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

Q: How do I run a specific agent using LangGraph Cloud (Stateful AI Agents) in Claude Desktop?

Use the listassistants tool to find the ID of your deployed graph. Once you have it, pass that ID and your input payload to createrun to start the execution inside Claude Desktop.

Q: Can I pause and modify agent state with LangGraph Cloud (Stateful AI Agents) inside Claude Desktop?

Yes. You fetch the current state using getthreadstate, edit the payload, and write it back with updatethreadstate right from the Claude Desktop chat panel.

Q: What happens if an agent run hangs while using LangGraph Cloud (Stateful AI Agents) in Claude Desktop?

You can check the status using getrun to see where it stalled. If it is stuck, call cancelrun to stop the execution immediately inside your Claude Desktop session.

Q: How does this MCP Server handle scheduled runs?

The server uses listcrons to show you any automated, recurring agent runs. You can monitor these background tasks without leaving your Claude Desktop interface.

Run complex, stateful multi-agent graphs directly inside Claude Desktop without losing your context.

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 Claude Desktop

Create your Vinkius account to connect LangGraph Cloud (Stateful AI Agents) to Claude Desktop 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 Claude Desktop

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Intercept and override agent state in Claude Desktop

The `update_thread_state` tool gives you direct control over your running agent's memory right inside the Claude Desktop chat window. When your LangGraph agent hits a decision point requiring human sign-off — and that's usually where things break — you can inspect the current state and rewrite the variables on the fly inside Claude Desktop. This prevents the LangGraph LLM from going down a hallucinated path while you are working in your desktop environment. By calling `get_thread_state`, Claude Desktop fetches the exact history of your stateful agent's execution. You see exactly what the agent knows in Claude Desktop before you decide to inject new variables or resume the run. It keeps your complex LangGraph Cloud graphs from running wild on your local machine.

Control active LangGraph Cloud runs from your chat

The `create_run` tool executes your deployed LangGraph Cloud agent graph directly inside Claude Desktop using your local context. You kick off background tasks with custom inputs and watch the steps execute in real time in your Claude Desktop chat. If the LangGraph agent gets stuck in an infinite loop, you can immediately kill it from the desktop app. Executing `cancel_run` stops runaway processes before they burn through your Claude Desktop session's token budget. You track active runs with `get_run` to see which LangGraph node is currently executing and why. This level of control makes Claude Desktop a powerful command center for stateful agent workflows.

Browse your LangGraph Cloud MCP Server configurations

The `list_assistants` tool retrieves all your deployed LangGraph Cloud agent configurations directly into the Claude Desktop sidebar. You switch between different specialized LangGraph agents without writing code or leaving your Claude Desktop conversation. Each assistant represents a unique graph setup ready to handle specific tasks in your desktop client. Querying `list_threads` shows you all active sessions that this MCP Server is currently tracking for Claude Desktop. You can resume old conversations or audit past runs in Claude Desktop by pulling up their history with `list_runs`. It turns your desktop chat client into a full-featured LangGraph Cloud agent dashboard.

Setup guide

Set up LangGraph Cloud (Stateful AI Agents) MCP in Claude Web or Desktop

1

Open Claude Settings

Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.
2

Add Custom Connector

Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL: https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. For OAuth-protected servers, expand Advanced settings to add credentials.
3

Start a conversation

Open a new chat. The LangGraph Cloud (Stateful AI Agents) MCP tools are available immediately — no restart needed.

Endpoint URL

https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

No configuration file needed — paste the URL directly in the Claude web interface.

Available on Free (1 connector), Pro, Max, Team, and Enterprise plans.

Prerequisites

Claude Desktop installed (macOS or Windows)
Active Vinkius subscription with a valid endpoint token

1

Open Claude Desktop Settings

Click the menu icon at the top-left corner, go to Settings → Developer → Edit Config. This opens claude_desktop_config.json in your default text editor.
2

Paste the LangGraph Cloud (Stateful AI Agents) MCP configuration

Copy the JSON snippet on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Desktop

Close and reopen the application. Claude needs a full restart to load new MCPs — refreshing a conversation is not enough.
4

Verify the connection

Open a new conversation. Click the 🔌 icon at the bottom of the message input. You should see tools listed under langgraph-cloud-stateful-ai-agents-mcp.

json

{
  "mcpServers": {
    "langgraph-cloud-stateful-ai-agents-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

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 Claude Desktop

Use the `list_assistants` tool to find the ID of your deployed graph. Once you have it, pass that ID and your input payload to `create_run` to start the execution inside Claude Desktop.

Yes. You fetch the current state using `get_thread_state`, edit the payload, and write it back with `update_thread_state` right from the Claude Desktop chat panel.

You can check the status using `get_run` to see where it stalled. If it is stuck, call `cancel_run` to stop the execution immediately inside your Claude Desktop session.

The server uses `list_crons` to show you any automated, recurring agent runs. You can monitor these background tasks without leaving your Claude Desktop interface.

Your thread states and raw agent memory never touch Vinkius servers in unencrypted form. The MCP Server executes in a secure V8 sandbox, sending state payloads directly to your LangGraph Cloud instance via HTTPS.

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