# Fix list: FullEnrich API + MCP From Anchor Terminal's listing at https://www.anchorterminal.com/tools/fullenrich, the October 2026 research run, assessed 1 October 2026. Grade C, 59.8 out of 100. This 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. For a coding agent working on FullEnrich 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. ## 1. Reliability, 60 out of 100, up to 8 more on the total Why it scored 60: Better Stack status page, but with one component (app.fullenrich.com/app) and none for the API or MCP (15 of 20). The front page showed no incidents and 99.976 per cent uptime over 30 days. The history page refused us three times because of our own fetch limit, so July and August are unchecked (15 of 30). 60 calls a minute on every endpoint, 100 contacts a bulk and 100 concurrent enrichments per workspace (15). No 429 format, Retry-After or back-off guidance found. Identical re-submissions within 3 months aren't charged again, which makes retries cheap (5 of 15). No SLA found (0). Generally available, no beta label on the API or MCP (10). The checklist (https://www.anchorterminal.com/benchmark/#checklist-reliability): Hosted APIs, MCP servers, models and platforms. - 20, a public status page with component history (Statuspage, Instatus, BetterStack or the vendor's own). - 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. - 15, rate limits documented with numbers. - 15, documented 429 or overload handling (Retry-After, backoff guidance), and idempotency keys or safe-retry guidance where writes are involved. - 10, an SLA published for any paid tier. - 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. - 25, a public CI and test suite, passing on the default branch. - 0 to 25, open crash or regression issues relative to activity (25 for few and handled, 0 for many, old and unanswered). - 15, semver discipline and breaking changes called out in a changelog. - 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. ## 2. Security & auth, 55 out of 100, up to 7.9 more on the total Why it scored 55: Bearer API key for REST, no scopes found. The MCP signs in with OAuth and holds no static secret in the client. Webhooks are signed with HMAC-SHA1 keyed with the API key itself (20 of 30). The MCP isn't read-only, and confirmation before enrichment is recommended but left to the client. The skills add a confirmation before any sequencer change and honour opt-out and do-not-contact signals (10 of 20). Results are mostly structured contact fields (8 of 15). A free credits endpoint and nothing more for per-call visibility found (5 of 15). SOC 2 Type 2 per the trust page, vulnerability reports to support@fullenrich.com per the repo's SECURITY.md, no security.txt or bug bounty (12 of 20). The checklist (https://www.anchorterminal.com/benchmark/#checklist-security): - 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. - 0 to 20, read-only or least-privilege modes, and confirmation or approval for destructive actions. - 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. - 0 to 15, audit logs or per-call visibility for the operator. - 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. ## 3. Payments & pricing, 40 out of 100, up to 7.5 more on the total Why it scored 40: No x402, MPP or L402 (0). Per-unit credit costs and plan prices are public, 1 credit a work email, 3 a personal email, 10 a mobile, 0.25 a search result, from $55 for 1,000 credits (20). 50 trial credits with no card, API and MCP included (20). A person signs up in a browser (0). The checklist (https://www.anchorterminal.com/benchmark/#checklist-payments): 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. - 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. - 20, a free tier or trial that doesn't need a card. - 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. ## 4. Agent ergonomics, 60 out of 100, up to 6.5 more on the total Why it scored 60: 13 MCP tools with short descriptions. Search returns a free preview of 10 results plus a count, and bulk output goes to CSV or JSON exports rather than the chat (17 of 25). Structured filters for people and companies and export endpoints (16 of 20). No documented error catalogue (8 of 20). Asynchronous enrichment with polling or a signed webhook, identical inputs within 3 months return without a new charge, and the MCP guide asks for preview, balance check and confirmation before paid steps. No tool annotations confirmed (12 of 20). No official SDKs found (7 of 15). The checklist (https://www.anchorterminal.com/benchmark/#checklist-ergonomics): - 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). - 20, pagination, filtering and output-size controls. - 20, actionable, documented error responses, codes and messages an agent can recover from. - 20, idempotency or safe retries, and for MCP the `readOnlyHint` and `destructiveHint` annotations. - 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. ## 5. Schema & documentation, 72 out of 100, up to 4.6 more on the total Why it scored 72: OpenAPI file for v2 at docs.fullenrich.com/api/v2/reference/openapi.yaml, with a v1 file alongside (25). llms.txt with 35 links and Markdown twins (10). The MCP keeps tool descriptions short on purpose and moves workflow guidance into separate skills, so a client without skills gets less of it (12 of 20). Typed inputs, with helper tools that list valid industry, seniority and function codes (12 of 15). Test contacts that cost 0 credits and signed webhook examples. We found no error reference in the docs index (8 of 15). v1 and v2 paths. The public product changelog stops at 30 November 2024, and only the MCP package has a current CHANGELOG (5 of 15). The checklist (https://www.anchorterminal.com/benchmark/#checklist-schema): APIs and MCP servers. - 25, a machine-readable contract (a public OpenAPI file or similar; for MCP, typed JSON Schema inputs on every tool). - 10, llms.txt or Markdown docs served for agents. - 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. - 0 to 15, typed inputs with enums, constraints and required fields, and no free-form JSON blobs. - 0 to 15, examples and documented error responses. - 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. ## 6. Transparency & trust, 66 out of 100, up to 3 more on the total Made of editorial 50, provenance 82. Why it scored 66: Closed service with terms naming FullEnrich Corp. The skills and registry repo is MIT (15). The privacy policy (updated 20 August 2026) gives retention periods (3 years from last contact for prospects, 25 months for service improvement), legal bases and SCC or DPF transfers, and points rights requests to support@fullenrich.com. It doesn't say whether people returned by enrichment are covered, and the trust page says enrichment uses third-party providers it doesn't name. An opt-out page exists at fullenrich.com/optout (18 of 30). v1 and v2 APIs run side by side with no dated deprecation found (3 of 20). A sub-processor list is published. Hosting locations aren't stated on the trust page (14 of 20). The checklist (https://www.anchorterminal.com/benchmark/#checklist-transparency): - 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. - 0 to 30, data handling and retention statements that agree with each other (privacy policy, DPA, retention periods, subprocessors). - 0 to 20, a deprecation policy or notices with dates. - 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. Provenance checks not met in full (half of this category, computed from checked facts): - Domain age: fullenrich.com, registered 2023-04-08 (3 years) (7 of 15) - security.txt: not found (0 of 10) ## 7. Maintenance & community, 68 out of 100, up to 2.8 more on the total Why it scored 68: The MCP registry package 1.0.4 shipped on 2026-08-27, 35 days ago (20). Three dated releases in the last 90 days, 1.0.2 on 10 August, 1.0.3 on 11 August and 1.0.4 on 27 August, all packaging and registry changes (20). The public product changelog hasn't moved since November 2024. Support by email and help centre (6 of 15). Listed in the official MCP registry as io.github.FullEnrich/fullenrich, a GitHub-verified namespace (15). The skills repo has tests and a version-locked publish workflow (7 of 10). The checklist (https://www.anchorterminal.com/benchmark/#checklist-maintenance): - 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. - 20, at least three releases or dated changelog entries in the last 90 days. - 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. - 15, presence in the official MCP registry under a verified namespace (MCP servers), or current official SDKs (APIs and models). - 10, package health, current dependencies and CI. Models are read for deprecation notice periods and model churn rather than release counts. ## What we couldn't check What 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. - unchecked: status history before the last 30 days. The history page was refused three times by our fetch limit - The listing's lastRelease of 2026-09-01 didn't match anything we found. The newest dated release is MCP package 1.0.4 on 2026-08-27 - Which third-party providers sit in the waterfall, and whether the privacy policy covers people returned by enrichment - unchecked: whether MCP tools carry readOnlyHint or destructiveHint annotations ## Weaknesses - Enrichment sources are third-party providers the vendor doesn't name - Status page covers the web app only, not the API or MCP - No 429 or error reference found in the docs - Public product changelog stops at November 2024 - Webhooks signed with HMAC-SHA1 keyed with the API key itself ## What costs an agent a turn today The notes we give agents before they call it. Each one is a workaround an agent shouldn't need. - Send identical names, domains and LinkedIn URLs when re-running, or deduplication misses and you pay again - Expect 30 to 90 seconds a contact. Use the webhook or poll `get_enrichment_results` - Ask for mobiles only when needed. They cost 10 credits against 1 for a work email - Call `list_industries` and `list_seniorities` before filtering search - Use the 0-credit test contacts in the docs to check an integration ## What the review panel asked for - sell a pay-as-you-go pack - separate webhook secret - scoped API keys ## When it's done Send 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.