# Crustdata: MCP server status, API access gate and what it does > A real-time API for company and person firmographic/growth data (headcount trends, funding, tech stack, web... Official MCP, Free to start. Checked 2026-09-07. *Markdown twin of the HTML page at the same path. Same content, no navigation, no styling, no scripts. Links below point at other twins. Site map for machines: [llms.txt](../llms.txt). The whole dataset: [directory.json](../data/directory.json).* *Maintained by Andrew McGuire (https://andrewcmcguire.com), who also publishes https://gtmsignals.co and https://justsaid.ai.* --- [Directory](../index.md) / [Data & Enrichment](../categories/data-enrichment.md) / Crustdata # Crustdata [Official MCP](../mcp/official.md) [Free to start](../gates/free.md) [Data & Enrichment](../categories/data-enrichment.md) RESEARCHED Checked 2026-09-07 > **RESEARCHED** Facts from public sources with URLs. No usage claims. Nobody has run this tool. The other tier is BENCH-TESTED, which means Andrew personally ran the tool on a stated date and cannot be bought at any price. Across the whole directory that count is 1. Vendor: [crustdata.com](https://crustdata.com) · entry id 01-crustdata · source 01-data-enrichment.md line 445 **What it does** A real-time API for company and person firmographic/growth data (headcount trends, funding, tech stack, web traffic, social signals), positioned as infrastructure for time-sensitive GTM triggers and agent-built prospecting workflows. **AI features, separated from automation with an AI label on it** Markets itself as built "for AI agents" with Claude Code example workflows; the underlying capability is real-time data aggregation and API delivery, not a proprietary AI model - "AI-native" mostly describes agent-friendly API/MCP design, not novel enrichment intelligence. **RevOps role** Real-time firmographic/trigger-signal layer for outbound (funding events, headcount changes, tech-stack shifts), used alongside or as an alternative to Clay/PDL. **MCP server** - **Status bucket**: Official MCP - **Auth**: unknown - **Parsed URLs**: 2 found in the mcp_url field - **Endpoint probe**: docs page, not an endpoint - **Docs URL**: [https://crustdata.com/](https://crustdata.com/) - **Probed**: 2026-09-04, HTTP 200 The vendor ships and maintains the server itself. A wrapper built by Zapier, Composio or a similar third party does not count as official. The status was established by hand on 2026-09-07. On 2026-09-04 the recorded URL served a documentation page, not an MCP endpoint. That is where to read about the server, not where to connect to it. An agent needs the second. mcp_status, verbatim from the file: official mcp_url, verbatim from the file: https://install.crustdata.com/mcp ; https://crustdata.com/ (MCP referenced directly on the vendor homepage: "drop the whole graph into your agent with the MCP, in one line"; a dedicated MCP docs sub-page was not locatable under docs.crustdata.com) - [https://install.crustdata.com/mcp](https://install.crustdata.com/mcp) - [https://crustdata.com/](https://crustdata.com/) **What this server exposes** - **Tools named**: 3 - **Strongest evidence**: in the vendor docs - **Harvested**: 2026-09-27 - **Catalogue shape**: a fixed catalogue the vendor publishes A tool below is one the server NAMES. Nobody has called it. That is the same two tier honesty rule the rest of the directory runs on: a named tool is research, and BENCH-TESTED stays the only claim that anybody ran anything. - **execute** Calls Crustdata's data tools evidence: in the vendor docs · calling it reads - **get_schema** Retrieves schema information for a Crustdata data tool evidence: in the vendor docs · calling it reads - **list_tools** Lists the available Crustdata data tools evidence: in the vendor docs · calling it reads 141 of the 741 entries that record an official or community MCP server carry a harvested tool list. The other 600 are unmeasured, which is not the same as empty. Harvest last run 2026-09-27. Every name across every server is on the [tools index](../tools-index.md). **Command line** No CLI found by the 2026-09-27 harvest across vendor docs, npm, PyPI, Homebrew and GitHub. That is a probe result, not proof of absence. **Access gate** - **Gate bucket**: Free to start - **Can a solo operator reach it**: Yes, without talking to anyone api_gate, verbatim from the file: free (free sandbox key advertised on the vendor homepage, self-serve signup; paid usage is credit-based on purchased credits) **API documentation** No documentation URL recorded. 727 of 1252 entries are in the same position. Blank is legal and it is published as blank. **GitHub health** Not measured. github_url, github_stars, github_last_commit and github_archived are null on every entry in this build. The refresh rail specced in SPEC section 7.2 has not been run. An unstamped star count is a lie, so nothing is shown rather than something stale. **On GitHub** No GitHub organisation could be tied to crustdata.com with evidence on 2026-09-08. Recorded by the harvest: github candidates were seen but none passed the evidence rules. 