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.
{
"mcpServers": {
"pathbound": {
"url": "https://mcp.pathbound.ai/mcp"
}
}
} …plus 20 more—26 MCP tools total, across contacts, companies, events, and conversations.
OAuth one connector. Drop a snippet into your MCP client. Ask a question.
Create an account at pathbound.ai. Free during public alpha.
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).
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.
{
"mcpServers": {
"pathbound": {
"url": "https://mcp.pathbound.ai/mcp"
}
}
} Ask the agent: “How many contacts do I have in Pipedrive?” The agent calls list_contacts via MCP and returns the count.
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.
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.
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.
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.
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.
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.
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.
Claude.ai, Claude Desktop, Claude Code, ChatGPT (with custom connectors), Cursor, Cline, Continue—any client that supports the Model Context Protocol with OAuth.
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.
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.
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.
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.
Same MCP server, same tools—just connect a different source. See the integrations directory.
Sign up, connect one CRM or drop the events snippet, and point your MCP client at
mcp.pathbound.ai/mcp.