Common Room MCP Server | Common Room (Docs)

Common Room MCP Server

Last updated Sep 23rd, 2026

Overview

Common Room's MCP server connects your AI assistant directly to your go-to-market data — product signals, community activity, intent data, contact enrichment, and more. Using the Model Context Protocol (MCP), any compatible AI client can query and update your Common Room workspace in natural language to research accounts, prep for calls, build prospect lists, draft personalized outreach, and write new records back to Common Room.

The server supports both reading and writing data. In addition to querying contacts, organizations, activities, and segments, you can create new records and update existing ones — all from natural language in your AI client.

The server is hosted at https://mcp.commonroom.io/mcp

Prerequisites

Before connecting any AI client to Common Room's MCP server, you'll need a Common Room instance and an account with access to the instance.

Connecting Your AI Client

Claude

  1. Open Claude's settings and navigate to the Connectors → Manage section
  2. Install the Common Room connector
  3. Complete the OAuth authorization flow to connect your Common Room account
  4. Common Room tools will be available in your Claude conversations immediately

Note: If you use Claude for desktop (Cowork mode), see the dedicated Common Room for Claude setup guide for a more integrated experience including a purpose-built plugin.

ChatGPT

Common Room is available as an official ChatGPT App, providing a one-click connection experience.

Install via the ChatGPT App Store:

  1. Visit the Common Room ChatGPT App and click Add to ChatGPT
  2. You'll be redirected to authorize Common Room with your account credentials
  3. Once connected, open a new chat and enable the Common Room connector via the + menu in the message bar → More → select Common Room

Note: As of December 2025, ChatGPT renamed "Connectors" to "Apps" — the underlying functionality is the same.

Using the MCP Server

Once connected, you interact with Common Room through natural language. The following examples show some of what's possible across any connected AI client.

Account Research

Get a full intelligence brief on any company in your workspace — including product signals, community engagement, intent data, CRM fields, and AI-generated summaries.

Example prompts:

"Research Datadog ( datadog.com) for me"

"What's the latest signal activity for stripe.com?"

"Give me a quick overview of Notion — are they a good ICP fit?"

"What's the health score for my top 5 accounts?"

Contact Research

Look up individuals by name, email address, LinkedIn handle, or GitHub username to understand their role, recent activity, and how to engage them.

Example prompts:

"Who is sarah.chen@acmecorp.com?"

"Look up Marcus Rivera at Stripe — is he active?"

"Tell me about the most engaged contacts at Datadog"

Call Preparation

Before any customer or prospect meeting, get a structured brief that pulls together everything you need to know — account signals, attendee profiles, suggested talking points, and likely objections.

Example prompts:

"Prep me for my call with Figma tomorrow"

"I have a renewal QBR with Mixpanel next week — what should I know?"

Prospecting

Build targeted account or contact lists using signal data, firmographics, and segment membership. The MCP server distinguishes between your existing accounts (with full signal history) and net-new companies not yet in your workspace.

Example prompts:

"Find companies in my territory with high product usage scores that aren't in an open opportunity"

Writing Data to Common Room

The MCP server supports creating and updating records directly from your AI client. Use natural-language prompts to add contacts, organizations, activities, notes, and segments — or to update existing records — without leaving your AI assistant.

Creating Contacts

Add new contacts to Common Room with email, LinkedIn URL, or a Prospector contact ID. Contact creation uses upsert semantics: if a matching record already exists (matched by email or LinkedIn URL), the existing record is updated rather than creating a duplicate.

Example prompts:

"Add jane@acme.com as a contact with the title VP of Engineering at Acme Corp"

Creating Organizations

Add new organizations using a domain or a Prospector company ID. Organization creation also uses upsert semantics, with the domain as the dedup key.

Example prompts:

"Add stripe.com as an organization"

Administrative Controls

Permissions

Write operations respect the same per-user OAuth permissions as read operations. Users can only create or update data their Common Room account already has access to. Workspace role-based access controls apply to every write — there is no elevated service account or shared token.

Available Tools

The Common Room MCP server exposes the following tools to connected AI clients. These tools are called automatically by the AI based on your natural language requests — you won't need to invoke them by name.

Tool Description
commonroom_get_catalog Discover available object types, properties, filters, and sort fields
commonroom_list_objects Query and retrieve objects with filtering, sorting, and pagination
commonroom_create_object Create new contacts, organizations, segments, activities, and notes
commonroom_update_object Update existing contacts and organizations by ID
commonroom_submit_feedback Provide feedback on query results to improve response quality

Frequently Asked Questions

How does authentication work?

The Common Room MCP server uses OAuth 2.1. When you add the server URL to your AI client, the client will open a browser window redirecting you to Common Room's authorization page.