{
  "fixes": {
    "slug": "rocketreach",
    "name": "RocketReach API",
    "listing": "https://www.anchorterminal.com/tools/rocketreach",
    "markdown": "# Fix list: RocketReach API\n\nFrom Anchor Terminal's listing at https://www.anchorterminal.com/tools/rocketreach, the October 2026 research run, assessed 9 October 2026. Grade D, 51.2 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 RocketReach API: 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, 34 out of 100, up to 11.6 more on the total\n\nWhy it scored 34: REST takes one key per account in the `Api-Key` header. Only one key is active at a time and generating a new one invalidates the old. The MCP server uses OAuth 2.1 with PKCE, open dynamic client registration, one-hour access tokens, 30-day refresh tokens that rotate, and a revocation endpoint. The access token carries the API key inside an encrypted envelope, and the `account` tool returns `api_key` in its response, so the key reaches the model's context (18 of 30). The docs say older clients may still send the key as an `api_key` query parameter, marked deprecated (5 off, 13). One scope, `rocketreach:read`, covers every tool, including lookups that spend credits and add contacts to My Contacts. No read-only mode, per-key limit or confirmation step was found. The account object has an `api_key_domain` field (4 of 20). Results are third-party profile data. No prompt-injection guidance was found (3 of 15). Usage and rate-limit counts from the account endpoint, a recent-errors panel in account settings, `RR-Request-ID` on webhooks, and MCP lookups tagged with the client name. No per-call log was found (8 of 15). security.txt is valid, with a contact address and an expiry of 8 June 2029. The DPA lists security measures in an annex and names a Trust Centre that we did not find linked. No certification or bug bounty was found (6 of 20). Total 34.\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. Payments \u0026 pricing, 10 out of 100, up to 11.3 more on the total\n\nWhy it scored 10: No x402, MPP or L402 in the docs or terms (0). The docs publish credit costs per action for Universal Credits, such as 2 credits for a professional email and 6 for a phone. The pricing page is drawn by script and showed our reader only its title, so no price in dollars was read, and the docs tell users without a paid plan to email for an API plan (5 of 20). The site's description says to try for free, and the rate-limit page implies an unpaid account can call the API until throttled. What a free account gets through the API was not established (5 of 20). A person signs up in a browser, the terms say account holders warrant they are human, and MCP authorisation needs a browser login (0). Total 10. The pricing lines are scored on what could be read.\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## 3. Reliability, 64 out of 100, up to 7.2 more on the total\n\nWhy it scored 64: Hosted lines. Status page on incident.io at status.rocketreach.co with five components, among them API and MCP (20). In the last 90 days it lists eight entries. On 20 August 2026 degraded performance ran from 12:00 AM to 10:00 AM across the site, extension, API and MCP, with a second hour that afternoon, delayed webhooks and a 29-minute outage in the evening. On 27 August elevated errors lasted 61 minutes. A 71-minute maintenance window on 27 September, in which the notice said API and MCP calls would be unresponsive or throttled, was announced on 15 September. Read as one major day and a second incident of about an hour (7 of 30). Rate limits published per plan and endpoint, plus a global 10 requests a second (15). 429 carries `Retry-After` and the docs show a retry example. No idempotency keys, though repeat lookups are free (12 of 15). No SLA found in the terms, the subscription agreement or the docs (0). The API and MCP server are not marked beta (10). Total 64.\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## 4. Maintenance \u0026 community, 31 out of 100, up to 6 more on the total\n\nWhy it scored 31: No changelog or release notes were found. The docs pages carry update dates. Four were updated on 8 October 2026 and the Email Verify reference on 11 September 2026. Read as recent API activity from docs metadata and not from a release record (20 of 30). No dated changelog entries (0 of 20). Support by email and a status page that posts updates. The help centre answered 403 and was not read (5 of 15). The Python SDK on GitHub is at 2.1.8 with its last code change on 26 March 2025 and no tags. The official MCP registry answered 500 to our search, so a registry entry is unchecked (3 of 15). The SDK repository has a Renovate configuration and states Python 3.4 or later (3 of 10). Total 31.\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## 5. Schema \u0026 documentation, 72 out of 100, up to 4.6 more on the total\n\nWhy it scored 72: Each reference page's Markdown twin carries an OpenAPI 3.1 definition for its operation, 17 operations in all. No single downloadable file was found (22 of 25). llms.txt and Markdown twins on the docs host (10). The MCP tools page states what each tool returns, what it costs and which tool to call next. REST operation descriptions are thin, and Company Lookup carries the Company Search subtitle (14 of 20). Query parameters are typed, with enums on `lookup_type` and `order_by`. No lookup parameter is marked required although one identifier is needed, and `metadata` is a free object (10 of 15). Error table, a worked 402 body, an MCP error catalogue and response examples. Every operation lists the same generic error set (11 of 15). The version sits in the path (`/api/v2`), with the Universal Credits endpoints alongside. No changelog was found (5 of 15). Total 72.