Skip to main content
Glama
Crunchbase MCP Server

Crunchbase MCP Server

Crunchbase MCP Server

A Model Context Protocol (MCP) server that provides access to Crunchbase data for AI assistants. This server allows AI assistants to search for companies, get company details, funding information, acquisitions, investor/investment data, and people data from Crunchbase.

Features

  • Search for companies based on various criteria

  • Get detailed information about specific companies (by name, UUID, or permalink)

  • Retrieve funding rounds for companies

  • Get acquisition data

  • Search for people associated with companies

  • Get a person's full profile, including job and education history

  • Get an investor's profile and investment portfolio ("what has investor Y backed")

  • Search individual investment records ("who invested in X")

Related MCP server: Coin MCP Server

Prerequisites

  • Node.js (v16 or higher)

  • A Crunchbase API key

Installation

  1. Clone the repository:

git clone https://github.com/Cyreslab-AI/crunchbase-mcp-server.git
cd crunchbase-mcp-server
  1. Install dependencies:

npm install
  1. Build the project:

npm run build

Configuration

The server requires a Crunchbase API key to function. You can obtain an API key by signing up for the Crunchbase API.

Setting up the API Key

Set the API key as an environment variable:

export CRUNCHBASE_API_KEY=your_api_key_here

MCP Configuration

You can use the included setup script to automatically configure the MCP server:

# Build the project first
npm run build

# Run the setup script
npm run setup

The setup script will:

  1. Ask for your Crunchbase API key

  2. Find your MCP settings file (or create a new one)

  3. Add the Crunchbase MCP server to your settings

Alternatively, you can manually add it to your MCP configuration file:

{
  "mcpServers": {
    "crunchbase": {
      "command": "node",
      "args": ["/path/to/crunchbase-mcp-server/build/index.js"],
      "env": {
        "CRUNCHBASE_API_KEY": "your_api_key_here"
      },
      "disabled": false,
      "autoApprove": []
    }
  }
}

Usage

Running the Server

Start the server:

npm start

For development with automatic reloading:

npm run dev

Available Tools

The server exposes the following tools:

  1. search_companies - Search for companies based on various criteria

    • Parameters:

      • query (optional): Search query (e.g., company name, description)

      • location (optional): Filter by location (e.g., "San Francisco", "New York")

      • category (optional): Filter by category (e.g., "Artificial Intelligence", "Fintech")

      • founded_after (optional): Filter by founding date (YYYY-MM-DD)

      • founded_before (optional): Filter by founding date (YYYY-MM-DD)

      • status (optional): Filter by company status (e.g., "active", "closed")

      • limit (optional): Maximum number of results to return (default: 10)

  2. get_company_details - Get detailed information about a specific company

    • Parameters (provide at least one; uuid/permalink take priority over name_or_id):

      • name_or_id (optional): Company name to search for. This resolves ambiguously - it's a name search that takes the first result, which can pick the wrong company for common names (e.g. "Meta"). Prefer uuid or permalink when you know them.

      • uuid (optional): Exact Crunchbase UUID of the company.

      • permalink (optional): Exact Crunchbase permalink of the company (e.g. "openai").

  3. get_funding_rounds - Get funding rounds for a specific company

    • Parameters (provide at least one identifier):

      • company_name_or_id (optional): Company name to search for (ambiguous, see above).

      • uuid / permalink (optional): Exact identifiers for the company. Preferred - also skips an extra lookup call.

      • limit (optional): Maximum number of results to return (default: 10)

  4. get_acquisitions - Get acquisitions made by or of a specific company (or recent acquisitions generally, if no company is given)

    • Parameters:

      • company_name_or_id (optional): Company name to search for (ambiguous, see above).

      • uuid / permalink (optional): Exact identifiers for the company. Preferred.

      • limit (optional): Maximum number of results to return (default: 10)

  5. search_people - Search for people based on various criteria

    • Parameters:

      • query (optional): Search query (e.g., person name)

      • company (optional): Filter by company name

      • title (optional): Filter by job title

      • limit (optional): Maximum number of results to return (default: 10)

  6. get_person_details - Get a person's full profile: bio fields (description, born_on, aliases, etc.) plus their job history (past and current roles) and education. Complements search_people, which only returns a person's current featured role.

    • Parameters (provide at least one identifier):

      • name (optional): Person name to search for (ambiguous - first result wins).

      • uuid / permalink (optional): Exact identifiers for the person. Preferred.

  7. get_investor_details - Get an investor's profile (an organization such as a VC firm or corporate investor) plus the investments it has participated in - answers "what has investor Y backed".

    • Parameters (provide at least one identifier):

      • name (optional): Investor name to search for (ambiguous - first result wins).

