How to Use the Common Room MCP in Vercel AI SDK

Q: How does streaming work when searching contacts in Common Room using Vercel AI SDK?

When the agent calls searchcontacts, the SDK streams the tool invocation state to your UI. You can catch this state in your React components to display a skeleton loader, then render the contact profiles the millisecond the data arrives.

Q: What is the best way to handle errors when adding contacts to segments?

Wrap your generateText or streamText call in a standard try-catch block. If addcontacttosegment fails due to an invalid segment ID, the SDK catches the error from the MCP server and lets your UI display a clean, human-readable fallback message.

Send Common Room community data directly into your Next.js frontend in real-time using the Vercel AI SDK.

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 Vercel AI SDK

Create your Vinkius account to connect Common Room to Vercel AI SDK 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 Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build live Common Room dashboards with Vercel AI SDK

Your users don't want to wait for a full page reload to see who just joined their community. By pairing this MCP server with `streamText`, you can render user profiles instantly as your agent finds them. The agent calls `get_contact_by_email` or `get_contact_tags` and pipes the raw JSON straight into your custom UI components before the LLM even finishes its sentence. This eliminates loading spinners entirely. When someone searches for a lead, the client uses `search_organizations` to pull company data and stream it directly into your React state. You get a fast, responsive interface that feels like a native desktop app rather than a slow API wrapper.

Real-time segment updates on the edge

Managing community buckets shouldn't require jumping between tabs. With this setup, your AI client can execute `add_contact_to_segment` or check progress using `get_segment_status` inside an Edge Function. Data streams back to the browser instantly, letting admins see exactly when a contact gets sorted. Because the Vercel AI SDK handles streaming tool calls natively, you can show a live log of contacts moving between lists. The agent lists the active groups with `list_segments` and lets users click to reassign members on the fly without waiting for backend queues.

Inspect accounts on the fly with our MCP Server

Give your sales team a live-updating console to inspect incoming signups. When a new email hits your database, the SDK triggers `get_organization_details` to fetch firmographic data. The agent displays the results in a custom UI card while the user is actively chatting. By querying `search_contacts` and displaying the results through React components, you bypass traditional dashboard clutter. Your team gets immediate context on who is talking to them, backed by live data pulled directly from your community database.

Setup guide

Set up Common Room MCP in Vercel AI SDK

Prerequisites

Node.js 18+ and a TypeScript project
ai + @modelcontextprotocol/sdk packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies

Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).
2

Create the Streamable HTTP transport

Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and use tools

Call mcpClient.tools() to auto-discover all Common Room tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.
4

Works with any model provider

Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts

import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent Common Room transactions",
});

console.log(text);
await mcpClient.close();

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 Vercel AI SDK

You configure the credentials through Vinkius, which handles the secure token exchange. In your Next.js app, you pass the single Vinkius endpoint URL to the setup, letting you query community segments without storing API keys in your frontend code.

Yes, the integration is fully compatible with Edge Functions. You initialize the client, call `list_segment_members` or `list_activity_types` to gather your community data, and stream the response to the user with minimal latency.

When the agent calls `search_contacts`, the SDK streams the tool invocation state to your UI. You can catch this state in your React components to display a skeleton loader, then render the contact profiles the millisecond the data arrives.

Wrap your `generateText` or `streamText` call in a standard try-catch block. If `add_contact_to_segment` fails due to an invalid segment ID, the SDK catches the error from the MCP server and lets your UI display a clean, human-readable fallback message.

Vinkius runs the server in an isolated V8 sandbox, ensuring your contact emails and organizational records are never cached or exposed. Your queries to `get_contact_by_email` run through encrypted, ephemeral tunnels that close immediately after the tool execution finishes.

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