Skip to content

MCP

MCP Server

Talk to OnePageCRM from AI agents via the Model Context Protocol.

Maintained by the OnePageCRM engineering team · Last updated Jul 20, 2026

The OnePageCRM MCP server exposes CRM data and actions to AI agents through the Model Context Protocol. Once connected, the agent can read your contacts, deals, actions, notes, calls, and meetings — and create or update them on your behalf.

Connection map: an AI client such as Claude, ChatGPT, or Le Chat connects to the OnePageCRM MCP server at app.onepagecrm.com/mcp after a one-time OAuth consent in the browser, then uses the describe, context, query, create, and update tools against your CRM data — every call runs as the signed-in user

Endpoint

https://app.onepagecrm.com/mcp

The server speaks MCP over HTTP and uses OAuth 2.1 for authorization. You never paste an API key into the AI client — instead the client redirects you to OnePageCRM, you sign in, you approve the connection, and tokens flow back to the client behind the scenes.

Tools the server exposes

ToolPurpose
describe(entity)Per-field schema — types, query traits (filter/sort/group/aggregate), writable/required flags, lookups, and examples.
context()Account-specific reference data — statuses, pipelines, users, tags, custom fields.
query(oql)Read data via OQL — filters, ordering, aggregates.
create(entity, data)Create a contact, deal, action, note, call, or meeting.
update(entity, id, data)Update an existing object.

Supported AI clients

These AI clients connect out of the box — every OnePageCRM user can wire them up straight away, with no registration step on your end:

  • ChatGPT (OpenAI)
  • Claude (Anthropic — claude.ai, Claude Code)
  • Mistral (Le Chat)
  • Grok (xAI)
  • Perplexity

Add the MCP endpoint URL as a connector, sign in, approve the consent screen, and you’re connected. The help-center guide has step-by-step screenshots for each client.

Don’t see your client? If it speaks MCP but doesn’t connect out of the box, get in touch — we’ll get it set up.

First prompts to try

Once connected, the agent has a small toolbox: describe, context, query, create, update. Drive it in plain language — it picks the right tools for you, and it will chain several in one request.

  • “What’s on my Action Stream today?”
  • “Show me the deals I closed last quarter, grouped by owner.”
  • “Turn this call transcript into a note for Jane Doe and add a follow-up action.”
  • “Reschedule my overdue actions across next week, by priority.”
  • “Add this as a contact, tag them Trade Show, and set an action to call Tuesday.”

Permissions

You pick the connection’s permission level on the consent screen. Every connection requires the mcp scope — it switches the whole feature on. Without it there is no MCP access: a token that lacks the scope can’t reach the server, and every request comes back 403. On its own, mcp grants only the schema and reference tools (describe, context); the data scope you approve alongside it — crm.readonly or crm — decides whether the agent can read or write your records:

You approveThe agent can use
mcp onlydescribe, context
mcp + crm.readonly…plus query
mcp + crm…plus create and update

A connection never gains scope later — refreshed tokens keep exactly what you approved. To move from read-only to read-write (or back), disconnect the client and connect again with the scope you want.

Within the approved scope, the agent acts as the user who authorized it. If you can see a contact, the agent can see it; if you can edit a deal, the agent can edit it.