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

Q: How do I inspect active runs of LangGraph Cloud (Stateful AI Agents) inside Cursor?

Use listruns to see all current executions on a specific thread. You can then call getrun inside Cursor to inspect the step-by-step progress of that run.

Q: Can I modify my agent's memory using LangGraph Cloud (Stateful AI Agents) in Cursor?

Yes. You can fetch the state with getthreadstate and push manual overrides using updatethreadstate directly from your Cursor agent prompt.

Q: How do I select which agent graph to run with LangGraph Cloud (Stateful AI Agents) in Cursor?

Call listassistants to get a list of all deployed graph configurations. You can then copy the assistant ID directly into your code or Cursor run commands.

Q: What happens if my agent gets stuck in a loop during a Cursor session with this MCP Server?

You can stop it immediately. Use the cancelrun tool to interrupt and terminate the active graph execution.

Inject real-time agent state and graph execution data directly into your Cursor codebase.

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 Cursor

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Debug stateful agent threads directly in Cursor

The `get_thread_state` tool pulls the exact runtime variables of your stateful LangGraph agent right into your Cursor editor. You can inspect the current message array and state variables while writing your frontend or backend code in Cursor. If you're tracking state, you're tracking the truth. Running `update_thread_state` lets you mock or override state values directly from Cursor's agent mode. You can simulate edge cases, test error boundaries, and verify how your Cursor code handles state mutations. It allows you to verify LangGraph state changes without manually clicking through a separate web browser.

Trigger and monitor LangGraph Cloud runs in Cursor

The `create_run` tool starts an execution of your deployed LangGraph Cloud agent graph directly from the Cursor chat panel. You feed it local workspace files as input variables to test how your LangGraph code processes them. It makes local agent development in Cursor fast and iterative. Tracking active executions is handled by `get_run`, which displays the status of each LangGraph node as your Cursor editor compiles code. If your local changes cause an infinite loop in the graph, this MCP Server lets you call `cancel_run` directly from Cursor. You get immediate terminal-like control over active runs without leaving your Cursor project.

Manage conversation threads and crons from Cursor

The `create_thread` tool instantiates a brand new conversation state container on your remote LangGraph instance from Cursor. You can associate your Cursor project workspace with this thread over the MCP connection to keep your local testing organized. This ensures your Cursor development runs don't pollute production databases. Using `list_crons` helps you track scheduled background jobs that automate LangGraph Cloud agent runs directly from Cursor. You can see when the next execution is slated to happen, ensuring your Cursor code changes won't break automated production workflows. It keeps your IDE in sync with all scheduled LangGraph automation.

Setup guide

Set up LangGraph Cloud (Stateful AI Agents) MCP in Cursor

Prerequisites

Cursor installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP Settings

Go to Cursor Settings → MCP or open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and search for "MCP: Add Server".
2

Add the LangGraph Cloud (Stateful AI Agents) MCP

Cursor will create or open .cursor/mcp.json in your project root. Paste the JSON snippet on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Enable Agent mode

Open Composer (Cmd+I / Ctrl+I) and switch to Agent mode using the dropdown at the top. MCP tools are only available in Agent mode.
4

Verify the connection

Ask Cursor something like "List my recent LangGraph Cloud (Stateful AI Agents) transactions." If the MCP tools are loaded correctly, Cursor will call the LangGraph Cloud (Stateful AI Agents) tools automatically. You can also check Settings → MCP for a green status indicator.

.cursor/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 Cursor

Use `list_runs` to see all current executions on a specific thread. You can then call `get_run` inside Cursor to inspect the step-by-step progress of that run.

Yes. You can fetch the state with `get_thread_state` and push manual overrides using `update_thread_state` directly from your Cursor agent prompt.

Call `list_assistants` to get a list of all deployed graph configurations. You can then copy the assistant ID directly into your code or Cursor run commands.

You can stop it immediately. Use the `cancel_run` tool to interrupt and terminate the active graph execution.

Your thread states and API keys are stored locally or in Vinkius's encrypted credentials manager. They are transmitted directly to LangGraph Cloud via end-to-end TLS, keeping your data out of Cursor's indexers.

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