How to Use the Chainlit MCP in Vercel AI SDK

Q: How do I use the Vercel AI SDK to get a specific Chainlit thread?

Your agent uses the getthread tool from this MCP server. Just provide the thread ID. The Vercel AI SDK will stream the thread's entire payload, including node topology, right into your application's UI.

Q: Can I build a real-time dashboard for Chainlit with the Vercel AI SDK?

Yes. Combine the listprojects and getstats tools. Your agent can loop through projects, fetch their stats, and stream the results. The AI SDK is built for this, letting you render the data live in a React or Next.js component.

Connect the Vercel AI SDK to your Chainlit projects. Stream observability data right into your UI components.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Chainlit MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Audit Chat Threads in Real-Time

This MCP server gives your agent direct access to Chainlit conversations. You can build a custom UI that pulls specific interactions with `get_thread` or lists the raw model I/O using `list_steps`. Your front-end can show exactly how a conversation unfolded, step by step. Because you're using the Vercel AI SDK, this data streams directly into your React or Svelte components. The user sees the thread details appearing live in the browser. No loading spinners, no waiting for a full API response. It feels instant.

Build Live Analytics Dashboards

Hook your frontend directly into your Chainlit Cloud analytics. The `list_projects` tool gets all your app spaces, then `get_stats` pulls the traffic and resource numbers for each one. Your agent can feed this data straight into a chart. Imagine a dashboard in your Next.js app that's always current. When you ask your agent to check the stats, you watch the numbers update on your screen. That's what happens when the AI SDK's streaming power meets this server's direct data access.

Stream and Display User Feedback

Find out what users really think about your app's conversations. The `list_feedbacks` tool gets you the ratings and reviews users have left. Your agent can fetch this feedback and display it in a dedicated admin panel you build. This isn't a static report. You can create a UI that shows feedback as it's being fetched by your agent. The connection is fast and direct, giving you a live look at user sentiment across all your deployments.

Setup guide

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

Your agent uses the `get_thread` tool from this MCP server. Just provide the thread ID. The Vercel AI SDK will stream the thread's entire payload, including node topology, right into your application's UI.

Yes. Combine the `list_projects` and `get_stats` tools. Your agent can loop through projects, fetch their stats, and stream the results. The AI SDK is built for this, letting you render the data live in a React or Next.js component.

It's straightforward. You'll install the Vercel AI SDK's MCP package, then use `createMCPClient` with the server URL from Vinkius. Pass the resulting tools to `generateText` or `streamText` and you're ready to go.

It's more direct. You don't have to build and host a middle-layer API yourself. This server provides authenticated, sandboxed access straight to the Chainlit data your agent needs, which usually means less latency and zero maintenance for you.

Your data privacy is maintained through strong separation. The server processes requests to access Chainlit project, thread, and feedback data ephemerally. Vinkius never stores your content, and access is controlled by your private endpoint token.

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