\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## 6. Agent ergonomics, 72 out of 100, up to 4.6 more on the total\n\nWhy it scored 72: The MCP server documents nine tools. We read the docs page and did not connect, so the size of the live definitions is unread (22 of 25). `start`, `page_size` up to 100, `order_by`, an `exclude` object and about 50 search facets, with a ceiling of 10,000 results a query (18 of 20). MCP errors carry `error_code` in `_meta` with `retry_after_seconds`, `credit_type` or `field` and `reason`. On REST only the 402 from email verification is structured, and running out of lookup credits returns a 403 with a text `detail` (15 of 20). Repeat lookups and polling are free and terminal errors are named. No idempotency keys, and MCP tool annotations were not read (9 of 20). Few parameters are needed for a call. One official SDK, Python 2.1.8, whose last code change is dated 26 March 2025 (8 of 15). Total 72.\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## 7. Transparency \u0026 trust, 58 out of 100, up to 3.7 more on the total\n\nMade of editorial 45, provenance 70.\n\nWhy it scored 58: Closed service with terms that name RocketReach, LLC and cover the API (15 of 30). The privacy policy, updated 30 September 2026, covers people in the database as well as customers. It names sources (public web pages, data brokers, and customers' connected email accounts by opt-in), a removal form, a DPO, EU and UK representatives, a Texas data broker notice and 2025 request counts. A DPA is public. Retention has no stated period (20 of 30). The API definitions mark deprecated fields with no dates, and no deprecation policy was found (4 of 20). The policy says data is collected and held in the US. The DPA says a sub-processor list is in a Trust Centre, which we did not find linked and did not read (6 of 20). Total 45.\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: rocketreach.co, no registry record we could read (0 of 15)\n- Terms of service: read, states 6 of the 7 things a reader expects, and has 2 clauses that cost points (5.1 of 10)\n- Changelog: 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: plan prices, what each plan includes, and whether a free account or trial includes API access. https://rocketreach.co/pricing is drawn by script and showed only its title to curl and to our reader\n- unchecked: the help centre at knowledgebase.rocketreach.co, which answered 403 to its first page request. We did not retry\n- unchecked: a Trust Centre the DPA names as holding the sub-processor list. No page read links it, so certifications and sub-processors are scored as not found\n- unchecked: the official MCP registry. Its search answered 500, so `registryName` is empty\n- unchecked: the domain registration date. rdap.org has no RDAP service for rocketreach.co\n- unchecked: live MCP tool definitions and annotations. We read the docs page and did not connect\n- unchecked: download counts and repository stars for the Python SDK\n- The site's home page is drawn by script and links nothing. The pricing, terms and privacy pages were requested at their conventional addresses, which the terms page then confirmed in its own links\n- The terms (updated 31 January 2024) say account holders warrant they are human, bar accounts registered by automated methods, and forbid scripts or robots that extract lookup data. Recorded as a fact with no deduction. It matters before any probe is run\n- Two credit systems are documented side by side (lookup and export credits, and Universal Credits). Which one a new account gets was not established\n\n## Weaknesses\n\n- The pricing page is drawn by script and was not read, and the docs tell users without a paid plan to email for an API plan\n- The MCP `account` tool returns the account's API key in its response, and the OAuth access token carries the same key inside it\n- One API key per account with no scopes. The single MCP scope `rocketreach:read` covers the tools that spend credits and add contacts\n- On 20 August 2026 the status page shows ten hours of degraded performance across the site, API and MCP, then a 29-minute outage\n- The terms say account holders warrant they are human and forbid automated extraction of lookup data. No deduction is taken, and it matters before any probe is run\n- No changelog or deprecation policy was found, and the Python SDK's last code change is dated 26 March 2025\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- Search first with `person_search` or `company_search`, which cost no credits, then look up only the profile IDs needed\n- Treat `status: \"pending\"` as normal. Poll `check_person_status` after at least 3 seconds, and polling is free\n- Do not echo the `account` tool's output to users or logs. It includes the account's API key\n- Send the key in the `Api-Key` header. The `api_key` query parameter is deprecated\n- Bulk lookup takes 1 to 100 queries and needs a webhook. Results arrive at the webhook, signed in `X-RocketReach-Signature`\n- Do not loop on `unknown` from `email_verify`, or on `lookup_failed` and `not_found`. The last two are terminal\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": 51.2,
    "assessed": "2026-10-09",
    "run": "October 2026 research run",
    "categories": [
      {
        "key": "security",
        "name": "Security \u0026 auth",
