1. Conduid
  2. AI
  3. pipedrive-server
MCP server · AI

pipedrive-server

Model Context Protocol server for Pipedrive API integration

Unclaimed ai
39Low

Scored 3 months ago · breakdown

About pipedrive-server

pipedrive-server is an MCP server published by git+WillDent in the AI category: model Context Protocol server for Pipedrive API integration. It has been installed 0 times through Conduid.

Install

Install
npx pipedrive-mcp-server
Claude Code
claude mcp add pipedrive-mcp-server-gitwilld -- npx -y pipedrive-mcp-server
npx
npx -y pipedrive-mcp-server

This server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.

Ask AI

Ask AI about pipedrive-server

Powered by Claude · Grounded in docs

I know everything about pipedrive-server. Ask me about installation, configuration, usage, or troubleshooting.

Security checks

  • ·README presentNot checked yet.
  • ·License declaredNot checked yet.
  • ·Tests presentNot checked yet.
  • ·Dependencies pinnedNot checked yet.
  • ·No dynamic code executionNot checked yet.
  • !Scoped permissionsDoesn't declare a permission scope. Assume it can do anything its process can.

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
  • Docker support with multi-stage builds
  • JWT authentication support
  • Built-in rate limiting for API requests
  • Advanced deal filtering (by owner, status, date range, value, etc.)

Setup

Standard Setup

  1. Clone this repository
  2. Install dependencies:
    npm install
    
  3. Create a .env file in the root directory with your configuration:
    PIPEDRIVE_API_TOKEN=your_api_token_here
    PIPEDRIVE_DOMAIN=your-company.pipedrive.com
    
  4. Build the project:
    npm run build
    
  5. Start the server:
    npm start
    

Docker Setup

Option 1: Using Docker Compose (standalone)

  1. Copy .env.example to .env and configure your settings:
    PIPEDRIVE_API_TOKEN=your_api_token_here
    PIPEDRIVE_DOMAIN=your-company.pipedrive.com
    MCP_TRANSPORT=sse  # Use SSE transport for Docker
    MCP_PORT=3000
    
  2. Build and run with Docker Compose:
    docker-compose up -d
    
  3. The server will be available at http://localhost:3000
    • SSE endpoint: http://localhost:3000/sse
    • Health check: http://localhost:3000/health

Option 2: Using Pre-built Docker Image

Pull and run the pre-built image from GitHub Container Registry:

For SSE transport (HTTP access):

docker run -d \
  -p 3000:3000 \
  -e PIPEDRIVE_API_TOKEN=your_api_token_here \
  -e PIPEDRIVE_DOMAIN=your-company.pipedrive.com \
  -e MCP_TRANSPORT=sse \
  -e MCP_PORT=3000 \
  ghcr.io/juhokoskela/pipedrive-mcp-server:main

For stdio transport (local use):

docker run -i \
  -e PIPEDRIVE_API_TOKEN=your_api_token_here \
  -e PIPEDRIVE_DOMAIN=your-company.pipedrive.com \
  ghcr.io/juhokoskela/pipedrive-mcp-server:main

Option 3: Integrating into Existing Project

Add the MCP server to your existing application's docker-compose.yml:

services:
  # Your existing services...

  pipedrive-mcp-server:
    image: ghcr.io/juhokoskela/pipedrive-mcp-server:main
    container_name: pipedrive-mcp-server
    restart: unless-stopped
    ports:
      - "3000:3000"
    environment:
      - PIPEDRIVE_API_TOKEN=${PIPEDRIVE_API_TOKEN}
      - PIPEDRIVE_DOMAIN=${PIPEDRIVE_DOMAIN}
      - MCP_TRANSPORT=sse
      - MCP_PORT=3000
      - PIPEDRIVE_RATE_LIMIT_MIN_TIME_MS=${PIPEDRIVE_RATE_LIMIT_MIN_TIME_MS:-250}
      - PIPEDRIVE_RATE_LIMIT_MAX_CONCURRENT=${PIPEDRIVE_RATE_LIMIT_MAX_CONCURRENT:-2}
    healthcheck:
      test: ["CMD", "wget", "--no-verbose", "--tries=1", "--spider", "http://localhost:3000/health", "||", "exit", "1"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 10s
    logging:
      driver: "json-file"
      options:
        max-size: "10m"
        max-file: "3"

Then add the required environment variables to your .env file.

Environment Variables

Required:

  • PIPEDRIVE_API_TOKEN - Your Pipedrive API token
  • PIPEDRIVE_DOMAIN - Your Pipedrive domain (e.g., your-company.pipedrive.com)

Optional (JWT Authentication):

  • MCP_JWT_SECRET - JWT secret for authentication
  • MCP_JWT_TOKEN - JWT token for authentication
  • MCP_JWT_ALGORITHM - JWT algorithm (default: HS256)
  • MCP_JWT_AUDIENCE - JWT audience
  • MCP_JWT_ISSUER - JWT issuer

When JWT authentication is enabled, all SSE requests (/sse and the message endpoint) must include an Authorization: Bearer <token> header signed with the configured secret.

Optional (Rate Limiting):

  • PIPEDRIVE_RATE_LIMIT_MIN_TIME_MS - Minimum time between requests in milliseconds (default: 250)
  • PIPEDRIVE_RATE_LIMIT_MAX_CONCURRENT - Maximum concurrent requests (default: 2)

Optional (Transport Configuration):

  • MCP_TRANSPORT - Transport type: stdio (default, for local use) or sse (for Docker/HTTP access)
  • MCP_PORT - Port for SSE transport (default: 3000, only used when MCP_TRANSPORT=sse)
  • MCP_ENDPOINT - Message endpoint path for SSE (default: /message, only used when MCP_TRANSPORT=sse)

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",
        "PIPEDRIVE_DOMAIN": "your-company.pipedrive.com"
      }
    }
  }
}
  1. Restart Claude for Desktop
  2. In the Claude application, you should now see the Pipedrive tools available

Available Tools

  • get-users: Get all users/owners from Pipedrive to identify owner IDs for filtering
  • get-deals: Get deals with flexible filtering options (search by title, date range, owner, stage, status, value range, etc.)
  • get-deal: Get a specific deal by ID (including custom fields)
  • get-deal-notes: Get detailed notes and custom booking details for a specific deal
  • 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

README mirrored from the source repository 3 months ago. The original is authoritative.

Questions

About pipedrive-server

How do I install pipedrive-server?

Run npx pipedrive-mcp-server, then add the server to your MCP client's configuration. Conduid has recorded 0 installs, so the command is known to work with current clients.

Is pipedrive-server safe to use with an AI agent?

Its trust score is 39 out of 100 (low). It passes 0 of 1 static security checks; the failures are listed above. It has no ConduID identity yet, so agent calls to it are not receipted.

Is pipedrive-server still maintained?

Conduid hasn't recorded a commit date for this repository yet. Check the repository directly for recent activity.