Commonroom MCP

Live

API KEY

COMMUNITY INTELLIGENCE

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.
Commonroom 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.
commonroom_members_list
List members
List community members with activity score and source filters.
Parameters
Name
Type
Required
Description
source
string
Optional
Source filter: github, slack, discord, twitter
limit
integer
Optional
Max members
commonroom_member_get
Get member
commonroom_activities_list
List activities
commonroom_signals_get
Get signals
commonroom_members_search
Search members
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.
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
Commonroom 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
Commonroom 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
Commonroom 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
Commonroom 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""
}
}
}