Coresignal API + MCP by Coresignal

# Fix list: Coresignal API + MCP

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/coresignal, the October 2026 research run, assessed 1 October 2026. Grade B, 63.1 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 Coresignal 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. Payments & pricing, 20 out of 100, up to 10 more on the total

Why it scored 20: No x402, MPP or L402 (0). Every plan price, credit allowance and per-endpoint credit cost is public, and only successful collect or enrich calls are charged (20). 7-day trial with 2,000 credits, card required per the 30 September check (0). 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.

## 2. Reliability, 55 out of 100, up to 9 more on the total

Why it scored 55: Better Stack status page at status.coresignal.com with components for the Data API (CDAPI), Real-Time API (RTAPI) and the dashboard (20). The history pages only reach back to 25 September, so we couldn't read 90 days. What's visible is an open RTAPI degradation, requests timing out because of an upstream source, running about six days on 1 October, and a two-hour maintenance of all services announced for 5 October (5). Rate limits published per plan, 5 to 100 or more requests a second (15). Per-API response-code pages exist, and we didn't find Retry-After or back-off guidance on the pages we read (5 of 15). No SLA found (0). The surfaces agents use are 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.

## 3. Security & auth, 58 out of 100, up to 7.4 more on the total

Why it scored 58: `apikey` header on REST. MCP v2 signs in with OAuth 2.1 through the dashboard and keeps the key server-side. We found no key scopes (22 of 30). Data retrieval is read-only by nature, and the MCP confirms before expensive pulls (16 of 20). Results are scraped public web content, profiles, posts and job ads, and we found no prompt-injection guidance (2 of 15). Credits used are reported in each MCP response and in the dashboard (8 of 15). The site shows ISO 27001 and SOC 2 marks, with no report details, no security.txt and no bug bounty found (10 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.

## 4. Agent ergonomics, 73 out of 100, up to 4.4 more on the total

Why it scored 73: The hosted MCP has 5 tools, and large results go to a file read back in pages with `artifact_read` rather than into the context (23 of 25). Search filters and pagination, with search itself free (18 of 20). 402 when credits run out and per-API response codes (14 of 20). The API is read-only apart from webhook subscriptions, credits are only taken on a 200, and MCP v2 pauses to confirm record count and credit cost before large pulls (12 of 20). No official SDKs found, and Elasticsearch DSL is heavy for a simple lookup (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.

## 5. 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 published terms, but the terms name Deeptrace Inc. (Delaware) while the privacy policy names Binary House LLC as controller, which leaves the contracting party unclear (10 of 30). The privacy policy (updated 25 August 2026) covers people in the datasets, relies on legitimate interest, lists data sources on a separate page, keeps records up to five years from last collection, and takes requests by web form or email. No DPA found in the policy (20 of 30). Release notes flag breaking changes with announcement dates, MCP v1 'will eventually be deprecated' with no date (10 of 20). Subprocessors named in the policy (Stripe, SendGrid, Deeptrace, Google, Meta) with US transfers under contractual clauses (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):

- security.txt: not found (0 of 10)

## 6. Schema & documentation, 86 out of 100, up to 2.3 more on the total

Why it scored 86: OpenAPI file at api.coresignal.com/cdapi/openapi.json, per the 30 September check (25). llms.txt index of 300+ pages (10). Endpoint pages and the MCP tool list state purpose and credit cost per call (15 of 20). Simple filters are typed, but the main search takes Elasticsearch DSL, a free-form JSON body (9 of 15). Response-code pages per API and request examples (12 of 15). v2 API paths and monthly release notes with dated entries and flagged breaking changes (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. Maintenance & community, 82 out of 100, up to 1.6 more on the total

Why it scored 82: Release notes have entries for October 2026 (30). Dozens of dated entries since July, including new Company Posts and Semantic Search endpoints (20). Public, detailed release notes, and we didn't test support (12 of 15). Listed in the official MCP registry as com.coresignal/mcp, a domain-verified namespace, per the 30 September check (15). No SDK packages to judge (5 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: Retry-After or back-off guidance on 429, since we didn't reach the rate-limit and response-code pages
- Which plan unlocks Contact Enrichment. The client-rendered pricing table was ambiguous between Pro and Premium
- Whether the August 2026 breaking changes to Agentic Search took effect on the announcement dates or later
- unchecked: whether the trial still needs a card. We relied on the 30 September check
- Status history before 25 September wasn't readable

## Weaknesses

- Real-Time API requests timing out for about six days up to 1 October, per the status page
- Main search takes Elasticsearch DSL, a free-form JSON body
- 7-day trial with a card per the 30 September check, and no free tier
- Terms name Deeptrace Inc. while the privacy policy names Binary House LLC
- Breaking changes in August 2026 to Agentic Search and Multi-source Jobs, announced in release notes with no stated notice period

## 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.

- Search for IDs first (free), then collect only the records you need
- Use base records at 10 credits when you don't need the 20-credit multi-source fields
- Use MCP v2 at /mcp/v2. The older /mcp endpoint will be deprecated
- Treat a 402 as out of credits, not a transient error
- Expect no work emails for EEA and UK people from the MCP email tool

## What the review panel asked for

- clarify which plan unlocks contact enrichment
- scoped REST keys
- injection guidance

## 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.