was-pipedrive-mcp
A self-contained MCP server for Pipedrive CRM that exposes 27 tools allowing AI coding assistants to read, create, update, search, and manage deals, contacts, activities, organizations, leads, and pipelines.
README
Pipedrive MCP (was-pipedrive-mcp)
A self-contained, cross-platform Model Context Protocol (MCP) server for Pipedrive CRM. Exposes 27 tools allowing AI coding assistants (Claude Desktop, Cursor, Antigravity, VS Code, Zed, etc.) to read, create, update, search, and manage Pipedrive deals, contacts, activities, organizations, leads, and pipelines. Built by Web Analytics Solution.
Prerequisites
| Required | How to install | |
|---|---|---|
| Node.js 18+ | running npx |
Mac: brew install node · Windows: https://nodejs.org · Linux: apt install nodejs npm |
| Git | letting npx clone from GitHub |
Mac: brew install git (or first git --version triggers Xcode tools) · Windows: https://git-scm.com · Linux: apt install git |
| Pipedrive account | to access CRM data | Sign up here |
| Personal API token | for API authentication | Walked through below |
Quick Start — 3 Steps
Step 1 — Get Credentials
- Log in to your Pipedrive account.
- Click on your profile icon in the top right corner and select Settings (or Personal preferences).
- Navigate to the API tab.
- Copy your Personal API token (or click Generate token if you don't have one yet).
Step 2 — Connect
Run the interactive authentication command in your terminal:
npx -y github:mnsmasum62786/was-pipedrive-mcp auth
Paste your API token when prompted. The CLI will automatically verify your token against Pipedrive (/users/me) and save it locally with secure 0600 permissions at ~/.was-pipedrive-mcp/config.json.
Step 3 — Add to Your AI Client
Add the following configuration to your AI client's MCP configuration JSON file:
{
"mcpServers": {
"Pipedrive MCP": {
"command": "npx",
"args": ["-y", "github:mnsmasum62786/was-pipedrive-mcp"]
}
}
}
Configuration File Locations by Client:
- Claude Desktop (Mac):
~/Library/Application Support/Claude/claude_desktop_config.json - Claude Desktop (Windows):
%APPDATA%\Claude\claude_desktop_config.json - Cursor:
~/.cursor/mcp.json(or via Cursor Settings -> MCP) - Google Antigravity / Windsurf:
~/.gemini/antigravity/mcp.jsonor~/.codeium/windsurf/mcp_config.json
What You Can Ask the AI
Here are example prompts you can use in your AI chat once connected:
Discovery & Inspection
- "Who am I logged in as in Pipedrive, and what company account is this?"
- "List all sales pipelines and their stages in my Pipedrive account."
- "List all users in our Pipedrive company account."
Sales Pipeline & Deals
- "Show me the top 10 open deals in Pipedrive right now."
- "Search for any deals related to 'Enterprise Upgrade'."
- "Create a new deal titled 'Acme Corp Q3 Renewal' valued at $15,000 USD in stage ID 2."
- "Move deal ID 45 to 'won' status."
Contacts & Organizations
- "Find contact persons with the name 'Jane Doe' or email 'jane@example.com'."
- "Create a new organization called 'TechStream Inc' located in Austin, TX."
- "Create a new contact person named 'John Smith' associated with organization ID 12 and phone '555-0199'."
Activities & Leads
- "List my scheduled activities and calls due this week."
- "Create a follow-up call activity for deal ID 45 due tomorrow at 14:00."
- "Mark activity ID 88 as completed."
- "Create a new lead in the Leads Inbox titled 'Inbound Web Inquiry - Acme Corp'."
All Tools (27 Total)
| Category | Tools | Description |
|---|---|---|
| Users & Account | pd_get_me, pd_list_users |
Inspect authenticated profile and company users. |
| Deals | pd_list_deals, pd_get_deal, pd_create_deal, pd_update_deal, pd_delete_deal, pd_search_deals |
Full CRUD, filtering, and text search for sales pipeline deals. |
| Persons (Contacts) | pd_list_persons, pd_get_person, pd_create_person, pd_update_person, pd_delete_person, pd_search_persons |
Manage individual contact persons and their contact details. |
| Organizations | pd_list_organizations, pd_get_organization, pd_create_organization, pd_update_organization, pd_search_organizations |
Manage company accounts and addresses. |
| Activities | pd_list_activities, pd_create_activity, pd_update_activity |
Schedule and complete tasks, calls, meetings, and emails. |
| Leads | pd_list_leads, pd_create_lead |
Manage early-stage leads in the Leads Inbox. |
| Pipelines & Stages | pd_list_pipelines, pd_list_stages |
Inspect pipeline structure and stage IDs. |
| Escape Hatch | pd_api |
Invoke any Pipedrive REST API v1 endpoint directly (GET, POST, PUT, DELETE). |
CLI Commands
You can run these commands directly via npx -y github:mnsmasum62786/was-pipedrive-mcp <command>:
auth— Interactive prompt to connect or re-connect your Pipedrive API token.status— Show config file path, verification status, and timestamp of saved credentials.logout— Delete the locally stored credentials file (~/.was-pipedrive-mcp/config.json).help— Print command line usage and environment variable instructions.
Multi-Account Setup
Power users can bypass the local config file by setting environment variables. This allows running multiple Pipedrive accounts simultaneously by defining separate entries in your AI client config:
{
"mcpServers": {
"Pipedrive Account A": {
"command": "npx",
"args": ["-y", "github:mnsmasum62786/was-pipedrive-mcp"],
"env": {
"PIPEDRIVE_API_KEY": "token_for_account_a"
}
},
"Pipedrive Account B": {
"command": "npx",
"args": ["-y", "github:mnsmasum62786/was-pipedrive-mcp"],
"env": {
"PIPEDRIVE_API_KEY": "token_for_account_b"
}
}
}
}
Troubleshooting
1. "Pipedrive MCP — not configured yet"
- Cause: The server was started without running the authentication setup.
- Fix: Open your terminal and run
npx -y github:mnsmasum62786/was-pipedrive-mcp auth.
2. HTTP 401 or Verification Failed during setup
- Cause: The Personal API token pasted is incorrect or has been revoked in Pipedrive.
- Fix: Check Settings -> Personal preferences -> API in Pipedrive, generate a new token, and run
authagain.
3. Windows PowerShell Execution Policy Error
If you see an error like npx.ps1 cannot be loaded because running scripts is disabled:
- Fix: Run the following command in PowerShell:
Set-ExecutionPolicy -Scope CurrentUser -ExecutionPolicy RemoteSigned
4. Old Code / Cached Version after Update
Windows and Mac may cache older npx bundles. To force clear the npx cache and pull the latest release:
- Windows (PowerShell):
Remove-Item -Recurse -Force "$env:LOCALAPPDATA\npm-cache" -ErrorAction SilentlyContinue npm cache clean --force - Mac / Linux:
rm -rf ~/.npm/_npx npm cache clean --force
License
MIT License. Built by Web Analytics Solution.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.