{
  "fixes": {
    "slug": "hunter",
    "name": "Hunter API + MCP",
    "listing": "https://www.anchorterminal.com/tools/hunter",
    "markdown": "# Fix list: Hunter API + MCP\n\nFrom Anchor Terminal's listing at https://www.anchorterminal.com/tools/hunter, the October 2026 research run, assessed 1 October 2026. Grade C, 56.8 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 Hunter 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. Security \u0026 auth, 33 out of 100, up to 11.7 more on the total\n\nWhy it scored 33: API keys can be created and deleted, and the docs accept the key in a header, as a bearer token or in the `api_key` query string, which puts it in logs (20 less 10). OAuth for the MCP in Claude, ChatGPT and Gemini, `X-API-Key` elsewhere (15 of 30). No read-only mode. MCP tools can delete leads and lists in bulk, create and delete API keys and start sequences that send email, with no built-in confirmation (3 of 20). Results are emails, names and source URLs with little free text (8 of 15). Account usage via the API, no per-call log found (5 of 15). hunter.io/security returns 404, no security.txt, no bug bounty or certification found (2 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## 2. Reliability, 50 out of 100, up to 10 more on the total\n\nWhy it scored 50: A status page at status.hunter.io exists per the 30 September check, but it renders client-side and both the page and its incidents feed came back empty to us, so we couldn't confirm components (15 of 20) or read any history (5). Per-endpoint limits published, from 5 a second and 50 a minute on Discover to 15 a second and 500 a minute on Domain Search and Email Finder (15). Hitting a rate limit returns 403, while 429 means the plan's usage is spent. No Retry-After or back-off guidance found, apart from a 202 on the verifier that says to call again (5 of 15). No SLA found (0). Generally available (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. Agent ergonomics, 54 out of 100, up to 7.5 more on the total\n\nWhy it scored 54: The hosted MCP exposes about 100 tools (96 by our count of llms-full.txt on 1 October, 107 in the 30 September check) across search, enrichment, leads, lists, sequences and account admin, with no toolsets or read-only subset found. The REST side returns up to 100 rows a call (8 of 25). `limit` up to 100, `offset` up to 10,000, cursor pagination on multi-domain search (18 of 20). Structured errors, but rate limits answer 403 and quota exhaustion 429, which inverts what most clients expect (12 of 20). Repeat lookups within a billing period are free, which makes retries safe, but the MCP's delete and bulk-delete tools carry no annotations we could find (8 of 20). Few required parameters and a test key (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## 4. Payments \u0026 pricing, 40 out of 100, up to 7.5 more on the total\n\nWhy it scored 40: No x402, MPP or L402 (0). Plan prices are public, and units are clear, 1 credit per email found, 0.5 per verification, nothing when no result comes back (20). Free plan with 50 credits a month and API and MCP access, no card (20). A person signs up in a 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## 5. Maintenance \u0026 community, 63 out of 100, up to 3.2 more on the total\n\nWhy it scored 63: Three changelog entries on 2026-09-30, including the ChatGPT app and MCP setup paths (30). Three dated entries in the last 90 days, all on the same day (20). Public changelog and support. Issue handling not visible (10 of 15). Not in the official MCP registry. Third-party wrappers from pipeworx-io and scalably are listed instead. We didn't find current official SDKs (0). llms-full.txt tells agents to avoid a deprecated local npm MCP package (3 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## 6. Transparency \u0026 trust, 81 out of 100, up to 1.7 more on the total\n\nMade of editorial 71, provenance 90.\n\nWhy it scored 81: Closed service with terms naming Hunter Web Services, Inc. (15). The privacy policy (updated 13 April 2026) covers the people in Hunter's index, says profiles come from crawling public pages that allow it and from pattern-generated addresses, cites a legitimate interest assessment and a DPIA, takes removal requests at hunter.io/claim, drops profiles within 3 months of leaving their source page, and links a DPA. The API enforces opt-outs with a 451 (28 of 30). The changelog flagged the June 2026 switch to recipient-based engagement figures as affecting API users, and no deprecation policy found (8 of 20). Subprocessors at hunter.io/subprocessors and servers in Belgium (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- security.txt: not found (0 of 10)\n\n## 7. Schema \u0026 documentation, 90 out of 100, up to 1.6 more on the total\n\nWhy it scored 90: OpenAPI JSON at hunter.io/openapi.json covering the primary v2 operations (25). llms.txt, llms-full.txt and agents.md written for agents (10). Reference pages state purpose and credit rules per endpoint, and llms-full.txt adds usage advice such as listing tags before creating one (15 of 20). Typed parameters with documented maxima (12 of 15). Examples, a `test-api-key` that returns dummy responses, and an error envelope `{errors: [{id, code, details}]}` including 451 for people who opted out (14 of 15). v2 API and a public dated changelog (14 of 15).