A Model Context Protocol (MCP) server that connects to the Pipedrive API v2, exposing Pipedrive CRM data to LLM applications like Claude.

• Full CRUD operations (Create, Read, Update, Delete) for Pipedrive data
• Full entity support including:
  • Deals
  • Persons (Contacts)
  • Organizations
  • Pipelines & Stages
  • Activities
  • Notes
• Batch operations for creating, updating, and deleting multiple items at once
• Search capabilities across all entity types
• Custom fields support - All fields including custom fields are exposed
• Predefined prompts for common operations
• Token-optimized responses for efficient data transfer

• Node.js (v16 or higher)
• A Pipedrive account with API access
• Pipedrive API token

1. Clone the repository:

git clone https://github.com/yourusername/pipedrive-mcp-server.git
cd pipedrive-mcp-server

2. Install dependencies:

npm install

3. Create a .env file in the root directory:

cp .env.example .env

4. Add your Pipedrive API token to the .env file:

PIPEDRIVE_API_TOKEN=your_pipedrive_api_token_here

5. Build the project:

npm run build

1. Log in to your Pipedrive account
2. Go to Personal Settings → API
3. Copy your personal API token

Run the server with auto-reload for development:

npm run dev

Build and run the compiled server:

npm run build
npm start

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"
      }
    }
  }
}

Read Operations:

• get_deals - List deals with filtering options
• get_deal - Get a specific deal by ID
• search_deals - Search for deals by term

Write Operations:

• create_deal - Create a new deal
• update_deal - Update an existing deal
• delete_deal - Delete a deal
• batch_create_deals - Create multiple deals at once
• batch_update_deals - Update multiple deals at once
• batch_delete_deals - Delete multiple deals at once

Read Operations:

• get_persons - List persons with filtering options
• get_person - Get a specific person by ID
• search_persons - Search for persons by name

Write Operations:

• create_person - Create a new person
• update_person - Update an existing person
• delete_person - Delete a person
• batch_create_persons - Create multiple persons at once
• batch_update_persons - Update multiple persons at once
• batch_delete_persons - Delete multiple persons at once

Read Operations:

• get_organizations - List organizations
• get_organization - Get a specific organization by ID
• search_organizations - Search for organizations

Write Operations:

• create_organization - Create a new organization
• update_organization - Update an existing organization
• delete_organization - Delete an organization
• batch_create_organizations - Create multiple organizations at once
• batch_update_organizations - Update multiple organizations at once
• batch_delete_organizations - Delete multiple organizations at once

Read Operations:

• get_pipelines - List all pipelines
• get_pipeline - Get a specific pipeline
• get_stages - List pipeline stages
• get_stage - Get a specific stage

Write Operations:

• create_pipeline - Create a new pipeline
• update_pipeline - Update an existing pipeline
• delete_pipeline - Delete a pipeline
• create_stage - Create a new stage in a pipeline
• update_stage - Update an existing stage
• delete_stage - Delete a stage

Read Operations:

• get_activities - List activities with filtering
• get_activity - Get a specific activity

Write Operations:

• create_activity - Create a new activity
• update_activity - Update an existing activity
• delete_activity - Delete an activity
• mark_activity_done - Mark an activity as done (convenience method)
• batch_create_activities - Create multiple activities at once
• batch_update_activities - Update multiple activities at once
• batch_delete_activities - Delete multiple activities at once

Read Operations:

• get_notes - List notes with filtering
• get_note - Get a specific note

Write Operations:

• create_note - Create a new note
• update_note - Update an existing note
• delete_note - Delete a note
• batch_create_notes - Create multiple notes at once
• batch_update_notes - Update multiple notes at once
• batch_delete_notes - Delete multiple notes at once

• search_items - Search across multiple item types

• get_users - List all users
• get_user - Get a specific user by ID
• get_current_user - Get current authenticated user

• get_deals_summary - Get summarized deals list
• get_persons_summary - Get summarized persons list
• get_organizations_summary - Get summarized organizations list
• get_activities_summary - Get summarized activities list
• get_overview - Get dashboard overview
• search_summarized - Get summarized search results

• get_current_quarter_deals - Get deals for current quarter
• get_quarter_summary - Get summary for specific quarter
• get_quarterly_progress - Get current quarter progress

The server includes several predefined prompts for common operations:

• list_all_deals - List all deals with their details
• search_person - Search for a person by name
• get_organization_deals - Get all deals for a specific organization
• pipeline_overview - Get overview of all pipelines and their stages

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)

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

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

IMPORTANT: This server now supports write operations (create, update, delete) which can modify your Pipedrive data.

Security Best Practices:

• Use this server in a secure environment
• Be cautious when using delete operations - they cannot be undone
• Test write operations thoroughly before using in production
• Consider implementing additional validation layers if needed
• Review all AI-generated operations before execution in critical scenarios
• The server uses the API token's permissions - ensure the token has appropriate access levels

Batch Operations:

• Batch operations process multiple items in parallel
• Failed items in a batch are reported but don't stop other items from processing
• Always review batch operation results for any failures

The server provides detailed error messages including:

• API authentication failures
• Network errors
• Invalid parameters
• Rate limit exceeded warnings

Contributions are welcome! Please feel free to submit a Pull Request.

MIT License - see LICENSE file for details

For issues or questions:

• Create an issue on GitHub
• Check Pipedrive API documentation: https://developers.pipedrive.com/docs/api/v1

• Built for use with Claude Desktop
• Uses the Model Context Protocol
• Integrates with Pipedrive CRM