# Fix list: Dropcontact API + MCP From Anchor Terminal's listing at https://www.anchorterminal.com/tools/dropcontact, the October 2026 research run, assessed 1 October 2026. Grade D, 51.1 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 Dropcontact 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. Schema & documentation, 41 out of 100, up to 9.6 more on the total Why it scored 41: No OpenAPI or other machine-readable spec found (0). No llms.txt found (0). The single-page reference says what the enrich call needs, a name plus a company identifier, and what comes back (14 of 20). Documented input fields, and since June 2026 unknown fields get a 400 on new accounts (10 of 15). Request and response examples, HTTP codes and per-contact error and warning codes such as `only_contact_data` and `unexpected_field` (12 of 15). /v1 in the path and no public 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. ## 2. Reliability, 57 out of 100, up to 8.6 more on the total Why it scored 57: Atlassian Statuspage at status.dropcontact.com with a separate Dropcontact API component (20). The front page shows no incidents from 17 September to 1 October. The history page renders client-side and we couldn't read July or August, so this is two clean weeks, not 90 days (10). 60 requests a second, 250 contacts a request and 15 kB a contact (15). 429 is documented without Retry-After. Results not ready return 'try again in 30 seconds', and the docs warn that webhooks can arrive out of order or twice (7 of 15). No SLA found (0). The REST API is generally available, while the vendor calls remote MCP connections 'still early' (5 of 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. ## 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). Plan prices and credit allowances are public in euros, and a credit is one verified email found (refunded when none is) or one email checked, so the unit price is clear (20). 50 free credits at signup with no card (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. Security & auth, 59 out of 100, up to 7.2 more on the total Why it scored 59: One API key per account in the `X-Access-Token` header, no scopes found. OAuth or the key as a bearer token on the MCP (20 of 30). Enrichment and verification are read-only. The only writes are webhook settings (14 of 20). Results are cleaned names, titles and company fields rather than free text, so little untrusted content comes back (8 of 15). An empty request returns the credit balance. We found no per-call log for operators (5 of 15). security.txt points to a HackerOne programme, valid until 2027-04-09 per the 30 September check. No SOC 2 or ISO 27001 found (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. ## 5. Maintenance & community, 18 out of 100, up to 7.2 more on the total Why it scored 18: No changelog. The newest dated API change we found is the June 2026 switch to 400 errors for unknown fields, between 90 and 180 days ago (10). No dated release entries in the last 90 days (0). Email support on every plan and no public changelog (5 of 15). Not in the official MCP registry and no official SDKs (0). No packages to judge (3 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. ## 6. Agent ergonomics, 60 out of 100, up to 6.5 more on the total Why it scored 60: The MCP has a handful of tools (enrich by name and company or by LinkedIn URL, validate an email), and REST takes up to 250 contacts a call. No field selection (20 of 25). No search, so little to page or filter. `forceResults=true` returns partial results early (10 of 20). Per-contact error and warning codes an agent can fix, such as adding a company to clear `only_contact_data` (16 of 20). Asynchronous jobs keyed by `request_id`, pay on success, but no idempotency key and duplicate webhooks are possible (8 of 20). Few required fields, no official SDKs found (6 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. ## 7. Transparency & trust, 73 out of 100, up to 2.4 more on the total Made of editorial 55, provenance 90. Why it scored 73: Closed service with terms naming Dropcontact SAS, registered in Bobigny, no. 823 752 647 (15). The personal data charter (updated 5 August 2025) says Dropcontact is a processor when enriching for a customer, keeps prospect data 3 years plus 4 in intermediate storage, takes rights requests at data@dropcontact.io, and a DPA is published. The pricing page says enrichment runs on its own algorithms on EU servers, while the charter says data is collected from public sources and some subcontractors are in the US under SCCs (22 of 30). One dated change notice (June 2026) and no deprecation policy (8 of 20). EU hosting and US subcontractors stated, no named subprocessor list found (10 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): - Changelog: not found (0 of 10) ## 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. - Incident history before 17 September 2026, since the history page renders client-side - Whether Dropcontact keeps its own database of enriched people or only processes for each customer. The charter describes a processor role and the pricing page says no third-party providers - unchecked: the MCP server's exact tool list and annotations - No named subprocessor list found ## Weaknesses - No OpenAPI spec, llms.txt or changelog - No prospect search, so it only enriches people you already have - Asynchronous only, with webhooks that can arrive out of order or twice - One unscoped API key per account - Remote MCP labelled early by the vendor and not in the official registry ## 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 a company name or website with every contact, or you get `only_contact_data` - Send only documented fields. New accounts get a 400 for unknown ones - Match webhook results by `request_id`, since order isn't guaranteed and duplicates happen - Poll no faster than every 30 seconds, as the not-ready response asks - Post an empty contact to read the credit balance at no cost ## What the review panel asked for - list prices in dollars as well - price verification below a found email - scoped API keys - per-call usage log ## 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.