        "score": 34,
        "maxGain": 11.6,
        "reason": "REST takes one key per account in the `Api-Key` header. Only one key is active at a time and generating a new one invalidates the old. The MCP server uses OAuth 2.1 with PKCE, open dynamic client registration, one-hour access tokens, 30-day refresh tokens that rotate, and a revocation endpoint. The access token carries the API key inside an encrypted envelope, and the `account` tool returns `api_key` in its response, so the key reaches the model's context (18 of 30). The docs say older clients may still send the key as an `api_key` query parameter, marked deprecated (5 off, 13). One scope, `rocketreach:read`, covers every tool, including lookups that spend credits and add contacts to My Contacts. No read-only mode, per-key limit or confirmation step was found. The account object has an `api_key_domain` field (4 of 20). Results are third-party profile data. No prompt-injection guidance was found (3 of 15). Usage and rate-limit counts from the account endpoint, a recent-errors panel in account settings, `RR-Request-ID` on webhooks, and MCP lookups tagged with the client name. No per-call log was found (8 of 15). security.txt is valid, with a contact address and an expiry of 8 June 2029. The DPA lists security measures in an annex and names a Trust Centre that we did not find linked. No certification or bug bounty was found (6 of 20). Total 34.",
        "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": "payments",
        "name": "Payments \u0026 pricing",
        "score": 10,
        "maxGain": 11.3,
        "reason": "No x402, MPP or L402 in the docs or terms (0). The docs publish credit costs per action for Universal Credits, such as 2 credits for a professional email and 6 for a phone. The pricing page is drawn by script and showed our reader only its title, so no price in dollars was read, and the docs tell users without a paid plan to email for an API plan (5 of 20). The site's description says to try for free, and the rate-limit page implies an unpaid account can call the API until throttled. What a free account gets through the API was not established (5 of 20). A person signs up in a browser, the terms say account holders warrant they are human, and MCP authorisation needs a browser login (0). Total 10. The pricing lines are scored on what could be read.",
        "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": 64,
        "maxGain": 7.2,
        "reason": "Hosted lines. Status page on incident.io at status.rocketreach.co with five components, among them API and MCP (20). In the last 90 days it lists eight entries. On 20 August 2026 degraded performance ran from 12:00 AM to 10:00 AM across the site, extension, API and MCP, with a second hour that afternoon, delayed webhooks and a 29-minute outage in the evening. On 27 August elevated errors lasted 61 minutes. A 71-minute maintenance window on 27 September, in which the notice said API and MCP calls would be unresponsive or throttled, was announced on 15 September. Read as one major day and a second incident of about an hour (7 of 30). Rate limits published per plan and endpoint, plus a global 10 requests a second (15). 429 carries `Retry-After` and the docs show a retry example. No idempotency keys, though repeat lookups are free (12 of 15). No SLA found in the terms, the subscription agreement or the docs (0). The API and MCP server are not marked beta (10). Total 64.",
        "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": 31,
        "maxGain": 6,
        "reason": "No changelog or release notes were found. The docs pages carry update dates. Four were updated on 8 October 2026 and the Email Verify reference on 11 September 2026. Read as recent API activity from docs metadata and not from a release record (20 of 30). No dated changelog entries (0 of 20). Support by email and a status page that posts updates. The help centre answered 403 and was not read (5 of 15). The Python SDK on GitHub is at 2.1.8 with its last code change on 26 March 2025 and no tags. The official MCP registry answered 500 to our search, so a registry entry is unchecked (3 of 15). The SDK repository has a Renovate configuration and states Python 3.4 or later (3 of 10). Total 31.",
        "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": 72,
        "maxGain": 4.6,
        "reason": "Each reference page's Markdown twin carries an OpenAPI 3.1 definition for its operation, 17 operations in all. No single downloadable file was found (22 of 25). llms.txt and Markdown twins on the docs host (10). The MCP tools page states what each tool returns, what it costs and which tool to call next. REST operation descriptions are thin, and Company Lookup carries the Company Search subtitle (14 of 20). Query parameters are typed, with enums on `lookup_type` and `order_by`. No lookup parameter is marked required although one identifier is needed, and `metadata` is a free object (10 of 15). Error table, a worked 402 body, an MCP error catalogue and response examples. Every operation lists the same generic error set (11 of 15). The version sits in the path (`/api/v2`), with the Universal Credits endpoints alongside. No changelog was found (5 of 15). Total 72.",
        "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": "ergonomics",
        "name": "Agent ergonomics",
        "score": 72,
        "maxGain": 4.6,
