Skip to main content

Pipedrive MCP Server

A Python-based MCP (Model Context Protocol) server that connects Claude to the Pipedrive CRM API. It runs locally via stdio and provides 57 tools for managing the full Pipedrive data model through natural language.

Installation

pip install pipedrive-mcp

Or run directly without installing (recommended for Claude Desktop):

uvx pipedrive-mcp

Project Structure

pipedrive_mcp/
├── __init__.py    ← Package version
├── pipedrive.py   ← Pipedrive API Connector (11 resource classes)
└── server.py      ← MCP Server (57 tools)

Available Tools

57 tools across 12 categories:

Category Tools Operations
Deals 7 list, get, search, create, update, delete, list_deal_fields
Persons 6 list, get, search, create, update, delete
Organizations 6 list, get, search, create, update, delete
Activities 6 list, get, create, update, delete, list_activity_types
Notes 5 list, get, create, update, delete
Leads 7 list, get, search, create, update, delete, convert_to_deal
Pipelines & Stages 4 list_pipelines, get_pipeline, list_stages, get_stage
Products 6 list, get, search, create, update, delete
Deal Products 4 list, add, update, remove
Deal Participants 3 list, add, remove
Users / Team 2 list, get
Search 1 item_search (universal cross-entity search)

Key Features

  • Owner assignment: create_deal and update_deal support owner_id to assign deals to team members
  • Custom fields: create_deal supports custom_fields parameter for setting custom field values
  • Search with data extraction: All search handlers extract structured data (id, name, org, score) from Pipedrive's nested response format
  • Activity owner support: Activities use the v1 API to properly support user_id for owner assignment
  • Timezone handling: API expects times in UTC — convert from your local timezone before passing due_time

Setup

Claude Desktop Configuration

Add to ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "pipedrive": {
      "command": "uvx",
      "args": ["pipedrive-mcp"],
      "env": {
        "PIPEDRIVE_API_KEY": "YOUR_PIPEDRIVE_API_TOKEN"
      }
    }
  }
}

After changing the config: fully quit Claude Desktop (Cmd+Q) and restart.

Project Instructions (optional but recommended)

For best results, create a markdown file with your Pipedrive-specific context and add it to your Claude project instructions. Useful things to include:

  • Your team's user/owner IDs (run list_users to find them)
  • Your pipeline & stage IDs (run list_pipelines and list_stages)
  • Your custom field hash keys (run list_deal_fields)
  • Your timezone (API expects UTC — e.g. CET = UTC+1 in winter)
  • Any activity type key_strings used in your workspace (list_activity_types)

Troubleshooting

  • MCP not visible? → Fully quit Claude Desktop (Cmd+Q) and restart
  • API errors? → Check your API key in the config
  • Module not found? → pip install pipedrive-mcp

Planned Enhancements

  • Webhook endpoint in MCP server for automatic triggers on Pipedrive stage changes
  • Troi time tracking integration
  • PyPI package for one-line installation via uvx pipedrive-mcp

Metadata

Release files for pipedrive-mcp 0.5.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for pipedrive-mcp 0.5.0
File Size Uploaded Provenance
pipedrive_mcp-0.5.0.tar.gz 75.1 kB Without provenance Details

Built distribution (wheel)

Table of built distributions (wheels) for pipedrive-mcp 0.5.0
File Interpreter ABI Platform
pipedrive_mcp-0.5.0-py3-none-any.whl Python 3 none any Details

Total release size: 99.1 kB

Release files / pipedrive_mcp-0.5.0.tar.gz

Download URL pipedrive_mcp-0.5.0.tar.gz
Size 75.1 kB
Tags Source
SHA-256 checksum
How to use checksums
00ebe1d89db8a4b7b707d3d6cc8885c2c0670b99432baede190cba8f1751738d
BLAKE2b-256 checksum
How to use checksums
8e1250e85f53f059a2883f1532825351fea18c9dfe14ccf219549fc3ba6ece9d
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via uv/0.10.7 {"installer":{"name":"uv","version":"0.10.7","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"macOS","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

Release files / pipedrive_mcp-0.5.0-py3-none-any.whl

Download URL pipedrive_mcp-0.5.0-py3-none-any.whl
Size 24.0 kB
Tags Python 3
SHA-256 checksum
How to use checksums
54a93c6dcdb3969ab25251c0cdd890c5e1846cfc2fa40aeb6e894b5bcadd5617
BLAKE2b-256 checksum
How to use checksums
8c30b9960756e212026c3d71b3884b3942b6603320814da5bb8c2db4c60e3328
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via uv/0.10.7 {"installer":{"name":"uv","version":"0.10.7","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"macOS","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

Security for pipedrive-mcp 0.5.0

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Release history Release notifications | RSS feed

This release

0.5.0 This release

2 release files No provenance

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page