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

Q: Can LangChain track the individual runs inside LangGraph Cloud (Stateful AI Agents)?

Yes. Your agent calls listruns to pull execution history for any specific thread. You map those results directly into your LangSmith tracing dashboard.

Q: How do I stop a runaway graph execution?

Send a request through the cancelrun tool. This interrupts the ongoing process before it burns through your token budget.

Q: Does LangGraph Cloud (Stateful AI Agents) support human approval workflows in LangChain?

You handle approvals by reading the current graph with getthreadstate. Once the human operator approves or edits the payload, you push the changes back using updatethreadstate.

Build stateful multi-step reasoning pipelines using LangChain and LangGraph Cloud agents.

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 LangChain

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stateful Context Tracking

This MCP server provides the `create_thread` tool to initialize isolated memory spaces for your LangChain agents. When building complex ReAct loops, you need persistent context between steps. Calling `list_threads` shows you every active conversation happening across your infrastructure. Your chains can inspect the exact variables inside those conversations using `get_thread_state`. Passing that state directly into LangSmith gives you full observability over what the graph actually did.

Remote Graph Execution via MCP Server

Triggering remote endpoints requires the `create_run` tool to send input payloads to a specific thread. Your LangChain agent decides which assistant config to target after pulling the options via `list_assistants`. It fires off the request and moves to the next step in your pipeline. Long-running tasks demand supervision. You poll `get_run` to check completion status while the rest of your chain continues working. If a step takes too long or hits a rate limit, the agent fires `cancel_run` to kill the process and try another path.

Human-in-the-Loop Interventions

Sometimes an agent gets stuck in a loop and needs a human to fix the trajectory. The `update_thread_state` tool writes manual overrides directly into the graph variables. Your LangChain pipeline pauses, waits for a user decision, and injects the corrected state back into the remote server. Scheduled workflows also need visibility. Running `list_crons` pulls down all active automated jobs targeting your agents through this MCP connection. You combine this with `list_runs` to audit exactly what your scheduled tasks accomplished overnight.

Setup guide

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

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes LangGraph Cloud (Stateful AI Agents) tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "langgraph-cloud-stateful-ai-agents-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent LangGraph Cloud (Stateful AI Agents) transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

Use the langchain-mcp-adapters package. You instantiate a MultiServerMCPClient pointing to the Vinkius endpoint and pass the returned tools to your agent.

Yes. Your agent calls `list_runs` to pull execution history for any specific thread. You map those results directly into your LangSmith tracing dashboard.

Send a request through the `cancel_run` tool. This interrupts the ongoing process before it burns through your token budget.

You handle approvals by reading the current graph with `get_thread_state`. Once the human operator approves or edits the payload, you push the changes back using `update_thread_state`.

This server processes conversation history arrays and input payloads. Vinkius runs the connection inside a V8 Isolate Sandbox that destroys itself after the session ends. Your connection token is the only credential passed, and no state data persists on the middleware layer.

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