How to Use the Intercom MCP in Vercel AI SDK

Q: How do I stream Intercom conversation updates using the Vercel AI SDK?

Call getconversation inside your Next.js route handler to fetch the thread, then pass that data directly to streamText. This lets your frontend render the customer's history chunk by chunk without waiting for the full payload to load.

Q: Can I use the Vercel AI SDK to search Intercom contacts from an Edge Function?

Yes, you instantiate the client with createMCPClient and call searchcontacts inside your edge route. The lightweight HTTP transport keeps bundle sizes small, making it ideal for fast edge execution.

Q: How do I handle Intercom OAuth tokens within the Vercel AI SDK setup?

You configure the authProvider during the createMCPClient setup to inject the correct bearer token for each user. This ensures your streaming UI only accesses conversations the logged-in agent is authorized to view.

Q: What is the correct way to close the connection after a stream finishes?

Always invoke mcpClient.close() inside your stream's onFinish callback or within a finally block. Failing to close the connection leaves open HTTP sockets, which can exhaust your serverless function limits during peak traffic.

Feed live Intercom customer data directly into your Vercel AI SDK setup using this high-performance MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Intercom MCP to Vercel AI SDK

Create your Vinkius account to connect Intercom 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 Intercom with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live chat feeds for Vercel AI SDK

The `get_conversation` tool pulls entire message threads directly into your Vercel AI SDK stream. This means your customer-facing dashboard renders active support histories instantly as the edge function executes, saving users from staring at blank loading states. You pass the resulting JSON array straight to `streamText`, which pushes the text chunks to your React components. Combined with `reply_to_conversation`, this setup lets your interface post replies in real-time, updating the UI state immediately after the LLM completes its generation.

Instant contact lookups in React

The `search_contacts` tool queries your customer base using specific email or phone criteria to find matching profiles. This MCP Server integration allows your Next.js application to pull up a user's subscription status or tier right alongside their active chat window. Because this works inside Edge Functions, you run these lookups without cold-start penalties. Your system matches the incoming message with a profile, retrieves details via `get_contact`, and renders custom UI cards before the user even types their next question.

Direct knowledge base rendering

The `list_articles` tool fetches help center documentation directly into your Vercel AI SDK context window. Instead of forcing users to search a separate help center page, your chat interface pulls the exact article text they need based on their current query. Your frontend displays these articles as clean markdown components. The agent uses `list_tags` to categorize the issue on the fly, ensuring your team knows exactly which help center topics get the most traction in your live app.

Setup guide

Set up Intercom 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 Intercom 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 Intercom 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 Intercom. 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 Intercom 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 Intercom MCP in Vercel AI SDK

Call `get_conversation` inside your Next.js route handler to fetch the thread, then pass that data directly to `streamText`. This lets your frontend render the customer's history chunk by chunk without waiting for the full payload to load.

Yes, you instantiate the client with `createMCPClient` and call `search_contacts` inside your edge route. The lightweight HTTP transport keeps bundle sizes small, making it ideal for fast edge execution.

You configure the `authProvider` during the `createMCPClient` setup to inject the correct bearer token for each user. This ensures your streaming UI only accesses conversations the logged-in agent is authorized to view.

Always invoke `mcpClient.close()` inside your stream's `onFinish` callback or within a `finally` block. Failing to close the connection leaves open HTTP sockets, which can exhaust your serverless function limits during peak traffic.

Your conversation threads and contact emails remain strictly within your Vercel deployment and the secure Vinkius sandbox. No support data is stored on external servers, and the ephemeral V8 container wipes all memory as soon as your edge function execution terminates.

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