Pipedrive MCP Server
Connects the Pipedrive API v2 to LLM applications, providing read-only access to CRM data including deals, contacts, and pipelines. It enables users to search and retrieve organization information, activities, and notes through natural language.
README
Pipedrive MCP Server
A Model Context Protocol (MCP) server that connects to the Pipedrive API v2, exposing Pipedrive CRM data to LLM applications like Claude.
Features
- Read-only access to Pipedrive data
- Full entity support including:
- Deals
- Persons (Contacts)
- Organizations
- Pipelines & Stages
- Activities
- Notes
- Search capabilities across all entity types
- Custom fields support - All fields including custom fields are exposed
- Predefined prompts for common operations
Prerequisites
- Node.js (v16 or higher)
- A Pipedrive account with API access
- Pipedrive API token
Installation
- Clone the repository:
git clone https://github.com/yourusername/pipedrive-mcp-server.git
cd pipedrive-mcp-server
- Install dependencies:
npm install
- Create a
.envfile in the root directory:
cp .env.example .env
- Add your Pipedrive API token to the
.envfile:
PIPEDRIVE_API_TOKEN=your_pipedrive_api_token_here
- Build the project:
npm run build
Getting Your Pipedrive API Token
- Log in to your Pipedrive account
- Go to Personal Settings → API
- Copy your personal API token
Usage
Development Mode
Run the server with auto-reload for development:
npm run dev
Production Mode
Build and run the compiled server:
npm run build
npm start
Configuring with Claude Desktop
Add the following to your Claude Desktop configuration file:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"pipedrive": {
"command": "node",
"args": ["/path/to/pipedrive-mcp-server/dist/index.js"],
"env": {
"PIPEDRIVE_API_TOKEN": "your_pipedrive_api_token_here"
}
}
}
}
Available Tools
Deals
get_deals- List deals with filtering optionsget_deal- Get a specific deal by IDsearch_deals- Search for deals by term
Persons (Contacts)
get_persons- List persons with filtering optionsget_person- Get a specific person by IDsearch_persons- Search for persons by name
Organizations
get_organizations- List organizationsget_organization- Get a specific organization by IDsearch_organizations- Search for organizations
Pipelines & Stages
get_pipelines- List all pipelinesget_pipeline- Get a specific pipelineget_stages- List pipeline stagesget_stage- Get a specific stage
Activities
get_activities- List activities with filteringget_activity- Get a specific activity
Notes
get_notes- List notes with filteringget_note- Get a specific note
Search
search_items- Search across multiple item types
Predefined Prompts
The server includes several predefined prompts for common operations:
list_all_deals- List all deals with their detailssearch_person- Search for a person by nameget_organization_deals- Get all deals for a specific organizationpipeline_overview- Get overview of all pipelines and their stages
Development
Commands
npm run dev # Run with auto-reload for development
npm run build # Build TypeScript to JavaScript
npm run start # Run the compiled server
npm run lint # Run ESLint
npm run typecheck # Run TypeScript type checking
npm test # Run tests (when implemented)
Project Structure
pipedrive-mcp-server/
├── src/
│ ├── index.ts # Main MCP server entry point
│ ├── pipedrive-client.ts # Pipedrive API client
│ └── tools/ # Individual tool implementations
│ ├── deals.ts
│ ├── persons.ts
│ ├── organizations.ts
│ ├── pipelines.ts
│ ├── activities.ts
│ ├── notes.ts
│ └── search.ts
├── dist/ # Compiled JavaScript output
├── package.json
├── tsconfig.json
├── .eslintrc.json
└── .env.example
API Rate Limits
The Pipedrive API has rate limits. The server handles API responses appropriately, but be mindful of:
- Default rate limit: 80 requests per 2 seconds
- Consider implementing caching for frequently accessed data
- Use pagination parameters to limit data transfer
Error Handling
The server provides detailed error messages including:
- API authentication failures
- Network errors
- Invalid parameters
- Rate limit exceeded warnings
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
License
MIT License - see LICENSE file for details
Support
For issues or questions:
- Create an issue on GitHub
- Check Pipedrive API documentation: https://developers.pipedrive.com/docs/api/v1
Acknowledgments
- Built for use with Claude Desktop
- Uses the Model Context Protocol
- Integrates with Pipedrive CRM
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。