pipedrive-mcp-server

MCP.Pizza Chef: WillDent

The pipedrive-mcp-server is a Model Context Protocol server that connects to the Pipedrive API v2, providing read-only access to CRM data such as deals, persons, organizations, and pipelines. It exposes all standard and custom fields, enabling LLM applications like Claude to query and interact with Pipedrive data seamlessly. This server simplifies integration of Pipedrive CRM data into AI workflows by offering predefined prompts for common operations and easy setup with environment-based API token configuration.

Use This MCP server To

Expose Pipedrive CRM data to LLM applications for querying Retrieve deals, persons, organizations, and pipeline information Access custom fields in Pipedrive records via LLMs Integrate Pipedrive data into AI-driven sales and marketing workflows Enable LLMs to generate insights from CRM data without write access Use predefined prompts to simplify common Pipedrive data queries Connect Pipedrive CRM to Claude and other LLM clients

README

Pipedrive MCP Server

This is a Model Context Protocol (MCP) server that connects to the Pipedrive API v2. It allows you to expose Pipedrive data and functionality to LLM applications like Claude.

Features

  • Read-only access to Pipedrive data
  • Exposes deals, persons, organizations, and pipelines
  • Includes all fields including custom fields
  • Predefined prompts for common operations

Setup

  1. Clone this repository
  2. Install dependencies:
    npm install
    
  3. Create a .env file in the root directory with your Pipedrive API token:
    PIPEDRIVE_API_TOKEN=your_api_token_here
    
  4. Build the project:
    npm run build
    
  5. Start the server:
    npm start
    

Using with Claude

To use this server with Claude for Desktop:

  1. Configure Claude for Desktop by editing your claude_desktop_config.json:
{
  "mcpServers": {
    "pipedrive": {
      "command": "node",
      "args": ["/path/to/pipedrive-mcp-server/build/index.js"],
      "env": {
        "PIPEDRIVE_API_TOKEN": "your_api_token_here"
      }
    }
  }
}
  1. Restart Claude for Desktop
  2. In the Claude application, you should now see the Pipedrive tools available

Available Tools

  • get-deals: Get all deals from Pipedrive (including custom fields)
  • get-deal: Get a specific deal by ID (including custom fields)
  • search-deals: Search deals by term
  • get-persons: Get all persons from Pipedrive (including custom fields)
  • get-person: Get a specific person by ID (including custom fields)
  • search-persons: Search persons by term
  • get-organizations: Get all organizations from Pipedrive (including custom fields)
  • get-organization: Get a specific organization by ID (including custom fields)
  • search-organizations: Search organizations by term
  • get-pipelines: Get all pipelines from Pipedrive
  • get-pipeline: Get a specific pipeline by ID
  • get-stages: Get all stages from all pipelines
  • search-leads: Search leads by term
  • search-all: Search across all item types (deals, persons, organizations, etc.)

Available Prompts

  • list-all-deals: List all deals in Pipedrive
  • list-all-persons: List all persons in Pipedrive
  • list-all-pipelines: List all pipelines in Pipedrive
  • analyze-deals: Analyze deals by stage
  • analyze-contacts: Analyze contacts by organization
  • analyze-leads: Analyze leads by status
  • compare-pipelines: Compare different pipelines and their stages
  • find-high-value-deals: Find high-value deals

License

MIT

pipedrive-mcp-server FAQ

How do I configure the Pipedrive API token for this MCP server?
You create a .env file in the root directory with PIPEDRIVE_API_TOKEN=your_api_token_here to authenticate API requests.
Does this MCP server allow modifying Pipedrive data?
No, it provides read-only access to ensure data integrity and security.
Can I access custom fields in Pipedrive records through this server?
Yes, all fields including custom fields are exposed to the LLM client.
How do I start the pipedrive-mcp-server after setup?
After installing dependencies and building the project, run npm start to launch the server.
Is this MCP server compatible with multiple LLM providers?
Yes, it is designed to work with LLMs like Claude, OpenAI GPT, and Anthropic's Claude by exposing structured Pipedrive data.
Are there predefined prompts included?
Yes, the server includes predefined prompts for common Pipedrive operations to simplify usage.
How do I integrate this MCP server with Claude for Desktop?
Configure your claude_desktop_config.json to include the pipedrive MCP server command and arguments as specified in the documentation.