Pipedrive MCP Server
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Pipedrive MCP Server Show me all active deals in the 'Proposal' stage"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
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
Related MCP server: Pipedrive MCP Server
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-serverInstall dependencies:
npm installCreate a
.envfile in the root directory:
cp .env.example .envAdd your Pipedrive API token to the
.envfile:
PIPEDRIVE_API_TOKEN=your_pipedrive_api_token_hereBuild the project:
npm run buildGetting 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 devProduction Mode
Build and run the compiled server:
npm run build
npm startConfiguring 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.exampleAPI 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
Available Tools
30 toolsget_activitiesC
Get a list of activities from Pipedrive
Inputs: start, limit, user_id, filter_id, +2 more.
get_activities_summaryA
Get a summarized list of activities (optimized for token usage) - shows essential fields only
Inputs: start, limit, user_id, done.
get_activityC
Get a specific activity by ID
Inputs: id (required).
get_current_quarter_dealsA
Get deals for the current quarter with date context (automatically uses correct quarter based on today's date)
Inputs: status, user_id, limit.
get_current_userB
Get details of the current authenticated user
Inputs: no named parameters.
get_dealC
Get a specific deal by ID
Inputs: id (required).
get_dealsC
Get a list of deals from Pipedrive
Inputs: start, limit, status, filter_id, +3 more.
get_deals_summaryA
Get a summarized list of deals (optimized for token usage) - shows essential fields only
Inputs: start, limit, status, user_id.
get_noteB
Get a specific note by ID
Inputs: id (required).
get_notesC
Get a list of notes from Pipedrive
Inputs: start, limit, user_id, deal_id, +5 more.
get_organizationC
Get a specific organization by ID
Inputs: id (required).
get_organizationsC
Get a list of organizations from Pipedrive
Inputs: start, limit, user_id, filter_id, +1 more.
get_organizations_summaryB
Get a summarized list of organizations (optimized for token usage) - shows essential fields only
Inputs: start, limit, user_id.
get_overviewA
Get a high-level overview with key metrics and recent items (very token-efficient)
Inputs: include_recent_deals, include_recent_activities, user_id.
get_personC
Get a specific person by ID
Inputs: id (required).
get_personsC
Get a list of persons from Pipedrive
Inputs: start, limit, user_id, filter_id, +1 more.
get_persons_summaryA
Get a summarized list of persons (optimized for token usage) - shows essential fields only
Inputs: start, limit, user_id.
get_pipelineC
Get a specific pipeline by ID
Inputs: id (required).
get_pipelinesC
Get all pipelines
Inputs: no named parameters.
get_quarterly_progressC
Get progress tracking for current quarter with forecasting data and date awareness
Inputs: user_id, include_forecast.
get_quarter_summaryC
Get comprehensive quarterly summary with key metrics and current quarter context
Inputs: quarter, year, user_id.
get_stageB
Get a specific stage by ID
Inputs: id (required).
get_stagesC
Get pipeline stages
Inputs: pipeline_id.
get_userB
Get details of a specific user by ID
Inputs: id (required).
get_usersC
Get all users (salespersons) from Pipedrive
Inputs: start, limit.
search_dealsC
Search for deals
Inputs: term (required), fields, exact_match, person_id, +3 more.
search_itemsC
Search across multiple item types in Pipedrive
Inputs: term (required), item_types, fields, search_for_related_items, +4 more.
search_organizationsC
Search for organizations
Inputs: term (required), fields, exact_match, start, +1 more.
search_personsC
Search for persons
Inputs: term (required), fields, exact_match, org_id, +2 more.
search_summarizedB
Search across all Pipedrive items with summarized results (token-optimized)
Inputs: term (required), item_types, limit.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 30 tools
Most tools are clearly distinct by resource type (activities, deals, organizations, persons, etc.) and action (get vs. search). However, some ambiguity exists between 'get_overview', 'get_quarter_summary', and 'get_quarterly_progress', which all provide high-level metrics and could be confused for overlapping purposes. The search tools also have some overlap (e.g., 'search_items' vs. specific resource searches), but descriptions help differentiate them.
Tool names follow a highly consistent verb_noun pattern throughout, using snake_case uniformly. All tools start with 'get_' or 'search_', followed by the resource name (e.g., 'get_deals', 'search_persons'), with variations like 'summary' or specific qualifiers (e.g., 'get_current_quarter_deals') maintaining this structure. There are no deviations in naming conventions.
With 30 tools, the count is borderline high for a CRM server, as it includes many specialized variants (e.g., summary versions, quarterly tools) that might be excessive. While Pipedrive's domain is broad, 30 tools feels heavy and could overwhelm agents, though not extreme. A more streamlined set of 15-20 tools might be more appropriate.
The tool surface provides comprehensive read/search coverage for core CRM resources (deals, persons, organizations, activities, notes, users, pipelines, stages) with both detailed and summary views. However, there are notable gaps in write operations (e.g., create, update, delete), which are essential for full lifecycle management in a CRM system. Agents can perform queries effectively but may fail when needing to modify data.
Related MCP Connectors
Read-only sales CRM for AI clients: leads, pipeline, AI-agent chats, calls, ad attribution.
Read deals, persons, organizations, activities and pipelines; create and update CRM records.
CRM1The HubSpot MCP Server acts as a bridge that enables AI assistants and Large Language Models to securely interact with HubSpot CRM data through natural conversation, without requiring users to understand complex API structures. It provides read-only access to standard CRM objects (contacts, companies, deals, tickets, products, invoices, and more) and their associations, secured via OAuth 2.0, allowing AI agents to perform tasks like summarizing deals, fetching company updates, and looking up record changes.
Connect AI agents to Prosyo to query pipeline metrics, search B2B prospects, and manage multichannel LinkedIn and cold email outreach.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceProvides full CRUD access to Pipedrive CRM API, enabling Claude and other LLM applications to manage deals, persons, organizations, activities, notes, and leads with advanced filtering and fuzzy search capabilities.101 npm6MIT
- AlicenseBqualityBmaintenanceProvides comprehensive access to Pipedrive CRM with 100+ tools for managing deals, contacts, organizations, activities, and sales workflows through natural language conversations with Claude.30389 npm12MIT
- AlicenseBqualityBmaintenanceEnables users to manage Pipedrive CRM data including deals, contacts, and activities directly through an AI assistant. It supports full CRUD operations, email engagement analysis, and mapping of custom field metadata for comprehensive pipeline management.123159 npm10MIT
- FlicenseBqualityDmaintenanceEnables to manage Pipedrive deals, activities, persons, organizations, and custom fields with automatic backup and restore capabilities, allowing safe pipeline management via natural language.28-