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

Q: How do I use LangGraph Cloud (Stateful AI Agents) with Claude Code in a shell script?

You can pipe commands together. For instance, claude mcp langgraph-cloud createthread jq -r '.id' will give you a thread ID you can use in subsequent createrun calls within your script.

Q: Can I fix a running agent from the command line?

Yes. Use claude mcp langgraph-cloud getthreadstate --threadid to get the state, save it to a file, edit it, and then use claude mcp langgraph-cloud updatethreadstate --threadid --stategraph @yourfile.json to push the fix.

Q: What's the command to connect LangGraph Cloud (Stateful AI Agents) to Claude Code?

Run claude mcp add --transport http langgraph-cloud-mcp -- . Use claude mcp list to confirm it was added correctly. Your configuration is saved in /.claude.json.

Q: How do I find a stuck run with Claude Code and LangGraph Cloud (Stateful AI Agents)?

You can script it. Use claude mcp langgraph-cloud listruns and parse the output with jq to filter for runs that have been 'running' for too long. Then, pipe those run IDs to the cancelrun command.

Orchestrate and manage stateful LangGraph agents directly from your terminal with Claude Code.

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 Code

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run Stateful Agents in CI/CD

This is built for automating agent workflows in headless environments. Your script can call `create_thread` to get a new thread ID, then trigger a job on it with `create_run`. It's designed for CI/CD. Build a polling loop in your shell script using `get_run` to wait for completion. Once it's done, your GitHub Action or Jenkins job can proceed to the next stage. It makes stateful agents just another part of your pipeline.

Manage Agent State with Shell Commands

Treat your agent's memory like any other data source. The `get_thread_state` tool returns a JSON object that you can parse and inspect with `jq`. It's completely scriptable. If you spot an error, craft a new JSON payload and pipe it to `update_thread_state` to fix it on the fly. You can use `list_threads` and `list_runs` to get a machine-readable view of your entire agent fleet's activity.

Automate Monitoring and Cleanup

Run this MCP Server in a cron job to keep your LangGraph instance healthy. A simple shell script can call `list_runs` to find stalled executions, then use `cancel_run` to terminate them. This stops them from wasting money. Another script could periodically call `list_crons` to verify that all your scheduled agent tasks are correctly configured. It's practical, backend-focused system administration for your agents.

Setup guide

Set up LangGraph Cloud (Stateful AI Agents) MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see langgraph-cloud-stateful-ai-agents-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest LangGraph Cloud (Stateful AI Agents) transactions." It will automatically discover and invoke the available LangGraph Cloud (Stateful AI Agents) tools.

Terminal

claude mcp add --transport http langgraph-cloud-stateful-ai-agents-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
2

Add the LangGraph Cloud (Stateful AI Agents) MCP

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

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "langgraph-cloud-stateful-ai-agents-mcp": {
      "type": "url",
      "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 Code

You can pipe commands together. For instance, `claude mcp langgraph-cloud create_thread | jq -r '.id'` will give you a thread ID you can use in subsequent `create_run` calls within your script.

Yes. Use `claude mcp langgraph-cloud get_thread_state --thread_id ` to get the state, save it to a file, edit it, and then use `claude mcp langgraph-cloud update_thread_state --thread_id --state_graph @your_file.json` to push the fix.

Run `claude mcp add --transport http langgraph-cloud-mcp -- `. Use `claude mcp list` to confirm it was added correctly. Your configuration is saved in `~/.claude.json`.

You can script it. Use `claude mcp langgraph-cloud list_runs` and parse the output with `jq` to filter for runs that have been 'running' for too long. Then, pipe those run IDs to the `cancel_run` command.

Yes. This server only handles your LangGraph thread states, run metadata, and assistant configs. Your Claude Code client authenticates with a bearer token over a secure connection, and Vinkius processes the data in memory within an ephemeral container that is immediately discarded.

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