MCP Server - Crustdata Docs

The Crustdata MCP server gives AI assistants direct access to 800M+ professional profiles and 200M+ companies. Connect it to Claude.ai, Claude Code, Cursor, or any MCP-compatible client and search, enrich, and analyze B2B data through natural language.

New — this is our latest MCP server, and we’d love for you to try it.

Ask in plain English. No query language, no endpoints to learn — just describe what you want.
Complex asks, one step. A request like “find AI startups hiring engineers, then get me the founders’ emails” runs start to finish in a single step.
Know the cost, instantly. Every request reports the exact credits it spent, in real time — no surprises.
Connect in seconds. Sign in with your Crustdata account — there’s no API key to copy or paste.

Quick start

Add the MCP connector

In Claude, open Customize → Connectors → Add custom connector.

Configure the connection

Name: Crustdata
URL: https://install.crustdata.com/mcp

Click Add to save.

Connect and authenticate

Open the new connector under Not connected and click Connect, then sign in with your Crustdata account. There’s no API key to copy or paste — signing in authorizes the connection.No account yet? Sign up at crustdata.co.

Start using it

Try one of the example prompts below.

Example prompts

Once connected, you can ask Claude questions like:

Prompt	What it does
”Find software engineering jobs at Anthropic”	Searches the job database with filters
”What jobs does Stripe have open right now?”	Fetches live job listings in real-time
”Find the profile for jane.doe@acme.com”	Reverse lookup by business email
”Show me AI startups with 100-500 employees”	Searches the company database with a headcount filter
”Who are the engineering leaders at Anthropic?”	Searches people by seniority and company
”Get me the email for this person’s profile”	Enriches a person profile with contact info
”Compare job openings at Anthropic, OpenAI, and Cohere”	Batch job search across multiple companies
”What is Anthropic posting about on social media?”	Fetches recent social media posts
”How many credits do I have?”	Checks your account balance

What you can do

Companies

Find and enrich companies by industry, headcount, location, funding, and more — with full firmographic profiles.

People & contacts

Search people by title, seniority, company, and skills, then enrich profiles with business emails, personal emails, and phone numbers.

Jobs

Search millions of job listings with filters and breakdowns, or pull a company’s live openings on demand.

Social & web

Track recent social posts by person, company, or keyword, and search and read content from across the web.

Credit costs vary by request and plan. See Pricing for per-request credit costs and Rate limits for limits.

Cost transparency

Every request reports the exact credits it spent, in real time — measured from what the request actually did, never estimated. Enrichment always takes the cheapest correct path, so you never over-spend by accident. Sign in with your Crustdata account when you connect — there’s no API key to copy or paste. Your key is never stored, and you can disconnect any time from your MCP client.

Programmatic access

You can use the same server from your own code — agent frameworks, backend jobs, or anywhere the sign-in flow isn’t practical. Connect any MCP client to the endpoint and pass your Crustdata API key as a bearer token:

Endpoint: https://install.crustdata.com/mcp
Header: Authorization: Bearer YOUR_API_KEY

For MCP clients that take a JSON config with custom headers:

{
  "mcpServers": {
    "crustdata": {
      "type": "streamable-http",
      "url": "https://install.crustdata.com/mcp",
      "headers": { "Authorization": "Bearer YOUR_API_KEY" }
    }
  }
}

Catalog resources

The server publishes its own usage guide as MCP resources — markdown pages an agent can read directly instead of re-deriving the tool list and schemas each session. Read crustdata://catalog first; it carries the must-know rules and an index of the sections:

Resource	What’s in it
`crustdata://catalog`	Start here — the must-know rules and an index of the sections below
`crustdata://catalog/quickstart`	How to drive the server: writing a script that composes tool calls
`crustdata://catalog/tools`	Every callable tool with its one-line purpose and cost
`crustdata://catalog/query-builder`	Filters, operators, and matching behavior
`crustdata://catalog/results`	Shaping results: `project`, `compact`, `paginate`, `parallelMap`
`crustdata://catalog/fields`	Common filter columns and identifiers per tool
`crustdata://catalog/patterns`	Recipes: search → enrich, identify → enrich, bulk, pagination
`crustdata://catalog/ranking`	Bounding result pages server-side and ranking in code
`crustdata://catalog/cost`	Credit pricing and the cheapest-path rules
`crustdata://catalog/full`	The entire guide in one read

Any MCP client can fetch these with a standard resource read — session.read_resource("crustdata://catalog") in the Python SDK, or client.readResource({ uri: "crustdata://catalog" }) in TypeScript.

Common workflows

Research a company — identify the company, enrich it with the fields you care about, and check its recent social activity. Find decision-makers — search people by company, seniority, and title, then enrich for contact info. Hiring analysis — search jobs by company, title, and location, and break the results down by category or location. Competitive intelligence — compare openings across competitors and track their social activity.

Support

For help or feedback, contact support@crustdata.co.

​Quick start

​Example prompts

​What you can do

Companies

People & contacts

Jobs

Social & web

​Cost transparency

​Sign-in

​Programmatic access

​Catalog resources

​Common workflows

​Support

Quick start

Example prompts

What you can do

Cost transparency

Sign-in

Programmatic access

Catalog resources

Common workflows

Support