Common Room MCP

Live

API KEY

COMMUNITY INTELLIGENCE

Marketing

Every community member, signal, and engagement event your team tracks lives in Commonroom. Commonroom MCP gives your agent authenticated access to community data scoped to the user who authorized it.

  • Acts as the user: Access and write actions stay tied to the Commonroom MCP account that authorized the agent.
  • Credentials stay vaulted: AES-256, resolved at request time, never in LLM context.
  • Scoped before every call: User permissions enforced. 90-day audit trail.
Common Room MCP
agent · Acme Q3
Run
Which community members showed buying signals this week and what companies are they at?
S
commonroom_signals_get
84ms
Community intelligence agent
7 members with buying signals this week. Top: @dev-sarah (Acme, 3 signals: pricing page, docs OAuth, GitHub stars), @pm-james (Globex, 2 signals: pricing, trial signup), @eng-maria (Initech, trial + docs).
Sources: 7 members, buying signals this week
commonroommcpmcp
7 members
18:29
Message Claude...

Tools your community intelligence agent reaches for on Commonroom MCP, scoped per user.

CALL ANY TOOL
List and search members, retrieve activity history, surface buying signals, and track community engagement.
commonroommcp_commonroom_create_object
Commonroom Create Object
Create a new object in Common Room — contact, organization, activity, or custom object type.
Parameters
Name
Type
Required
Description
objectType
string
Required
The Common Room object type to operate on. Use get_catalog to discover all available types.
activityBody
string
Optional
Body text content of the activity being recorded.
activityType
string
Optional
Activity type identifier for this engagement signal. Use get_catalog with objectType=ActivityType to see all valid types.
communityId
string
Optional
ID of the Common Room community to operate on.
companyDomain
string
Optional
Domain of the company (e.g. acme.com). Used to link contacts to organizations.
companyName
string
Optional
Name of the company the contact belongs to.
contactId
string
Optional
The unique ID of an existing Contact in Common Room.
customFields
array
Optional
Custom field values to set on the object.
description
string
Optional
Optional description or notes about the object.
domain
string
Optional
Domain of the organization (e.g. acme.com).
email
string
Optional
Email address of the contact. Used as the unique identifier for Contact objects.
entityType
string
Optional
The entity type associated with the activity.
fullName
string
Optional
Full name of the contact.
githubUsername
string
Optional
GitHub username of the contact.
linkedInUrl
string
Optional
Full LinkedIn profile URL of the contact.
name
string
Optional
Name of the organization or custom object.
note
string
Optional
A note to attach to this contact or organization.
occurredAt
string
Optional
ISO 8601 timestamp for when the activity occurred.
organizationId
string
Optional
The unique ID of an existing Organization in Common Room.
prospectorCompanyId
string
Optional
The Prospector company ID to associate with this record.
prospectorContactId
string
Optional
The Prospector contact ID to associate with this record.
segmentId
string
Optional
The ID of a Segment to assign this contact or organization to.
title
string
Optional
Job title of the contact.
twitterHandle
string
Optional
Twitter/X handle of the contact (without @).
commonroommcp_commonroom_get_catalog
Commonroom Get Catalog
commonroommcp_commonroom_list_objects
Commonroom List Objects
commonroommcp_commonroom_submit_feedback
Commonroom Submit Feedback
commonroommcp_commonroom_update_object
Commonroom Update Object
Build your Agent
Drop the toolkit in, point it at the user, and your community intelligence agent can use Commonroom MCP from the first run.
Python · LlamaIndex
import { ScalekitClient } from "@scalekit-sdk/node";
import { DynamicStructuredTool } from "@langchain/core/tools";
import { createReactAgent } from "@langchain/langgraph/prebuilt";
import { z } from "zod";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);

const { tools } = await sk.tools.listScopedTools("user_123", {
filter: { connectionNames: ["commonroommcp"], toolNames: ["commonroom_members_list", "commonroom_member_get", "commonroom_activities_list"] },
pageSize: 100,
});

const lcTools = tools.map((t) => new DynamicStructuredTool({
name: t.tool.definition.name,
description: t.tool.definition.description,
schema: z.object({}).passthrough(),
func: async (args) => {
const { data } = await sk.tools.executeTool({
toolName: t.tool.definition.name,
identifier: "user_123",
params: args,
});
return JSON.stringify(data);
},
}));

const agent = createReactAgent({ llm, tools: lcTools });
import { ScalekitClient } from "@scalekit-sdk/node";
import OpenAI from "openai";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
filter: { connectionNames: ["commonroommcp"], toolNames: ["commonroom_members_list", "commonroom_member_get", "commonroom_activities_list"] },
pageSize: 100,
});

const llmTools = tools.map((t) => ({
type: "function",
function: {
name: t.tool.definition.name,
description: t.tool.definition.description,
parameters: t.tool.definition.input_schema,
},
}));

const resp = await openai.responses.create({
model: "gpt-4o", input: prompt, tools: llmTools,
});
import { ScalekitClient } from "@scalekit-sdk/node";
import Anthropic from "@anthropic-ai/sdk";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
filter: { connectionNames: ["commonroommcp"], toolNames: ["commonroom_members_list", "commonroom_member_get", "commonroom_activities_list"] },
pageSize: 100,
});

const llmTools = tools.map((t) => ({
name: t.tool.definition.name,
description: t.tool.definition.description,
input_schema: t.tool.definition.input_schema,
}));

