CRM

Pipedrive with Claude & ChatGPT—Pipedrive MCP server

Live access to your persons, organizations, and deal timeline, read and write, through one unified profile per customer. Works in Claude, ChatGPT, Cursor, and any MCP-compatible agent.

What it looks like

What does Pipedrive data look like in Claude?

Connect Pipedrive once. Your agent gets identity-resolved profiles, the full deal and activity timeline, and write access—through one MCP server, identity-resolved with Gmail, Intercom, your website events, and your other sources.

MCP

Pipedrive, exposed as MCP tools.

Claude · pathbound MCP connected
you
Brief me on [email protected]—what’s her Pipedrive deal status, recent activity, and any risk signals?
get_contact { email: "[email protected]" } 200 · 304 tokens · 470ms
contact Jane Reyes · Senior PM
organization acme.com · fintech · 240
pipedrive deal = Acme Expansion · Proposal Made · $32k
get_contact_timeline { contact_id: "ctc_01H..." } 9 events · 450ms
tracker visited /pricing · 2× today
gmail replied to follow-up · yesterday
pipedrive stage → Proposal Made · activity due Fri
claude
Jane is Senior PM at Acme (fintech, 240). Her Pipedrive deal Acme Expansion ($32k) moved to Proposal Made, with a follow-up activity due Friday. She visited /pricing twice today and replied to your follow-up yesterday.
signal Proposal out, active engagement, activity already scheduled. Bring the Friday touch forward.
claude_desktop_config.json
{
  "mcpServers": {
    "pathbound": {
      "url": "https://mcp.pathbound.ai/mcp"
    }
  }
}
Pipedrive tools out of the box · read & write
get_contact unified profile across Pipedrive + your other sources
get_contact_timeline page views, email replies, deal stage changes
list_contacts filter by organization, label, owner, deal stage
get_company Pipedrive organization rolled into the unified company
create_contact_note log call recaps, research, internal context
update_contact patch person fields, labels, owner on the unified profile

…plus 20 more—26 MCP tools total, across contacts, companies, events, and conversations.

Setup

How do I connect Pipedrive to Claude?

OAuth one connector. Drop a snippet into your MCP client. Ask a question.

  1. 01

    Sign up for Pathbound

    Create an account at pathbound.ai. Free during public alpha.

  2. 02

    Connect Pipedrive

    In the dashboard, go to Integrations → Pipedrive → Connect. OAuth via Pipedrive’s official OAuth flow in one click; sync runs every minute and pulls persons, organizations, deals, and activities (incremental via update_time).

  3. 03

    Add Pathbound to your MCP client

    Drop the snippet below into your Claude Desktop config (or in Claude.ai web: Settings → Connected Apps → Add custom MCP → enter https://mcp.pathbound.ai/mcp). The same URL works for ChatGPT, Cursor, Cline, and any MCP client that supports OAuth.

    claude_desktop_config.json
    {
      "mcpServers": {
        "pathbound": {
          "url": "https://mcp.pathbound.ai/mcp"
        }
      }
    }
  4. 04

    Run a test prompt

    Ask the agent: “How many contacts do I have in Pipedrive?” The agent calls list_contacts via MCP and returns the count.

Why Pathbound

Your customer doesn’t live only in Pipedrive.

A direct Pipedrive MCP shows your agent Pipedrive. Pathbound shows your agent the customer—across Pipedrive, Gmail, Intercom, your website events, Apollo, Calendly, and the rest of your stack—through one unified profile served over the Model Context Protocol.

Beyond Pipedrive

Gmail threads, Intercom conversations, website page views, Apollo enrichment, Calendly meetings—all stitched onto one timeline per person. Your agent stops asking “who is this?” on every other tool.

Identity-resolved

Same person as [email protected] in Pipedrive, [email protected] in Gmail, “Jane R.” in Intercom—Pathbound resolves to one entity. A direct connector only knows its own person IDs.

Built for LLMs

Token-efficient response shapes (count_only, fields=summary), server-side aggregation, batch tools. Agents get the answer, not raw JSON dumps. Stays inside the context window.

Governed writes

Your agent can write, too—notes and person updates land on the unified profile, gated per-tool by an admin. Write-back to Pipedrive, versioning, and rollback are rolling out—the controls SOC 2 and GDPR reviewers expect.

FAQ

Common questions.

Is this an official Pipedrive MCP server?

Pathbound is an independent platform. We connect to Pipedrive via Pipedrive’s official OAuth 2.0 flow and expose your data through one Model Context Protocol server alongside your other sources. Not affiliated with Pipedrive.

How is this different from the Pipedrive REST API?

REST is for backends and scheduled jobs. MCP is for AI agents—it’s the protocol Claude, ChatGPT, and Cursor speak. Pathbound’s MCP also unifies Pipedrive with Gmail, Intercom, your website events, and other sources into one profile per contact, so the agent doesn’t glue six APIs together itself.

Which MCP clients does this work with?

Claude.ai, Claude Desktop, Claude Code, ChatGPT (with custom connectors), Cursor, Cline, Continue—any client that supports the Model Context Protocol with OAuth.

Can the agent write to Pipedrive, or just read?

Both. Pathbound exposes 16 read tools (list, get, timeline, conversations, aggregate, batch) and 10 write tools (create / update persons and organizations, create / update / delete notes). Writes land on the unified profile every connected agent reads; write-back into Pipedrive itself is rolling out.

What does the sync pull?

Persons, Organizations, Deals, and Activities, incrementally every minute using Pipedrive’s update_time filter. Each Person resolves to a unified profile by email → phone, then links to its Organization via the unified Company.

How does authentication work?

OAuth 2.0 end to end. The MCP client opens Pathbound’s login; you log in once and the agent gets scoped access tied to your user. Revoke anytime from Settings → Connected Apps.

Is my customer data secure?

Tenant-isolated and OAuth-scoped per user, with encryption at rest via our infrastructure provider’s default configuration. GDPR-aligned; SOC 2 readiness in progress. Pathbound does not sell customer data, and we don’t call AI providers on your behalf—your MCP client does, under your account and the AI provider’s terms.

What about HubSpot, Salesforce, Zoho, Apollo, Intercom?

Same MCP server, same tools—just connect a different source. See the integrations directory.

Try it on your own data

Within five minutes, your agent is querying real customer context.

Sign up, connect one CRM or drop the events snippet, and point your MCP client at mcp.pathbound.ai/mcp.