How to Use the Common Room MCP in Mastra AI

Q: Can I trigger a Mastra workflow based on Common Room activity types?

Yes, you can build a workflow that polls the server using listactivitytypes to check for new interactions. Once a new activity type is detected, Mastra can trigger downstream actions like logging the event or updating a contact's profile.

Build resilient community automation workflows with Mastra AI and Common Room.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Common Room MCP to Mastra AI

Create your Vinkius account to connect Common Room to Mastra AI and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Common Room with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run resilient onboarding workflows using Mastra AI

Community operations require steps that cannot afford to fail. When a new member joins, your Mastra agent can run a multi-step workflow that starts with `get_contact_by_email` to check their background. If the API rate limit hits, Mastra automatically retries with exponential backoff to ensure the check completes. From there, the workflow uses conditional logic to decide what to do next. Should the contact have specific tags found via `get_contact_tags`, Mastra routes them to a VIP list using `add_contact_to_segment` or alerts an account executive if they belong to a target company.

Sync accounts reliably with this MCP Server

Mapping community members to accounts often breaks when APIs timeout. Mastra handles this by wrapping your `search_organizations` and `get_organization_details` calls in a durable execution context. If the network hiccups, the workflow pauses and resumes without losing state. You can write a workflow that first searches for a company, checks its details, and then updates the member's record. This ensures your CRM data and community data stay aligned even during peak traffic periods or API outages.

Automate cohort management with conditional steps

Keep your marketing lists fresh by scheduling regular cohort checks. Your agent can run a daily workflow that calls `list_segments` to find active groups, then queries `get_segment_status` to monitor changes in member counts. If a segment grows too quickly, Mastra triggers a conditional branch to alert your community managers. The agent can automatically extract the list using `list_segment_members` and format a report, ensuring no high-value cohort goes unnoticed.

Setup guide

Set up Common Room MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Common Room tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "common-room-mcp-client",
  servers: {
    "common-room-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Common Room Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Common Room tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Common Room transactions"
);
console.log(result.text);

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Common Room. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Common Room now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Common Room MCP in Mastra AI

You instantiate the MCP client using the Vinkius URL and add it to your Mastra configuration. From there, you spread the server tools directly into your agent's toolset, allowing it to execute functions like `search_contacts` out of the box.

Yes, Mastra supports human-in-the-loop approvals. You can configure your workflow to pause before executing `add_contact_to_segment`, prompting an operator to approve the change before the database is updated.

Mastra features built-in retry mechanisms with exponential backoff. If a heavy query like `list_segment_members` triggers a rate limit, the framework automatically backs off and retries the call, preventing workflow failures.

Yes, you can build a workflow that polls the server using `list_activity_types` to check for new interactions. Once a new activity type is detected, Mastra can trigger downstream actions like logging the event or updating a contact's profile.

Vinkius runs the MCP server in an isolated V8 sandbox where credentials never touch the client-side code. Your segment counts and tag data are processed entirely in memory, ensuring that sensitive community metrics are never written to persistent disk storage.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript