Pipedrive

Provides Claude with read-only and write-enabled access to Pipedrive data via MCP tools, with rate limiting, caching, and structured prompts.

typescript

GitHub Stars

typescript

Language

4 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "iamsamuelfraga-mcp-pipedrive": {
      "command": "npx",
      "args": [
        "-y",
        "@iamsamuelfraga/mcp-pipedrive"
      ],
      "env": {
        "LOG_LEVEL": "info",
        "PIPEDRIVE_TOOLSETS": "deals,persons,organizations,activities",
        "PIPEDRIVE_API_TOKEN": "YOUR_API_TOKEN",
        "PIPEDRIVE_READ_ONLY": "false"
      }
    }
  }
}

You can run a Production-ready MCP server that exposes Pipedrive data and operations to Claude, enabling natural-language automation of deals, contacts, activities, and custom fields. It includes rate limiting, caching, error handling, and read-only mode for safe experimentation, while offering guided workflows and read-only resources for quick insights.

How to use

Use an MCP client to connect to the Pipedrive MCP Server and start issuing natural-language requests. You can perform end-to-end workflows such as creating deals linked to contacts, scheduling activities, searching for organizations and their people, and examining pipelines. You also have read-only access to reference data like pipelines and custom fields, and you can enable or disable certain tool categories to tailor the experience. Start with simple tasks to confirm connectivity, then compose multi-step prompts to drive deals and activity management.

How to install

Prerequisites: Node.js installed on your machine, and a Claude Desktop setup if you plan to run locally.

Global installation option (optional): install the MCP server globally to run it from anywhere.

Using npx is recommended for quick startup without prior installation.

Configuration and usage notes

The MCP server uses your Pipedrive API token to access data. You can run it locally via a command runner like npx and configure environment variables to control behavior.

Environment variables you can set include the PIPEDRIVE_API_TOKEN, optional PIPEDRIVE_READ_ONLY to lock write operations, PIPEDRIVE_TOOLSETS to enable specific tool categories, and LOG_LEVEL for logging verbosity.

Available tools

pipedrive://pipelines

Access pipeline data including stages and deal counts for overview and reporting.

pipedrive://custom-fields

Discover custom field definitions for deals, persons, organizations, and activities.

pipedrive://current-user

Retrieve information about the authenticated user and their permissions.

create-deal-workflow

Guided workflow to create a new deal, attach a person, and schedule an initial activity.

sales-qualification

BANT-style qualification checklist to assess leads within Claude prompts.

follow-up-sequence

Multi-day activity follow-up sequence to maintain engagement with prospects.

weekly-pipeline-review

Pipeline health report prompt that summarizes open deals by stage and key metrics.

lost-deal-analysis

Analysis workflow to identify patterns in lost deals and inform next steps.

Built by

VeilStrat

AI signals for GTM teams