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

Q: How can two agents in CrewAI share information using LangGraph Cloud (Stateful AI Agents)?

They both work on the same thread. One agent uses createrun to add information to the thread's state. The second agent then uses getthreadstate to read that information before starting its own task.

Q: Can I create a 'manager' agent in CrewAI to approve the work of other agents?

Yes. The manager agent would use getthreadstate to review the work. If it's correct, the agent does nothing. If it's wrong, the agent uses updatethreadstate to post a correction or new instructions back into the shared thread.

Q: How do I start a new collaborative task for my crew with LangGraph Cloud (Stateful AI Agents) and CrewAI?

Your first step is to have an agent call createthread. This generates a unique ID for the new task. You then pass this thread ID to all agents assigned to the task so they know which shared memory to work from.

Q: How can I stop a CrewAI agent that's stuck in a loop?

You can build a monitor agent that uses listruns to find long-running executions. Once identified, that monitor agent can call cancelrun with the specific run ID to terminate the process and log an error.

Give your CrewAI team a shared brain. This server provides the persistent memory for agents to collaborate on tasks.

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 CrewAI

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

A Shared Whiteboard for Your Crew

Your agents need a place to coordinate. Use `create_thread` to give your crew a dedicated space for a new project or task. This thread is their shared memory, accessible to every agent in the crew. Any agent can read the entire history and current state of the project with `get_thread_state`. This stops agents from stepping on each other's toes and allows one agent to pick up exactly where another left off.

Coordinate and Review Agent Actions

Collaboration requires rules. A 'researcher' agent can use `create_run` to add findings to the thread. Then, a 'writer' agent can use `list_runs` to see that the research run is complete before starting its own work. This creates a clear, auditable chain of events. You can see which agent performed which run and what the outcome was. It’s how you build complex, multi-step operations with specialized agents working in sequence.

Build Supervisor Agents with this MCP Server

A crew needs a manager. You can design a 'supervisor' agent that monitors the crew's work. It can use `list_threads` to watch all active projects and `get_thread_state` to inspect progress. If the supervisor spots an error, it can step in. It can use `update_thread_state` to correct the project's direction or use `cancel_run` to stop a junior agent that's going down the wrong path. This is how you build truly autonomous, self-correcting teams.

Setup guide

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

Prerequisites

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

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke LangGraph Cloud (Stateful AI Agents) tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="LangGraph Cloud (Stateful AI Agents) Analyst",
    goal="Access and analyze LangGraph Cloud (Stateful AI Agents) data via MCP.",
    backstory="Expert analyst with direct LangGraph Cloud (Stateful AI Agents) access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent LangGraph Cloud (Stateful AI Agents) transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="LangGraph Cloud (Stateful AI Agents) Analyst",
        goal="Access and analyze LangGraph Cloud (Stateful AI Agents) data via MCP.",
        backstory="Expert analyst with direct LangGraph Cloud (Stateful AI Agents) access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent LangGraph Cloud (Stateful AI Agents) transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

They both work on the same thread. One agent uses `create_run` to add information to the thread's state. The second agent then uses `get_thread_state` to read that information before starting its own task.

Yes. The manager agent would use `get_thread_state` to review the work. If it's correct, the agent does nothing. If it's wrong, the agent uses `update_thread_state` to post a correction or new instructions back into the shared thread.

Your first step is to have an agent call `create_thread`. This generates a unique ID for the new task. You then pass this thread ID to all agents assigned to the task so they know which shared memory to work from.

You can build a monitor agent that uses `list_runs` to find long-running executions. Once identified, that monitor agent can call `cancel_run` with the specific run ID to terminate the process and log an error.

Your LangGraph conversational state—the messages and variables within a thread—is the only data this server touches. Access is controlled by your unique endpoint token. Each MCP server is ephemeral and runs in a zero-trust environment, ensuring your crew's work stays private.

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