How to Use the LangGraph Cloud (Stateful AI Agents) MCP in Vercel AI SDK

Q: How do I show an agent's progress in real-time with LangGraph Cloud (Stateful AI Agents) and the Vercel AI SDK?

Use the getrun tool in a polling loop or a streaming hook. It returns the current status of a graph execution. You can then display this status directly in your React components to show users exactly what the agent is doing.

Q: Can I let my users correct an AI agent's mistake?

Yes, that's what updatethreadstate is for. You can fetch the current state, display it in a form, let the user edit it, and then post the corrected state back. It gives your users final say over the agent's memory.

Build UIs that show your agent thinking. This Vercel AI SDK server streams LangGraph state directly to your components.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect LangGraph Cloud (Stateful AI Agents) MCP to Vercel AI SDK

Create your Vinkius account to connect LangGraph Cloud (Stateful AI Agents) 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 LangGraph Cloud (Stateful AI Agents) with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Manage Agent Conversations

This isn't a simple chatbot back-and-forth. You're building applications with persistent memory. Use `create_thread` to start a new stateful session for a user, then `create_run` to have an assistant act on it. You can see every thread you've created with `list_threads`. This gives you a top-down view of all active agent conversations, perfect for building admin dashboards or user session histories right in your Next.js app.

Stream State Directly to Your UI

Stop hiding agent activity behind a loading spinner. With the Vercel AI SDK, you can use `get_thread_state` to feed an agent's entire memory directly into your React components. Your users watch the agent's work happen live. Track the progress of any operation using `get_run` and `list_runs`. You can build a real-time activity log showing every step the agent takes. It’s the difference between a black box and a glass box.

Build Human-in-the-Loop Controls

Sometimes the user needs to grab the wheel. The `update_thread_state` tool lets you manually overwrite an agent's memory. This is how you build an 'approve/deny' button or let a user correct the agent's course. If a run is going sideways or taking too long, don't just wait. `cancel_run` gives you an immediate kill switch. You can wire this up to a 'Cancel' button in your UI, giving users full control over the agent's execution.

Setup guide

Set up LangGraph Cloud (Stateful AI Agents) 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 LangGraph Cloud (Stateful AI Agents) 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 LangGraph Cloud (Stateful AI Agents) 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 LangGraph Cloud. 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 LangGraph Cloud (Stateful AI Agents) 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 LangGraph Cloud (Stateful AI Agents) MCP in Vercel AI SDK

Use the `get_run` tool in a polling loop or a streaming hook. It returns the current status of a graph execution. You can then display this status directly in your React components to show users exactly what the agent is doing.

Yes, that's what `update_thread_state` is for. You can fetch the current state, display it in a form, let the user edit it, and then post the corrected state back. It gives your users final say over the agent's memory.

You can connect to any assistant deployed in your LangGraph Cloud environment. The `list_assistants` tool will give you a full list of available graph configurations you can execute against.

Yes. While you trigger runs from your frontend, you can also see scheduled jobs. The `list_crons` tool shows you all the automated runs configured in your LangGraph Cloud project, which is useful for building monitoring dashboards.

This server processes your LangGraph thread state, which includes conversation history and graph variables. All data is transmitted over encrypted connections, and Vinkius isolates your server instance. We never see your thread contents.

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