# Pipedrive

> Pipedrive MCP — search deals, contacts, organizations, and activities across the Pipedrive REST API.

[Canonical HTML page](https://top-mcps.com/mcp/pipedrive) · [server.json](https://top-mcps.com/mcp/pipedrive.json) · [methodology](https://top-mcps.com/about/methodology)

## Install

### Claude Desktop — `claude_desktop_config.json`

Paste under mcpServers. Fully quit and reopen Claude after editing.

```json
{
  "mcpServers": {
    "pipedrive": {
      "command": "npx",
      "args": [
        "-y",
        "pipedrive-mcp-server"
      ],
      "env": {
        "PIPEDRIVE_API_TOKEN": "${PIPEDRIVE_API_TOKEN}"
      }
    }
  }
}
```

### Claude Code — `CLI or .mcp.json`

Run from your repo. Commit .mcp.json to share with your team.

```shell
# export PIPEDRIVE_API_TOKEN=your_pipedrive_api_token
claude mcp add pipedrive -- npx -y pipedrive-mcp-server
```

### Cursor — `.cursor/mcp.json`

Global path: ~/.cursor/mcp.json. Reload window after editing.

```json
{
  "mcpServers": {
    "pipedrive": {
      "command": "npx",
      "args": [
        "-y",
        "pipedrive-mcp-server"
      ],
      "env": {
        "PIPEDRIVE_API_TOKEN": "${PIPEDRIVE_API_TOKEN}"
      }
    }
  }
}
```

### VS Code — `.vscode/mcp.json`

VS Code uses the "servers" key (not "mcpServers").

```jsonc
{
  "servers": {
    "pipedrive": {
      "command": "npx",
      "args": [
        "-y",
        "pipedrive-mcp-server"
      ],
      "env": {
        "PIPEDRIVE_API_TOKEN": "${PIPEDRIVE_API_TOKEN}"
      }
    }
  }
}
```

### Windsurf — `~/.codeium/windsurf/mcp_config.json`

Open via Cascade → hammer icon → Configure.

```json
{
  "mcpServers": {
    "pipedrive": {
      "command": "npx",
      "args": [
        "-y",
        "pipedrive-mcp-server"
      ],
      "env": {
        "PIPEDRIVE_API_TOKEN": "${PIPEDRIVE_API_TOKEN}"
      }
    }
  }
}
```

### Cline — `cline_mcp_settings.json`

Open via the Cline sidebar → MCP Servers → Edit.

```json
{
  "mcpServers": {
    "pipedrive": {
      "command": "npx",
      "args": [
        "-y",
        "pipedrive-mcp-server"
      ],
      "env": {
        "PIPEDRIVE_API_TOKEN": "${PIPEDRIVE_API_TOKEN}"
      }
    }
  }
}
```

### Continue — `~/.continue/config.json`

Continue uses modelContextProtocolServers with a transport block.

```json
{
  "experimental": {
    "modelContextProtocolServers": [
      {
        "transport": {
          "type": "stdio",
          "command": "npx",
          "args": [
            "-y",
            "pipedrive-mcp-server"
          ],
          "env": {
            "PIPEDRIVE_API_TOKEN": "${PIPEDRIVE_API_TOKEN}"
          }
        }
      }
    ]
  }
}
```

### Codex CLI — `~/.codex/config.toml`

Codex uses TOML. Each server is a [mcp_servers.<name>] subtable.

```shell
# ~/.codex/config.toml
[mcp_servers.pipedrive]
command = "npx"
args = [
  "-y",
  "pipedrive-mcp-server",
]
env = { PIPEDRIVE_API_TOKEN = "${PIPEDRIVE_API_TOKEN}" }
```

### Zed — `~/.config/zed/settings.json`

Zed calls them "context_servers". Settings live-reload on save.

```jsonc
{
  "context_servers": {
    "pipedrive": {
      "command": {
        "path": "npx",
        "args": [
          "-y",
          "pipedrive-mcp-server"
        ]
      },
      "env": {
        "PIPEDRIVE_API_TOKEN": "${PIPEDRIVE_API_TOKEN}"
      }
    }
  }
}
```