        "reason": "The MCP server documents nine tools. We read the docs page and did not connect, so the size of the live definitions is unread (22 of 25). `start`, `page_size` up to 100, `order_by`, an `exclude` object and about 50 search facets, with a ceiling of 10,000 results a query (18 of 20). MCP errors carry `error_code` in `_meta` with `retry_after_seconds`, `credit_type` or `field` and `reason`. On REST only the 402 from email verification is structured, and running out of lookup credits returns a 403 with a text `detail` (15 of 20). Repeat lookups and polling are free and terminal errors are named. No idempotency keys, and MCP tool annotations were not read (9 of 20). Few parameters are needed for a call. One official SDK, Python 2.1.8, whose last code change is dated 26 March 2025 (8 of 15). Total 72.",
        "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": 58,
        "maxGain": 3.7,
        "reason": "Closed service with terms that name RocketReach, LLC and cover the API (15 of 30). The privacy policy, updated 30 September 2026, covers people in the database as well as customers. It names sources (public web pages, data brokers, and customers' connected email accounts by opt-in), a removal form, a DPO, EU and UK representatives, a Texas data broker notice and 2025 request counts. A DPA is public. Retention has no stated period (20 of 30). The API definitions mark deprecated fields with no dates, and no deprecation policy was found (4 of 20). The policy says data is collected and held in the US. The DPA says a sub-processor list is in a Trust Centre, which we did not find linked and did not read (6 of 20). Total 45.",
        "blend": "editorial 45, provenance 70",
        "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": "rocketreach.co, no registry record we could read",
        "points": 0,
        "max": 15
      },
      {
        "label": "Terms of service",
        "value": "read, states 6 of the 7 things a reader expects, and has 2 clauses that cost points",
        "points": 5.1,
        "max": 10
      },
      {
        "label": "Changelog",
        "value": "not found",
        "points": 0,
        "max": 10
      }
    ],
    "unchecked": [
      "unchecked: plan prices, what each plan includes, and whether a free account or trial includes API access. https://rocketreach.co/pricing is drawn by script and showed only its title to curl and to our reader",
      "unchecked: the help centre at knowledgebase.rocketreach.co, which answered 403 to its first page request. We did not retry",
      "unchecked: a Trust Centre the DPA names as holding the sub-processor list. No page read links it, so certifications and sub-processors are scored as not found",
      "unchecked: the official MCP registry. Its search answered 500, so `registryName` is empty",
      "unchecked: the domain registration date. rdap.org has no RDAP service for rocketreach.co",
      "unchecked: live MCP tool definitions and annotations. We read the docs page and did not connect",
      "unchecked: download counts and repository stars for the Python SDK",
      "The site's home page is drawn by script and links nothing. The pricing, terms and privacy pages were requested at their conventional addresses, which the terms page then confirmed in its own links",
      "The terms (updated 31 January 2024) say account holders warrant they are human, bar accounts registered by automated methods, and forbid scripts or robots that extract lookup data. Recorded as a fact with no deduction. It matters before any probe is run",
      "Two credit systems are documented side by side (lookup and export credits, and Universal Credits). Which one a new account gets was not established"
    ],
    "weaknesses": [
      "The pricing page is drawn by script and was not read, and the docs tell users without a paid plan to email for an API plan",
      "The MCP `account` tool returns the account's API key in its response, and the OAuth access token carries the same key inside it",
      "One API key per account with no scopes. The single MCP scope `rocketreach:read` covers the tools that spend credits and add contacts",
      "On 20 August 2026 the status page shows ten hours of degraded performance across the site, API and MCP, then a 29-minute outage",
      "The terms say account holders warrant they are human and forbid automated extraction of lookup data. No deduction is taken, and it matters before any probe is run",
      "No changelog or deprecation policy was found, and the Python SDK's last code change is dated 26 March 2025"
    ],
    "agentNotes": [
      "Search first with `person_search` or `company_search`, which cost no credits, then look up only the profile IDs needed",
      "Treat `status: \"pending\"` as normal. Poll `check_person_status` after at least 3 seconds, and polling is free",
      "Do not echo the `account` tool's output to users or logs. It includes the account's API key",
      "Send the key in the `Api-Key` header. The `api_key` query parameter is deprecated",
      "Bulk lookup takes 1 to 100 queries and needs a webhook. Results arrive at the webhook, signed in `X-RocketReach-Signature`",
      "Do not loop on `unknown` from `email_verify`, or on `lookup_failed` and `not_found`. The last two are terminal"
    ],
    "recheck": "https://www.anchorterminal.com/builders/#disputes"
  },
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-10-10",
    "license": "CC-BY-4.0",
    "method": "https://www.anchorterminal.com/benchmark/",
    "methodology": "0.4",
    "openapi": "https://www.anchorterminal.com/openapi.json",
    "preview": false,
    "run": "2026-10-01",
    "runLabel": "October 2026 research run"
  }
}