      • uuid / permalink (optional): Exact identifiers for the investor organization. Preferred (e.g. permalink "sequoia-capital").

      • limit (optional): Maximum number of portfolio investments to return (default: 10)

  8. search_investments - Search individual investment records (one investor participating in one funding round). Filter by organization to answer "who invested in X", or by investor to answer "what has investor Y backed".

    • Parameters:

      • organization_uuid / organization_permalink (optional): The company that received the investment.

      • investor_uuid / investor_permalink (optional): The investor that made the investment.

      • funding_round_uuid (optional): A specific funding round to list investments for.

      • limit (optional): Maximum number of results to return (default: 10)

      • after_id (optional): Pagination cursor - pass the uuid of the last result from a previous call to get the next page.

Available Resources

The server also exposes the following resources:

  1. Trending Companies - List of trending companies on Crunchbase

    • URI: crunchbase://trending/companies

  2. Company Details - Detailed information about a specific company (resolved by name search)

    • URI Template: crunchbase://companies/{name}

  3. Company Funding Rounds - Funding rounds for a specific company

    • URI Template: crunchbase://companies/{name}/funding

  4. Company Acquisitions - Acquisitions made by or of a specific company

    • URI Template: crunchbase://companies/{name}/acquisitions

  5. Organization Details (by permalink) - Detailed information about a specific organization, looked up directly by its exact Crunchbase permalink (skips the ambiguous name-search-then-resolve step used by crunchbase://companies/{name}).

    • URI Template: crunchbase://organization/{permalink}

    • The {permalink} argument supports completion: an MCP client that calls completion/complete for this template gets live suggestions from Crunchbase's own /autocompletes endpoint (e.g. typing "open" can suggest "openai").

Example Queries

Here are some examples of how an AI assistant might use this MCP server:

  1. Search for AI companies in San Francisco:

{
  "query": "AI",
  "location": "San Francisco",
  "limit": 5
}
  1. Get details for a specific company:

{
  "name_or_id": "OpenAI"
}
  1. Get funding rounds for a company:

{
  "company_name_or_id": "Anthropic"
}
  1. Search for CEOs at tech companies:

{
  "title": "CEO",
  "limit": 10
}
  1. Get an investor's profile and portfolio (get_investor_details):

{
  "permalink": "sequoia-capital",
  "limit": 10
}
  1. Find who invested in a company (search_investments):

{
  "organization_permalink": "openai"
}
  1. Get a person's full bio and job history (get_person_details):

{
  "permalink": "sam-altman"
}

License

MIT

Contact

For questions or support, please contact: contact@cyreslab.ai

Available Tools

5 tools
get_acquisitionsC

Get acquisitions made by or of a specific company

Inputs: company_name_or_id, limit.

get_company_detailsC

Get detailed information about a specific company

Inputs: name_or_id (required).

get_funding_roundsC

Get funding rounds for a specific company

Inputs: company_name_or_id (required), limit.

search_companiesC

Search for companies based on various criteria

Inputs: category, founded_after, founded_before, limit, +3 more.

search_peopleC

Search for people based on various criteria

Inputs: company, limit, query, title.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    B3.2/5.0

    Scored across 5 tools

    Disambiguation5/5

    Each tool has a clearly distinct purpose: get_acquisitions, get_company_details, and get_funding_rounds target specific data types for a company, while search_companies and search_people handle broader searches. There is no overlap in functionality, making tool selection straightforward for an agent.

    Naming Consistency5/5

    All tools follow a consistent verb_noun pattern with snake_case, using 'get_' for retrieval operations and 'search_' for broader queries. This uniformity enhances readability and predictability across the tool set.

    Tool Count4/5

    With 5 tools, the server is well-scoped for a Crunchbase domain, covering key data retrieval and search functions. It is slightly lean but reasonable, as it includes core operations without unnecessary bloat, though additional tools like updates or deletions might be expected in a broader context.

    Completeness4/5

    The tools provide solid coverage for querying company and people data, including details, acquisitions, funding rounds, and searches. Minor gaps exist, such as lack of update/delete operations or tools for related entities like investors, but the core retrieval and search needs are well-met for the domain.

    Maintenance

    ActivityStale
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      C
      maintenance
      An MCP (Model Context Protocol) server that provides Google search capabilities and webpage content analysis tools. This server enables AI models to perform Google searches and analyze webpage content programmatically.
      14 npm
      261
      ISC
    • F
      license
      Not graded
      quality
      D
      maintenance
      A Model Context Protocol server that provides AI models with structured access to external data and services, acting as a bridge between AI assistants and applications, databases, and APIs in a standardized, secure way.
      2
      -