Enrich Layer API + MCP by Enrich Layer

# Fix list: Enrich Layer API + MCP

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/enrich-layer, the October 2026 research run, assessed 1 October 2026. Grade C, 56 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 Enrich Layer 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. Security & auth, 40 out of 100, up to 10.5 more on the total

Why it scored 40: One secret key per user, sent as a bearer token. We found no scopes or key rotation docs (15 of 30). The API only reads, and the MCP marks all 25 tools read-only (18 of 20). Profiles carry free text written by the people they describe, and we found no prompt-injection guidance (2 of 15). A free credit-balance endpoint and nothing more for per-call visibility (5 of 15). No security.txt, disclosure policy, bug bounty or certification. The privacy policy says SOC 2 is under consideration (0 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.

## 2. Payments & pricing, 40 out of 100, up to 7.5 more on the total

Why it scored 40: No x402, MPP or L402 (0). Pack prices ($10 for 100 credits to $1,000 for 46,297), annual plans and per-endpoint credit costs are public (20). 500 free credits at signup with no card, per the 30 September check (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.

## 3. Reliability, 65 out of 100, up to 7 more on the total

Why it scored 65: Cachet status page at status.enrichlayer.com with a component per API group (School, Company, People, Contact, Jobs, Search, Meta) (20). The only incident shown is a stickied notice from 24 November 2025 that the Person Profile endpoint answers in 30 to 100 seconds, and that component still showed 'Performance Issues' on 1 October 2026. No other history is readable (10). 300 requests a minute with bursts to 1,500 over 5 minutes, 2 a minute on trial accounts until the first top-up (15). 429 documented with advice to back off exponentially, no Retry-After (10 of 15). No SLA found (0). Generally available (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.

## 4. Maintenance & community, 26 out of 100, up to 6.5 more on the total

Why it scored 26: Newest npm release @enrichlayer/mcp-server 0.3.0 on 2026-06-19, over 90 days ago. Commits on 10 and 11 August 2026 haven't been released (10). No releases or dated changelog entries in the last 90 days (0). Four merged pull requests since March 2026 and no public changelog. We couldn't see issue replies from git (8 of 25). Not in the official MCP registry and no official SDKs found (0). CI runs build, tests and an OpenAPI conformance check, and dependencies are recent (8 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.

## 5. Agent ergonomics, 68 out of 100, up to 5.2 more on the total

Why it scored 68: 25 MCP tools, all compact, no toolsets. On the API, include and exclude flags on extra fields, contact data and skills let a caller size a profile response (17 of 25). `next_token` pagination on person and company search and filters (17 of 20). Errors are passed through as status plus message, with a 30-second timeout message from the MCP (10 of 20). Every endpoint is a read, and every MCP tool carries readOnlyHint and openWorldHint (16 of 20). Few required parameters, and the only official client we found is the MCP package (8 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.

## 6. Schema & documentation, 76 out of 100, up to 3.9 more on the total

Why it scored 76: OpenAPI 3.0 file at enrichlayer.com/docs/api/v2/openapi.yaml. The MCP repo vendors a 408 kB copy and its CI fails any tool that drifts from it (25). llms.txt per the 30 September check (10). MCP tool descriptions state what each returns, which identifier to pass and the credit cost, but not when to pick one tool over another (14 of 20). Zod schemas with enums for include and exclude flags and cache modes (13 of 15). Examples in the spec. Errors come back as status and message, and we found no error catalogue (9 of 15). /api/v2 paths, no public changelog, MCP versions 0.2.0 and 0.3.0 tagged (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.

## 7. Transparency & trust, 61 out of 100, up to 3.4 more on the total

Made of editorial 53, provenance 68.

Why it scored 61: The MCP server is MIT, the API is closed with terms naming Vertical Int, Inc. (Wyoming) (18 of 30). The privacy policy (updated 9 June 2025) covers people in its databases, relies on legitimate interests, names sources including professional networking platforms and data brokers, and takes deletion requests by email. Retention has no periods and no DPA is mentioned (15 of 30). A Proxycurl transition guide maps old paths to new, and no deprecation policy found (5 of 20). Subprocessors listed (Google, PostHog, Intercom, all US). The MCP's Sentry error reporting is off unless `SENTRY_DSN` is set and the README says so (15 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: enrichlayer.com, registered 2025-04-05 (1 year) (3 of 15)
- Changelog: not found (0 of 10)
- security.txt: 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.

- The listing's openapi field was null. The MCP README names enrichlayer.com/docs/api/v2/openapi.yaml as the source of truth, and we've patched it in
- Whether failed or empty lookups are charged
- Whether Enrich Layer runs a hosted MCP endpoint. The source mentions a deployed server but the README gives no public URL
- unchecked: whether keys can be rotated or scoped

## Weaknesses

- Person Profile endpoint flagged with performance issues since 24 November 2025, with 30 to 100 second responses
- Trial accounts limited to 2 requests a minute until the first top-up
- No security.txt, disclosure policy, bug bounty or certification
- No public changelog, and no MCP release since June 2026
- Privacy policy lists data brokers among sources and gives no retention periods

## 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.

- Top up once before testing. Trial keys run at 2 requests a minute
- Set the person profile timeout to at least 100 seconds
- Ask for `extra`, personal emails or phone numbers only when needed, since each adds credits
- Use `callback_url` on slow lookups such as work email instead of holding the connection
- Map old Proxycurl paths with the transition guide rather than guessing

## What the review panel asked for

- state whether failed or empty lookups bill
- key scopes and rotation
- a disclosure policy

## 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.