### ChatGPT — `ChatGPT → Apps directory`

Pipedrive doesn't ship a hosted HTTPS endpoint today. ChatGPT supports remote MCP servers only — to use this server in ChatGPT you'll need to deploy it to a public HTTPS URL first (e.g. via Cloudflare Workers or Vercel) or wait for an official remote build.

```none

```

## At a glance

- **Maintainer:** Community (multiple maintained forks — Pipeworx, lukehinds, WillDent)
- **Transport:** stdio
- **Auth model:** API key
- **Required secrets:** PIPEDRIVE_API_TOKEN
- **Supported clients:** Claude, Cursor, Any MCP-compatible client
- **License:** MIT
- **Language:** TypeScript
- **Latest version:** latest
- **Last verified:** 2026-06-11
- **GitHub stars:** 56 (fetched 2026-06-17T07:09:46.826Z)
- **Score:** 56/100 (rubric 2026-04 — see https://top-mcps.com/about/methodology)
- **Source:** https://github.com/WillDent/pipedrive-mcp-server

## Security & scope

- **Access scope:** read-write
- **Sandbox:** Authenticates with a Pipedrive API token. Access scope matches the token-owner's permissions in Pipedrive.
- **Gotchas:**
  - Personal API tokens inherit all of the user's permissions — create a dedicated automation user with minimum scope rather than reusing a salesperson's token.
  - Pipedrive enforces per-token rate limits; high-volume agents should batch reads via the unified search endpoint.

## Quick answer

**What it does.** Wraps the Pipedrive REST API as MCP tools — search/read/create/update for deals, persons, organizations, activities, notes, and pipelines via API-token auth.

**Best for:**
- Deal stage updates from chat
- Activity logging without leaving the IDE
- Pipeline reporting queries
- Person/organization research and updates
- Cross-pipeline "stuck deals" surfacing

**Not for:**
- Compliance-only-vendor-MCP environments
- Bulk data migration (use the REST API directly)
- Teams not on Pipedrive

## Recipes

### Surface stuck deals across the pipeline

```
Using the Pipedrive MCP, find every deal in stage "Proposal Sent" that has had no activity in the last 14 days. Return deal title, owner, value, and last activity date.
```

_Tested with: Claude Desktop, Cursor_

## Description

A community-maintained Pipedrive MCP server that wraps the Pipedrive REST API v1 — deals, persons, organizations, activities, notes, pipelines, and unified search. Requires a Pipedrive API token from your Pipedrive personal preferences. No official Pipedrive-published MCP exists yet; this is the most-maintained community implementation as of 2026-06.

## Why it matters

Pipedrive is the highest-search-volume SMB CRM after HubSpot — every "best MCP for CRM" SERP names it. Until Pipedrive ships an official server, a clean community wrapper is the realistic path for teams that want agent-driven pipeline updates against Pipedrive data.

## Key features

- Wraps the full Pipedrive REST API v1
- Deals, persons, organizations, activities, notes, pipelines
- Unified search across record types
- API-token auth via `PIPEDRIVE_API_TOKEN`
- Local stdio — runs next to the client

## FAQ

### Where is the API token?

Pipedrive → Settings → Personal preferences → API. Each user has a personal token; for shared agent flows, create a dedicated automation user with the minimum required permissions and use its token instead of a salesperson's personal token.

### Is there an official Pipedrive MCP?

Not as of 2026-06. Pipedrive has discussed it in the developer community but has not shipped a first-party server. Until then, the community wrappers are the realistic path. We will swap to the official endpoint when it ships.

### Does it support custom fields?

Yes — the Pipedrive REST API exposes custom fields by their hash key. The MCP surfaces them as part of the record payload so an agent can read or update them by name or by key.

### Which fork should I install?

The npm package `pipedrive-mcp-server` (WillDent) is the most-installed maintained option as of 2026-06. The Pipeworx and lukehinds forks are alternatives if you need a specific feature set; the API coverage is similar across all three.

## Changelog

- **2026-06-11** — Refreshed install snippets and fact sheet; verified for 2026.
- **2025-09-15** — Initial directory listing.