Who it is for
Sales and go-to-market teams that already use Common Room for prospecting and account research.
Overview
Common Room brings buyer intelligence into ChatGPT as a research surface. Accounts and contacts can be looked up, buying signals surfaced, and activity history read through ordinary questions.
Prospect list building is part of it. New companies can be found by industry, headcount, technology in use, or location, and contacts filtered or sorted by segment, role, lead score, or recorded website visits. Results draw on CRM fields, scores, enrichment data, and signals held in the connected account.
Worked examples in the listing include researching a named company and drafting an approach to it, looking up a single contact by email address, finding economic buyers inside a saved segment, and identifying pricing page visitors from the past week. Six skills are named, covering account and contact research, prospecting, call preparation, outreach drafting, and a weekly briefing.
Sales and go-to-market teams that already use Common Room for prospecting and account research.
Prospect filters extend to technology in use and recent website visits alongside the usual firmographic criteria.
Availability
Common Room ships this on both marketplaces: Common Room is listed in the Claude connectors directory and in the ChatGPT apps directory, under the same publisher domain.
Only 392 of the 3,150 products in this directory are listed in both marketplaces. One MCP server can serve both surfaces; what differs is each platform's listing and review process.
ChatGPT listing
Common Room declares 6 named skills, which puts it in the 6.7% of ChatGPT-listed apps that do.
Claude listing
Common Room publishes 5 tools to Claude, a deliberately narrow surface; only 22.3% of the 1,253 Claude-listed connectors expose fewer.
The median Claude-listed connector filed under Sales & Marketing publishes 18, so this one sits 13 tools below its bucket's median, 85th of 94.
It falls in the 4-6 tools band, which holds 16.2% of the Claude directory.
Common Room publishes a remote MCP endpoint. Claude connects to it over HTTP; there is nothing to install locally.
Every connector in the Claude directory is remote, all 1,253 of them, so transport is not a differentiator there.
https://mcp.commonroom.io/mcp Common Room carries partner verification in the Claude directory, which 474 of 1,253 listings do (37.8%). That is a review step past self-publishing, not an Anthropic-built server.
In the publisher's words
Embed complete buyer intelligence directly within Claude. Research accounts and contacts, surface buying signals, and browse activity history - all through natural language. Build prospect lists of net-new companies by industry, size, tech stack, or location. Filter and sort contacts by segment, role, lead score, or website visits. Every result is grounded in real context, real prioritization, and real revenue opportunity directly from your CRM fields, scores, enrichment, and signals - so you always know what's actually happening in your accounts.
Quoted from the connector's own Claude directory listing as captured in August 2026. Node8 did not write it and does not vouch for it.
Nearby
Per account agents for sales and revenue teams
Claude · ChatGPT
Verified per-deal records assembled from scattered revenue data
Claude
Shared brand context and on-brand content generation for GTM
Claude
Low-level GTM search primitives for in-house agent builders
Claude
Cloud marketplace revenue and subscription reporting across AWS, Microsoft, Google
Claude
Retention campaign drafting and sending through StopChurn
Claude
This is an independent catalogue entry compiled by Node8 from Common Room's public marketplace listings as they stood in August 2026. Listing facts come from the marketplaces; the comparisons against the rest of the directory and any live-endpoint measurements are Node8's. Node8 is not affiliated with Common Room, and inclusion here is not an endorsement.
Node8 builds MCP servers end to end: deciding which tools are worth exposing, the authentication and permission model, the review submissions, and the onboarding that gets them used. One server serves ChatGPT, Claude, and Microsoft Copilot.