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

Q: How do I trigger a new agent execution using LangGraph Cloud (Stateful AI Agents) in VS Code Copilot?

Use createrun by specifying the target assistant ID and passing your input payload. You can find the available IDs by running listassistants first within VS Code Copilot.

Q: Can my team share thread states using LangGraph Cloud (Stateful AI Agents) in VS Code Copilot?

Yes. You can use listthreads to find shared development threads, and then inspect or modify them using getthreadstate and updatethreadstate in VS Code Copilot.

Q: What do I do if an automated cron job fails with LangGraph Cloud (Stateful AI Agents) in VS Code Copilot?

Run listcrons to check the schedule and status. If a run is stuck, you can fetch its details using getrun to pinpoint the failing node inside your VS Code Copilot environment.

Q: How do I stop a runaway agent execution from VS Code Copilot using this MCP Server?

Simply call the cancelrun tool with the active run ID. This immediately interrupts the execution on the LangGraph server and stops billing.

Manage stateful multi-agent workflows and human overrides directly inside VS Code Copilot.

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 VS Code Copilot

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Control team-wide agent runs in VS Code Copilot

The `create_run` tool executes stateful LangGraph Cloud graph runs directly from your VS Code Copilot chat window using this MCP Server. Your entire engineering team can trigger runs against the same deployed LangGraph assistants using shared VS Code workspace configurations. This keeps your testing environments consistent across the team inside VS Code Copilot. Monitoring active executions is straightforward with `get_run`, which reports the exact execution step to your VS Code Copilot chat. If a shared test run hangs, this MCP Server lets you invoke `cancel_run` to free up the thread for other developers in your workspace. It prevents orphaned runs from consuming your team's LangGraph Cloud budget.

Inspect and override graph states in VS Code Copilot

The `get_thread_state` tool fetches the raw state variables and conversation history of any active LangGraph Cloud session into VS Code Copilot. You can view these variables inline in VS Code Copilot, making it easy to debug complex state transitions. This reduces the time spent guessing why an agent chose a specific path in your VS Code workspace. Executing `update_thread_state` allows you to inject mock data or fix broken states during collaborative VS Code Copilot debugging sessions. You can correct conversational trajectories on the fly without having to restart the entire thread inside VS Code. It provides a clean way to manually override LangGraph state transitions.

Manage assistants and scheduled crons in VS Code Copilot

The `list_assistants` tool retrieves all active LangGraph Cloud graph deployments and displays them inside VS Code Copilot. You can quickly verify which version of your agent is deployed to the cloud before triggering test suites in VS Code. It ensures you are always testing against the correct graph configuration inside VS Code Copilot. Checking background automation is handled by `list_crons`, which lists all active scheduled runs inside VS Code Copilot. You can verify that your automated testing schedules are active and correctly configured directly from your VS Code editor. It brings full LangGraph Cloud visibility into your daily development environment.

Setup guide

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

Prerequisites

VS Code 1.99 or later with GitHub Copilot extension
Active Vinkius subscription with a valid endpoint token

1

Open MCP configuration

Open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and run "MCP: Add Server". Select HTTP (Streamable) as the server type. VS Code will create .vscode/mcp.json in your workspace.
2

Add the LangGraph Cloud (Stateful AI Agents) MCP

Paste the JSON snippet shown on the right into your .vscode/mcp.json. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Switch to Agent mode

Open Copilot Chat (Cmd+Shift+I / Ctrl+Shift+I) and switch to Agent mode using the dropdown. MCP tools are only available in Agent mode — they do not appear in Edit or Ask modes.
4

Verify the connection

In the Copilot Chat input, type # to list available tools. You should see the LangGraph Cloud (Stateful AI Agents) tools listed. Try asking: "List my recent LangGraph Cloud (Stateful AI Agents) transactions" and Copilot will invoke them automatically.

.vscode/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 VS Code Copilot

Use `create_run` by specifying the target assistant ID and passing your input payload. You can find the available IDs by running `list_assistants` first within VS Code Copilot.

Yes. You can use `list_threads` to find shared development threads, and then inspect or modify them using `get_thread_state` and `update_thread_state` in VS Code Copilot.

Run `list_crons` to check the schedule and status. If a run is stuck, you can fetch its details using `get_run` to pinpoint the failing node inside your VS Code Copilot environment.

Simply call the `cancel_run` tool with the active run ID. This immediately interrupts the execution on the LangGraph server and stops billing.

Your agent runs and graph states remain strictly within your LangGraph Cloud deployment. This MCP Server acts as a secure proxy, executing inside an isolated V8 sandbox with zero local data retention.

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