Access Crunchbase data for business information and insights. Requires a Crunchbase API key.
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, and people data from Crunchbase.
git clone https://github.com/Cyreslab-AI/crunchbase-mcp-server.git
cd crunchbase-mcp-server
npm install
npm run build
The server requires a Crunchbase API key to function. You can obtain an API key by signing up for the Crunchbase API.
Set the API key as an environment variable:
export CRUNCHBASE_API_KEY=your_api_key_here
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:
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": []
}
}
}
Start the server:
npm start
For development with automatic reloading:
npm run dev
The server exposes the following tools:
search_companies - Search for companies based on various criteria
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)get_company_details - Get detailed information about a specific company
name_or_id
(required): Company name or UUIDget_funding_rounds - Get funding rounds for a specific company
company_name_or_id
(required): Company name or UUIDlimit
(optional): Maximum number of results to return (default: 10)get_acquisitions - Get acquisitions made by or of a specific company
company_name_or_id
(optional): Company name or UUIDlimit
(optional): Maximum number of results to return (default: 10)search_people - Search for people based on various criteria
query
(optional): Search query (e.g., person name)company
(optional): Filter by company nametitle
(optional): Filter by job titlelimit
(optional): Maximum number of results to return (default: 10)The server also exposes the following resources:
Trending Companies - List of trending companies on Crunchbase
crunchbase://trending/companies
Company Details - Detailed information about a specific company
crunchbase://companies/{name}
Company Funding Rounds - Funding rounds for a specific company
crunchbase://companies/{name}/funding
Company Acquisitions - Acquisitions made by or of a specific company
crunchbase://companies/{name}/acquisitions
Here are some examples of how an AI assistant might use this MCP server:
{
"query": "AI",
"location": "San Francisco",
"limit": 5
}
{
"name_or_id": "OpenAI"
}
{
"company_name_or_id": "Anthropic"
}
{
"title": "CEO",
"limit": 10
}
MIT
For questions or support, please contact: contact@cyreslab.ai
A high-performance JavaScript server for the Alliance of Genome Resources (AGR) MCP.
An MCP server for interacting with Elasticsearch clusters, enabling LLM-powered applications to search, update, and manage data.
A runtime-configurable MCP server that turns a Supabase project into an AI-compatible tool interface.
Access and manage MariaDB or MySQL databases using an MCP server.
Search, Query and interact with data in your Milvus Vector Database.
Access Mina blockchain data, including events, actions, and network state, through the Mina Archive Node API.
A simple MCP server for MySQL, demonstrating fundamental MCP protocol concepts. Requires a MySQL database connection configured via environment variables.
A read-only MCP server for Pipedrive, enabling LLMs to query live data using the CData JDBC Driver.
Implement semantic memory layer on top of the Qdrant vector search engine
A read-only MCP server for querying live Snowflake data, powered by CData.