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

Q: How do I configure LangGraph Cloud (Stateful AI Agents) with Google ADK?

Install google-adk and set up an McpToolset using StreamableHttpServerParameters. Pass that toolset into your LlmAgent initialization. You can optionally filter the exposed tools using toolnames.

Q: Can Google ADK models read the full history from LangGraph Cloud (Stateful AI Agents)?

They can. Your agent calls getthreadstate to pull the complete array of messages and graph variables. Gemini's massive context window can easily ingest these heavy state payloads.

Q: How do I track scheduled agent runs in Google ADK?

You query the listcrons tool. It returns all active scheduled jobs automating your agent runs. You use this data to prevent triggering duplicate workflows.

Q: Does LangGraph Cloud (Stateful AI Agents) allow Google ADK to stop active runs?

Yes, your agent can issue a cancelrun command. This interrupts the ongoing graph execution instantly, saving compute resources if the user abandons the session.

Give your Google ADK agents access to LangGraph Cloud. Trigger runs, manage conversation threads, and monitor state transitions.

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 Google ADK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Execute Runs via Google ADK

The `create_run` tool kicks off an assistant on a specific thread so your long-context Gemini models can execute complex workflows. You hand over the initial payload, and LangGraph handles the multi-step execution. This keeps your application logic decoupled from the agent runtime. If you need to stop a runaway process, `cancel_run` halts it immediately. You can track everything currently executing on a thread by calling `list_runs`, keeping your Google Cloud logging accurate.

Manage Persistent Graph State

Using `create_thread`, your system establishes a dedicated bucket for conversational state that survives beyond a single session. Enterprise agents require persistent memory. You pull the exact current variables and message arrays using `get_thread_state` via the MCP Server. When you need to see all active conversations, `list_threads` returns the full directory. This lets your Gemini agent load massive historical contexts directly into its million-token window before making a decision.

Control Assistants and Crons

Your MCP toolset exposes every deployed graph configuration through the `list_assistants` tool. This means your agent can dynamically choose which specialized workflow to trigger based on the user's request. You avoid hardcoding assistant IDs in your source code. For automated tasks, `list_crons` shows you active scheduled jobs. If an agent makes a mistake, an operator can step in and use `update_thread_state` to overwrite the graph variables and course-correct the execution.

Setup guide

Set up LangGraph Cloud (Stateful AI Agents) MCP in Google ADK

Prerequisites

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

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with LangGraph Cloud (Stateful AI Agents) tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="LangGraph Cloud (Stateful AI Agents)_agent",
    model="gemini-2.0-flash",
    instruction="You have access to LangGraph Cloud (Stateful AI Agents) tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

Install `google-adk` and set up an `McpToolset` using `StreamableHttpServerParameters`. Pass that toolset into your `LlmAgent` initialization. You can optionally filter the exposed tools using `tool_names`.

They can. Your agent calls `get_thread_state` to pull the complete array of messages and graph variables. Gemini's massive context window can easily ingest these heavy state payloads.

You query the `list_crons` tool. It returns all active scheduled jobs automating your agent runs. You use this data to prevent triggering duplicate workflows.

Yes, your agent can issue a `cancel_run` command. This interrupts the ongoing graph execution instantly, saving compute resources if the user abandons the session.

The Vinkius architecture relies on ephemeral sandboxes and zero-trust principles. Your node variables, message arrays, and thread states stream directly to your GCP environment. The MCP server retains zero persistent data.

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