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-schema):\n\nAPIs and MCP servers.\n\n- 25, a machine-readable contract (a public OpenAPI file or similar; for MCP, typed JSON Schema inputs on every tool).\n- 10, llms.txt or Markdown docs served for agents.\n- 0 to 20, descriptions that say what a tool is for, when to use it and when not to, read from the tool definitions in the source or the API reference.\n- 0 to 15, typed inputs with enums, constraints and required fields, and no free-form JSON blobs.\n- 0 to 15, examples and documented error responses.\n- 15, versioning and a public changelog.\n\nModels are read from the API reference, the OpenAPI file, llms.txt, the structured-output and tool-use docs and the model cards. Frameworks from docs a model can follow, typed interfaces, examples and the API reference.\n\n## What we couldn't check\n\nWhat we couldn't read counted as absent. Publishing it on a page a plain HTTP fetch can read (not only in a browser) lets the next check count it.\n\n- MCP tool count, 96 by our count of llms-full.txt against 107 in the 30 September check. We left toolCount alone\n- unchecked: status page components and incident history, since the page renders client-side\n- Whether API keys can be scoped to endpoints or read-only use\n- Whether Hunter publishes official SDKs\n\n## Weaknesses\n\n- Hosted MCP has about 100 tools, including bulk deletes and API key creation, with no read-only mode\n- API key accepted in the `api_key` query string\n- Rate limits answer 403 and quota exhaustion answers 429\n- No security page, security.txt, bug bounty or certification found\n- Status page renders client-side and its history couldn't be read\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- Treat 451 as final. The person opted out and retrying won't help\n- Back off on 403 with a rate-limit message. 429 means the plan's credits are gone\n- Send the key in `X-API-Key`, never as `?api_key=`\n- Use `test-api-key` to check request shapes without spending credits\n- Use the hosted MCP at mcp.hunter.io/mcp, not the deprecated local npm package\n\n## What the review panel asked for\n\n- publish overage pricing\n- read-only MCP mode\n- drop query-string keys\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": 56.8,
    "assessed": "2026-10-01",
    "run": "October 2026 research run",
    "categories": [
      {
        "key": "security",
        "name": "Security \u0026 auth",
        "score": 33,
        "maxGain": 11.7,
        "reason": "API keys can be created and deleted, and the docs accept the key in a header, as a bearer token or in the `api_key` query string, which puts it in logs (20 less 10). OAuth for the MCP in Claude, ChatGPT and Gemini, `X-API-Key` elsewhere (15 of 30). No read-only mode. MCP tools can delete leads and lists in bulk, create and delete API keys and start sequences that send email, with no built-in confirmation (3 of 20). Results are emails, names and source URLs with little free text (8 of 15). Account usage via the API, no per-call log found (5 of 15). hunter.io/security returns 404, no security.txt, no bug bounty or certification found (2 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": "reliability",
        "name": "Reliability",
        "score": 50,
        "maxGain": 10,
        "reason": "A status page at status.hunter.io exists per the 30 September check, but it renders client-side and both the page and its incidents feed came back empty to us, so we couldn't confirm components (15 of 20) or read any history (5). Per-endpoint limits published, from 5 a second and 50 a minute on Discover to 15 a second and 500 a minute on Domain Search and Email Finder (15). Hitting a rate limit returns 403, while 429 means the plan's usage is spent. No Retry-After or back-off guidance found, apart from a 202 on the verifier that says to call again (5 of 15). No SLA found (0). Generally available (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": "ergonomics",
        "name": "Agent ergonomics",
        "score": 54,
        "maxGain": 7.5,
