the terms and privacy policy name different companies and no API terms were found\n- The listing's openapi field was null. We've set it to the person spec, one of eight files for version 2025-11-01\n- unchecked: the tool count on the hosted MCP, which publishes its list as a resource\n\n## Weaknesses\n\n- No status page and no SLA\n- No public dollar price per credit, and the free trial is on request\n- Breaking changes shipped inside the pinned version 2025-11-01\n- Default limits of 15 to 30 requests a minute\n- Terms cover website use only, and terms and privacy policy name different companies\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- Always send `x-api-version: 2025-11-01`. Unpinned calls get the latest version\n- Call `/account/endpoints` first to see what your plan enables and what each field costs\n- Ask only for the premium field groups you need, since each one bills\n- Poll `GET /batch/{id}` before submitting more batch jobs. Active jobs count against a cap of 5 to 30\n- Read the `crustdata://catalog` resource before calling MCP tools\n\n## What the review panel asked for\n\n- publish a dollar price per credit\n- add a self-serve free tier\n- a disclosure policy\n- API terms of service\n\n## When it's done\n\nSend what changed and where it's published as a dispute (https://www.anchorterminal.com/builders/#disputes, or `POST https://www.anchorterminal.com/api/v1/contact` with `\"kind\": \"dispute\"`). Disputes are answered in public, and the listing is checked again by the same checklist. Paying for an audit or a listing claim changes nothing here.\n",
    "grade": "D",
    "score": 53.5,
    "assessed": "2026-10-01",
    "run": "October 2026 research run",
    "categories": [
      {
        "key": "payments",
        "name": "Payments \u0026 pricing",
        "score": 5,
        "maxGain": 11.9,
        "reason": "No x402, MPP or L402 (0). Credit costs per endpoint and field are public, but no dollar price per credit or plan is, and the pricing page sends larger buyers to sales. We gave 5 rather than 0 because an agent can work out relative cost from the public credit table (5). Free trial on request, no self-serve free tier (0). A person signs up and talks to the vendor (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": 45,
        "maxGain": 11,
        "reason": "No status page found. status.crustdata.com doesn't resolve and the docs link none (0). No readable incident history (5). Default rate limits published per endpoint group, 15 a minute on enrich, 30 on search, 10 on live lookups, 300 on autocomplete (15). 429s return a typed `rate_limit_error` with `X-RateLimit-Limit`, `-Remaining` and `-Reset` headers, `Retry-After` on batch concurrency limits, back-off with jitter recommended, and batch guidance to poll before resubmitting (15). No SLA found, and the published terms cover the website only (0). The API is generally available. Natural-language person search is labelled beta, but the core endpoints aren't (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": 56,
        "maxGain": 7.7,
        "reason": "Bearer keys, several named keys per account with active, inactive and deleted states, per-key endpoint restrictions and monthly credit caps since July 2026. OAuth for the MCP (28 of 30). Per-key endpoint limits give least privilege. Watchers create standing jobs, and the MCP docs don't separate read and write tools or ask for confirmation (12 of 20). Live web fetch, web search and social posts return untrusted text, and we found no prompt-injection guidance (2 of 15). Usage and logs filterable by key, a usage events API from October 2026, and `X-Credits-Used` on every response (14 of 15). No security.txt, bug bounty, disclosure policy or certification found (0 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": 73,
        "maxGain": 4.4,
        "reason": "Premium field groups are opt-in and billed per group, cursor pagination, and the MCP publishes its tool catalogue as a resource instead of a long tools/list (22 of 25). Cursor pagination and rich filters (20). Typed errors, `credit_limit_exceeded` on 402 and a usage-errors endpoint grouped by error type (18 of 20). Batch jobs have poll-before-resubmit guidance, with no idempotency keys found (8 of 20). Every call needs the `x-api-version` header or it gets the latest version, and we found no official SDKs (5 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": 56,
        "maxGain": 3.9,
        "reason": "Closed service. The terms are a website-use notice naming CrustData Inc. (California), while the privacy policy names Crustdata Technologies Inc., and we found no API terms (8 of 30). The privacy policy (updated 19 May 2025) covers people in the datasets, cites consent, contract and legitimate interests, and runs an opt-out portal that removes data within 30 days and blocks it from coming back. Retention has no periods and no DPA is mentioned (15 of 30). Date-pinned versions and migration guides, but breaking changes inside the pinned version with no dated notice (8 of 20). US transfers stated, no subprocessor list (5 of 20).",
        "blend": "editorial 36, provenance 76",
        "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": "maintenance",
        "name": "Maintenance \u0026 community",
        "score": 67,
        "maxGain": 2.9,
        "reason": "Newest changelog entry is the Usage API in October 2026 (30). Over twenty dated entries since July (20). Detailed public changelog, and we didn't test support (12 of 15). The only registry entry, io.github.mhimed-crustdata/crustdata, sits under a personal GitHub namespace, and we found no official SDKs (0). Versioned specs are current. No packages to judge (5 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": 89,
        "maxGain": 1.8,
        "reason": "Eight OpenAPI YAML files for version 2025-11-01, one per API group (account, batch, company, job, person, social_post, watch, web) (25). llms.txt with Markdown twins (10). Endpoint pages explain cost and when to search versus enrich (17 of 20). Typed filter trees with documented operators (12 of 15). Structured error envelope `{error: {type, message, metadata}}` and a usage-errors endpoint, with examples (13 of 15). Date-pinned API versions and a detailed changelog. Three changelog entries since August are flagged breaking inside the same pinned version, which undercuts the pin (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"
      }
    ],
    "provenance": [
      {
        "label": "Domain age",
        "value": "crustdata.com, registered 2019-03-18 (7 years)",
        "points": 11,
        "max": 15
      },
      {
        "label": "Status page",
        "value": "not found",
        "points": 0,
        "max": 10
      },
      {
        "label": "security.txt",
        "value": "not found",
        "points": 0,
        "max": 10
      }
    ],
    "deductions": [
      "In September 2026 the changelog flags `config.refresh_frequency_days` as refused on indexed discovery watches, a breaking change shipped inside the pinned version 2025-11-01 with no advance notice found (https://docs.crustdata.com/openapi-specs/2025-11-01/changelog.md)"
    ],
    "unchecked": [
      "The dollar price of a credit on any plan",
      "Which legal entity contracts for the API, since the terms and privacy policy name different companies and no API terms were found",
      "The listing's openapi field was null. We've set it to the person spec, one of eight files for version 2025-11-01",
      "unchecked: the tool count on the hosted MCP, which publishes its list as a resource"
    ],
    "weaknesses": [
      "No status page and no SLA",
      "No public dollar price per credit, and the free trial is on request",
      "Breaking changes shipped inside the pinned version 2025-11-01",
      "Default limits of 15 to 30 requests a minute",
      "Terms cover website use only, and terms and privacy policy name different companies"
    ],
    "agentNotes": [
      "Always send `x-api-version: 2025-11-01`. Unpinned calls get the latest version",
      "Call `/account/endpoints` first to see what your plan enables and what each field costs",
      "Ask only for the premium field groups you need, since each one bills",
      "Poll `GET /batch/{id}` before submitting more batch jobs. Active jobs count against a cap of 5 to 30",
      "Read the `crustdata://catalog` resource before calling MCP tools"
    ],
    "requests": [
      {
        "text": "publish a dollar price per credit",
        "reviews": 1
      },
      {
        "text": "add a self-serve free tier",
        "reviews": 1
      },
      {
        "text": "a disclosure policy",
        "reviews": 1
      },
      {
        "text": "API terms of service",
        "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"
  }
}