Pipedrive MCP Server
Enables AI assistants to analyze Pipedrive sales pipeline, deal velocity, and activity engagement, helping sales teams understand where deals are stalling.
README
Pipedrive MCP Server
A high-performance Model Context Protocol (MCP) server that enables Claude (and other MCP-compatible LLMs) to analyze your Pipedrive sales pipeline, deal velocity, and activity engagement.
This server is specifically designed to help sales teams understand why deals are stalling and where the "rubber isn't hitting the road" by providing deep visibility into deal stages, activities, and contact details.
🚀 Features
- Deep Deal Analysis: Retrieve full deal details enriched with contact person and organization metadata.
- Activity Tracking: Monitor user activities (calls, meetings, emails) to analyze engagement levels.
- Pipeline Visibility: Explore pipelines and stages to identify bottlenecks.
- Lead Management: Access the leads inbox for early-stage pipeline analysis.
- Dockerized: Easy deployment via Docker with zero-config on your host machine.
- Clean Protocol: Optimized for Claude Desktop with all logging redirected to
stderrto prevent protocol corruption.
🛠 Built With
- TypeScript: Type-safe implementation for reliable API interactions.
- MCP SDK: Built on the official
@modelcontextprotocol/sdk. - Pipedrive SDK: Uses the official
pipedriveNode.js library (v2 & v1). - Docker: Containerized for consistent performance across environments.
📋 Prerequisites
- Docker installed and running.
- A Pipedrive API Key.
📦 Installation & Setup
1. Build the Image
Clone this repository and build the Docker image:
docker build -t pipedrive-mcp-server .
2. Configure Claude Desktop
Add the Pipedrive MCP server to your Claude Desktop configuration.
File Location:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json
Configuration:
{
"mcpServers": {
"pipedrive": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"PIPEDRIVE_API_KEY=your_api_key_here",
"pipedrive-mcp-server"
]
}
}
}
Replace your_api_key_here with your actual Pipedrive API token.
🛠 Available Tools
get_deals: List deals with pipeline, stage, and status filters.get_deal_details: Get a specific deal with full enrichment of Person and Organization data.get_activities: List activities filtered by deal, user, or type.get_leads: Retrieve leads from the leads inbox.get_pipelines: List all configured pipelines.get_stages: List stages for a specific pipeline.get_users: List all users in your Pipedrive company.
🔍 Example Queries
Once connected, you can ask Claude:
- "Analyze the deals in the 'Negotiation' stage. Which ones haven't had any activity in the last 7 days?"
- "Who is the main contact person for the 'Big Enterprise' deal, and what was our last interaction?"
- "Show me all leads owned by [User] and summarize why they haven't moved to the deal pipeline yet."
- "Are we talking to the right ICP for our open deals in the 'Discovery' stage?"
📄 License
MIT License. See LICENSE for details.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.