1 candidate account seen and rejected by the evidence rules: crustdata. A name match alone is never accepted; the account has to point at the vendor domain. **Jobs it can do** - [Search people by criteria](../jobs/search-people-by-criteria.md) - [Search companies by firmographics](../jobs/search-companies-by-firmographics.md) - [Enrich a company from a domain](../jobs/enrich-company-from-domain.md) - [Find a person's LinkedIn URL from a name and company](../jobs/find-linkedin-url-from-name-and-company.md) - [Detect a company's tech stack](../jobs/detect-technographics.md) - [Detect a funding or news event](../jobs/detect-funding-or-news-event.md) A job tag means the vendor says the tool does this. It is not a test result, not proof the capability is reachable through the tool's MCP server, and not proof it is available on the gate this entry records. Tagged by machine-pass on 2026-08-25 against the closed 56 job vocabulary. 271 of 1,252 entries carry at least one tag; 849 tags are assigned in total. **Also listed in another category** This page is the canonical home. The listing below is the same product, counted separately in the source markdown. - **Listed as**: Crustdata - **Category**: [Signals & Intent](../categories/signals-intent-abm.md) - **MCP status there**: Official MCP - **Gate there**: Free to start - **Source**: 05-signals-intent-abm.md line 519 - **Canonical page**: [Crustdata](../tools/crustdata.md) What that listing says it does: Aggregates real-time company and people data (250+ data points per company from 15+ sources - funding, headcount, web signals, social, reviews) plus a "Watcher API" for near-real-time hiring/funding/event alerts, covering 60M companies and 1B+ people. 16 of the 1252 entries are cross listed like this. They are why the entry count is 1252 and the unique product count is 1236. The canonical home is declared in INDEX.md, not chosen by the parser. **Sources** - [https://crustdata.com/](https://crustdata.com/) - [https://docs.crustdata.com/general/pricing](https://docs.crustdata.com/general/pricing) - [https://crustdata.com/blog/b2b-prospecting-workflow-claude-code](https://crustdata.com/blog/b2b-prospecting-workflow-claude-code) - [https://docs.crustdata.com/person-docs/search/introduction](https://docs.crustdata.com/person-docs/search/introduction) - [https://install.crustdata.com/mcp](https://install.crustdata.com/mcp) 5 source URLs. Raw sources field, verbatim: https://crustdata.com/, https://docs.crustdata.com/general/pricing, https://crustdata.com/blog/b2b-prospecting-workflow-claude-code, https://docs.crustdata.com/person-docs/search/introduction, https://install.crustdata.com/mcp **Notes, verbatim from the file** MCP existence is confirmed on the vendor's own homepage, but the exact MCP-specific auth flow and a dedicated MCP docs URL could not be pinned down in this pass - mcp_auth and the precise api_gate are marked unknown rather than guessed. Web search/fetch and basic search+enrichment endpoints appear self-serve (free sandbox key referenced); live real-time Person and Company endpoints are explicitly plan-gated per docs.crustdata.com/general/pricing, with no full public price list and credits that expire after 6 months (up to 7 credits per enriched person profile). [api_gate 2026-08-25] Reclassified unknown -> free from the vendor's own page (https://crustdata.com/): free sandbox API key issued self-serve at signup, no credit card; paid usage is credit-based on top. 2026-09-03: vendor docs state the Person Search API (POST /person/search) accepts combined filters such as basic_profile.name and experience.employment_details.company_name and returns social_handles.professional_network_identifier.profile_url with a linkedin.com/in/ value, at "0.03 credits per result returned" (https://docs.crustdata.com/person-docs/search/introduction); no MCP tool name is stated there. [api_gate 2026-09-03] Re-checked against the live vendor pricing surfaces and held at free; the cross-listed 05-signals-intent-abm.md entry was reconciled paid -> free to match. Two corrections to the 2026-08-25 line above: the vendor homepage today says "Free sandbox key, full API, MCP server and skill templates" but does NOT say "no credit card", so that phrase is withdrawn as unsourced; and https://crustdata.com/pricing today shows no price list at all, only credit-based real-time API access with monthly/annual plans, flat-file data, and a contact-sales custom/enterprise tier. https://docs.crustdata.com/general/pricing confirms credits are "valid for 6 months from the purchase date", /person/search and /company/search at 0.03 credits per result, autocomplete and /company/identify free, "Web live endpoints are available on self-serve plans", and Company and Person live endpoints still plan-gated. Free-to-start with paid usage on top; no sales call to get a key, so not enterprise-only and not paid-only. 2026-09-07: Official MCP registry entry io.github.mhimed-crustdata/crustdata lists remote https://install.crustdata.com/mcp; that URL returned 401 to an MCP initialize POST. mhimed-crustdata is a Crustdata-affiliated account and the host is a crustdata.com subdomain. https://mcp.crustdata.com/mcp also answers 401 (https://install.crustdata.com/mcp). **Provenance** - **Entry id**: 01-crustdata - **Source file**: 01-data-enrichment.md - **Source line**: 445 - **Tier**: RESEARCHED - **last_checked**: 2026-09-07 - **Data baked**: 2026-09-27 Every field above is rendered from directory.json exactly as the build produced it. Nothing is summarised and nothing is dropped. The one change made at render time is typographic and it is disclosed on the [methodology page](../methodology.md).