const msg = await anthropic.messages.create({
model: "claude-sonnet-4-6", max_tokens: 1024,
tools: llmTools,
messages: [{ role: "user", content: prompt }],
});
import { Agent } from "@google/adk/agents";
import {
MCPToolset, StreamableHTTPConnectionParams,
} from "@google/adk/tools/mcp";

const toolset = new MCPToolset({
connectionParams: new StreamableHTTPConnectionParams({
url: "https://mcp.scalekit.com/commonroommcp",
headers: { Authorization: `Bearer ${userScopedToken}` },
}),
});

const agent = new Agent({
name: "agent", model: "gemini-2.0-flash",
tools: await toolset.getTools(),
});
Try these prompts
Paste any prompt into your agent to start using Commonroom MCP.
Members & signals
Copy the prompt
Copied
Find members with buying signals this week.
Copy the prompt
Copied
List top 10 members by activity score.
Copy the prompt
Copied
Get profile for [member name].
Copy the prompt
Copied
Which companies have the most active members?
Activity & engagement
Copy the prompt
Copied
List all GitHub stars from this week.
Copy the prompt
Copied
Find new members who joined from [source] today.
Copy the prompt
Copied
Which members posted in Slack this week?
Copy the prompt
Copied
Activity breakdown by source last 30 days.
Reporting
Copy the prompt
Copied
Top companies by member engagement.
Copy the prompt
Copied
New member growth this month.
Copy the prompt
Copied
Members who went quiet (no activity 14+ days).
Copy the prompt
Copied
Segment members by job title.
SEE HOW AUTH WORKS
Users authorize Commonroom MCP once. Their credentials stay vaulted, every call is checked, and every action is logged.
1
Authorize
Your user connects
Common Room MCP
once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access
Who:
user ‘A’
when:
Once per user
access:
Limited to user
2
Store
Their
Common Room MCP
token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection
vault:
encrypted
scope:
per-user
tokens:
auto-refreshed
3
Resolve
When your agent calls a
Common Room MCP
tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs
speed:
~40ms
check:
before every call
seen by:
nobody
4
Audit
Every
Common Room MCP
tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it
history:
90 days
export:
SIEM-ready
logged:
every call
Test other agents
Same per-user auth pattern across other community intelligence agents and MCP connectors. Working code, live demos, fork what fits.
SALES
Outbound prospecting agent
Build targeted prospect lists with Apollo, enrich with firmographic data, and draft personalised outreach. Runs on a schedule.
ENGINEERING
Engineering standup agent
Aggregate GitHub and GitLab activity, link to Jira, and post a daily standup digest to Slack. No async updates.
Why Scalekit
Secure your agent's access. Connectors ship in minutes
Other connector libraries treat auth as a demo afterthought. Scalekit starts with user identity, scope enforcement, and audit.
01.
Shared tokens break per-user analytics
A shared token looks fine in a demo. In production every call looks like a service account. Scalekit resolves the real user credential so attribution, audit, and scope stay accurate.
// shared token
 audit → bot_service_account
 user_filter → broken

 // scalekit
 audit → user_abc
 scope → enforced ✓
02.
Authentication is not authorization
03.
Multi-tenancy is architectural
04.
Commonroom MCP today. Others tomorrow.
“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”
Venu Madhav Kattagoni
Head of Engineering / Von
FAQs
Frequently Asked Questions
Does the agent access Commonroom MCP as the user or as a shared key?
As the user. Each workspace member authorizes once and Scalekit resolves their credential at request time. Audit logs attribute every action to that user, not a shared service account.
Where is the Commonroom MCP api key stored?
In Scalekit's managed AES-256 token vault, namespaced per tenant. Refresh is automatic. Revocation is a single dashboard action. Tokens never appear in prompts, logs, or LLM context.
Can I limit what the agent is allowed to do in Commonroom MCP?
Yes. Pass a tool name filter to listScopedTools so the community intelligence agent only sees the subset you authorize. Pre-API-call scope checks block out-of-policy actions before the request reaches Commonroom MCP.
What happens when a user revokes Commonroom MCP access?
The connection is invalidated on the next tool call. Subsequent requests for that user fail closed with a clear error. Other users in the tenant remain unaffected. The event is logged for audit.
Can the agent access member data across all community sources the workspace has connected?
Only sources connected to the Commonroom workspace under the authorizing user's API key. The key is scoped to a single Commonroom organization. Cross-org member data is inaccessible.
Start in your coding agent
Up and running in one command
Install the Scalekit skill in your editor of choice. Connector, auth, tools, prompt, all wired up
Claude Code REPL
/plugin marketplace add scalekit-inc/claude-code-authstack
/plugin install agentkit@scalekit-auth-stack
Cursor Code REPL
# ~/.cursor/mcp.json
{
""mcpServers"": {
""commonroommcp"": {
""url"": ""https://mcp.scalekit.com/commonroommcp"",
""headers"": { ""Authorization"": ""Bearer $SCALEKIT_TOKEN"" }
}
}
}
Codex Code REPL
# ~/.codex/config.toml
[mcp_servers.commonroommcp]
url = ""https://mcp.scalekit.com/commonroommcp""
auth_env = ""SCALEKIT_TOKEN""
Copilot Code REPL
# .vscode/mcp.json
{
""servers"": {
""commonroommcp"": {
""url"": ""https://mcp.scalekit.com/commonroommcp"",
""type"": ""http""
}
}
}