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.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。