        "reason": "The hosted MCP exposes about 100 tools (96 by our count of llms-full.txt on 1 October, 107 in the 30 September check) across search, enrichment, leads, lists, sequences and account admin, with no toolsets or read-only subset found. The REST side returns up to 100 rows a call (8 of 25). `limit` up to 100, `offset` up to 10,000, cursor pagination on multi-domain search (18 of 20). Structured errors, but rate limits answer 403 and quota exhaustion 429, which inverts what most clients expect (12 of 20). Repeat lookups within a billing period are free, which makes retries safe, but the MCP's delete and bulk-delete tools carry no annotations we could find (8 of 20). Few required parameters and a test key (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": "payments",
        "name": "Payments \u0026 pricing",
        "score": 40,
        "maxGain": 7.5,
        "reason": "No x402, MPP or L402 (0). Plan prices are public, and units are clear, 1 credit per email found, 0.5 per verification, nothing when no result comes back (20). Free plan with 50 credits a month and API and MCP access, no card (20). A person signs up in a 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": "maintenance",
        "name": "Maintenance \u0026 community",
        "score": 63,
        "maxGain": 3.2,
        "reason": "Three changelog entries on 2026-09-30, including the ChatGPT app and MCP setup paths (30). Three dated entries in the last 90 days, all on the same day (20). Public changelog and support. Issue handling not visible (10 of 15). Not in the official MCP registry. Third-party wrappers from pipeworx-io and scalably are listed instead. We didn't find current official SDKs (0). llms-full.txt tells agents to avoid a deprecated local npm MCP package (3 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": "transparency",
        "name": "Transparency \u0026 trust",
        "score": 81,
        "maxGain": 1.7,
        "reason": "Closed service with terms naming Hunter Web Services, Inc. (15). The privacy policy (updated 13 April 2026) covers the people in Hunter's index, says profiles come from crawling public pages that allow it and from pattern-generated addresses, cites a legitimate interest assessment and a DPIA, takes removal requests at hunter.io/claim, drops profiles within 3 months of leaving their source page, and links a DPA. The API enforces opt-outs with a 451 (28 of 30). The changelog flagged the June 2026 switch to recipient-based engagement figures as affecting API users, and no deprecation policy found (8 of 20). Subprocessors at hunter.io/subprocessors and servers in Belgium (20).",
        "blend": "editorial 71, provenance 90",
        "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": 90,
        "maxGain": 1.6,
        "reason": "OpenAPI JSON at hunter.io/openapi.json covering the primary v2 operations (25). llms.txt, llms-full.txt and agents.md written for agents (10). Reference pages state purpose and credit rules per endpoint, and llms-full.txt adds usage advice such as listing tags before creating one (15 of 20). Typed parameters with documented maxima (12 of 15). Examples, a `test-api-key` that returns dummy responses, and an error envelope `{errors: [{id, code, details}]}` including 451 for people who opted out (14 of 15). v2 API and a public dated changelog (14 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": "security.txt",
        "value": "not found",
        "points": 0,
        "max": 10
      }
    ],
    "unchecked": [
      "MCP tool count, 96 by our count of llms-full.txt against 107 in the 30 September check. We left toolCount alone",
      "unchecked: status page components and incident history, since the page renders client-side",
      "Whether API keys can be scoped to endpoints or read-only use",
      "Whether Hunter publishes official SDKs"
    ],
    "weaknesses": [
      "Hosted MCP has about 100 tools, including bulk deletes and API key creation, with no read-only mode",
      "API key accepted in the `api_key` query string",
      "Rate limits answer 403 and quota exhaustion answers 429",
      "No security page, security.txt, bug bounty or certification found",
      "Status page renders client-side and its history couldn't be read"
    ],
    "agentNotes": [
      "Treat 451 as final. The person opted out and retrying won't help",
      "Back off on 403 with a rate-limit message. 429 means the plan's credits are gone",
      "Send the key in `X-API-Key`, never as `?api_key=`",
      "Use `test-api-key` to check request shapes without spending credits",
      "Use the hosted MCP at mcp.hunter.io/mcp, not the deprecated local npm package"
    ],
    "requests": [
      {
        "text": "publish overage pricing",
        "reviews": 1
      },
      {
        "text": "read-only MCP mode",
        "reviews": 1
      },
      {
        "text": "drop query-string keys",
        "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"
  }
}