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

Q: How do I connect LangGraph Cloud (Stateful AI Agents) to the OpenAI Agents SDK?

Install openai-agents via pip. Create an MCPServerStreamableHttp instance with your endpoint URL and pass it in the mcpservers list when initializing your Agent. Set cacheToolsList=True to speed up tool discovery.

Q: Can my OpenAI agent manually fix a broken conversation state?

Yes. The updatethreadstate tool lets your agent inject corrections directly into the graph variables. This works perfectly for human-in-the-loop review steps.

Q: How does LangGraph Cloud (Stateful AI Agents) handle hanging processes in the OpenAI Agents SDK?

You kill them directly. The cancelrun tool interrupts any ongoing graph execution. Your agent can monitor status via getrun and terminate it if it breaches your latency threshold.

Q: Does the OpenAI Agents SDK support fetching deployed LangGraph assistants?

It does. By calling listassistants through the MCP Server, your code retrieves every deployed graph configuration. You can then route specific tasks to the right assistant dynamically.

Connect LangGraph Cloud to your OpenAI Agents SDK system. Run stateful graphs, track threads, and handle human overrides in production.

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 OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Thread Tracking for OpenAI Agents

The `create_thread` tool spins up a dedicated LangGraph container for your agent's conversation state. Once it exists, you query `list_threads` to map active users to their specific histories. Your agent needs memory that persists across sessions, and this handles the infrastructure. Pulling current context happens through `get_thread_state`. That hands your agent the exact state graph and variables, letting it pick up exactly where it left off yesterday. Vinkius handles the underlying MCP Server connections so your code stays clean.

Trigger and Monitor Runs

Firing off an agent workflow requires the `create_run` tool to pass an input payload to a specific thread. LangGraph takes over the execution from there. If a process hangs or hits a timeout, your system can step in and hit `cancel_run` to kill it immediately. Monitoring progress relies on `get_run` and `list_runs`. The OpenAI dashboard will trace your initial call, while these tools fetch the step-by-step status directly from the graph engine. You get complete visibility into the execution pipeline.

Built-in Human Approvals

The `update_thread_state` tool comes into play when an agent gets stuck and needs a human to manually override the graph variables. It allows you to inject corrections before the run continues. This is mandatory for high-stakes actions requiring compliance sign-offs. You can also check what automated tasks are queued using `list_crons`. Combined with `list_assistants`, your setup knows exactly which deployed configurations are handling which scheduled workloads.

Setup guide

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

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all LangGraph Cloud (Stateful AI Agents) tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives LangGraph Cloud (Stateful AI Agents) tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate LangGraph Cloud (Stateful AI Agents) tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="LangGraph Cloud (Stateful AI Agents) Agent",
            instructions="You have access to LangGraph Cloud (Stateful AI Agents) tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Install `openai-agents` via pip. Create an `MCPServerStreamableHttp` instance with your endpoint URL and pass it in the `mcp_servers` list when initializing your Agent. Set `cacheToolsList=True` to speed up tool discovery.

Yes. The `update_thread_state` tool lets your agent inject corrections directly into the graph variables. This works perfectly for human-in-the-loop review steps.

You kill them directly. The `cancel_run` tool interrupts any ongoing graph execution. Your agent can monitor status via `get_run` and terminate it if it breaches your latency threshold.

It does. By calling `list_assistants` through the MCP Server, your code retrieves every deployed graph configuration. You can then route specific tasks to the right assistant dynamically.

Vinkius handles auth via a single endpoint token, running the MCP Server in an ephemeral V8 Isolate Sandbox. Your conversation history and graph state payloads pass straight from LangGraph to your client. We do not store your node variables or message arrays.

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