How to integrate Langbase MCP with Google ADK

BOOK A CALLGET STARTED FOR FREE
Framework Integration Gradient
Langbase Logo
Google ADK Logo
divider

Introduction

This guide walks you through connecting Langbase to Google ADK using the Composio tool router. By the end, you'll have a working Langbase agent that can chunk a long document for semantic search, list all conversation threads for this agent, create a new memory for session data, show messages from a specific thread today through natural language commands.

This guide will help you understand how to give your Google ADK agent real control over a Langbase account through Composio's Langbase MCP server.

Before we dive in, let's take a quick look at the key ideas and tools involved.

TL;DR

Here's what you'll learn:
  • Get a Langbase account set up and connected to Composio
  • Install the Google ADK and Composio packages
  • Create a Composio Tool Router session for Langbase
  • Build an agent that connects to Langbase through MCP
  • Interact with Langbase using natural language

What is Google ADK?

Google ADK (Agents Development Kit) is Google's framework for building AI agents powered by Gemini models. It provides tools for creating agents that can use external services through the Model Context Protocol.

Key features include:

  • Gemini Integration: Native support for Google's Gemini models
  • MCP Toolset: Built-in support for Model Context Protocol tools
  • Streamable HTTP: Connect to external services through streamable HTTP
  • CLI and Web UI: Run agents via command line or web interface

What is the Langbase MCP server, and what's possible with it?

The Langbase MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Langbase account. It provides structured and secure access to your Langbase projects, letting your agent split content, manage memories, orchestrate threads, and build complex AI data flows on your behalf.

  • Content chunking and processing: Automatically split large documents or text into manageable chunks for downstream processing and efficient AI handling.
  • Memory management: Create, list, or delete memory objects so your agent can organize and retrieve contextual information as needed.
  • Conversation thread orchestration: Start new conversation threads, fetch thread details, or list messages—making it easy for your agent to manage dialogue history and context.
  • Pipe creation and listing: Let your agent create new processing pipes or retrieve all existing pipes, enabling seamless orchestration of data and AI workflows.
  • Document and data retrieval: List all documents stored in a memory, giving your agent access to relevant information and knowledge for any task.

Supported Tools & Triggers

Tools
Split Content into ChunksTool to split content into smaller chunks.
Create ThreadTool to create a new conversation thread.
List Documents in MemoryTool to list documents in a specific memory.
Get Thread DetailsTool to retrieve details of a specific conversation thread.
List Thread MessagesTool to list all messages in a conversation thread.
Create MemoryTool to create a new memory.
Delete MemoryTool to delete a specific memory.
List MemoriesTool to list all memory objects.
Create a new pipeTool to create a new pipe.
List all pipesTool to list all pipes.

What is the Composio tool router, and how does it fit here?

What is Tool Router?

Composio's Tool Router helps agents find the right tools for a task at runtime. You can plug in multiple toolkits (like Gmail, HubSpot, and GitHub), and the agent will identify the relevant app and action to complete multi-step workflows. This can reduce token usage and improve the reliability of tool calls. Read more here: Getting started with Tool Router

The tool router generates a secure MCP URL that your agents can access to perform actions.

How the Tool Router works

The Tool Router follows a three-phase workflow:

  1. Discovery: Searches for tools matching your task and returns relevant toolkits with their details.
  2. Authentication: Checks for active connections. If missing, creates an auth config and returns a connection URL via Auth Link.
  3. Execution: Executes the action using the authenticated connection.

Step-by-step Guide

Prerequisites

Before starting, make sure you have:
  • A Google API key for Gemini models
  • A Composio account and API key
  • Python 3.9 or later installed
  • Basic familiarity with Python

Getting API Keys for Google and Composio

Google API Key
  • Go to Google AI Studio and create an API key.
  • Copy the key and keep it safe. You will put this in GOOGLE_API_KEY.
Composio API Key and User ID
  • Log in to the Composio dashboard.
  • Go to Settings → API Keys and copy your Composio API key. Use this for COMPOSIO_API_KEY.
  • Decide on a stable user identifier to scope sessions, often your email or a user ID. Use this for COMPOSIO_USER_ID.

Install dependencies

bash
pip install google-adk composio-google python-dotenv

Inside your virtual environment, install the required packages.

What's happening:

  • google-adk is Google's Agents Development Kit
  • composio connects your agent to Langbase via MCP
  • composio-google provides the Google ADK provider
  • python-dotenv loads environment variables

Set up ADK project

bash
adk create my_agent

Set up a new Google ADK project.

What's happening:

  • This creates an agent folder with a root agent file and .env file

Set environment variables

bash
GOOGLE_API_KEY=your-google-api-key
COMPOSIO_API_KEY=your-composio-api-key
COMPOSIO_USER_ID=your-user-id-or-email

Save all your credentials in the .env file.

What's happening:

  • GOOGLE_API_KEY authenticates with Google's Gemini models
  • COMPOSIO_API_KEY authenticates with Composio
  • COMPOSIO_USER_ID identifies the user for session management

Import modules and validate environment

python
import os
import warnings

from composio import Composio
from composio_google import GoogleProvider
from dotenv import load_dotenv
from google.adk.agents.llm_agent import Agent
from google.adk.tools.mcp_tool.mcp_session_manager import StreamableHTTPConnectionParams
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset

load_dotenv()

warnings.filterwarnings("ignore", message=".*BaseAuthenticatedTool.*")

GOOGLE_API_KEY = os.getenv("GOOGLE_API_KEY")
COMPOSIO_API_KEY = os.getenv("COMPOSIO_API_KEY")
COMPOSIO_USER_ID = os.getenv("COMPOSIO_USER_ID")

if not GOOGLE_API_KEY:
    raise ValueError("GOOGLE_API_KEY is not set in the environment.")
if not COMPOSIO_API_KEY:
    raise ValueError("COMPOSIO_API_KEY is not set in the environment.")
if not COMPOSIO_USER_ID:
    raise ValueError("COMPOSIO_USER_ID is not set in the environment.")
What's happening:
  • os reads environment variables
  • Composio is the main Composio SDK client
  • GoogleProvider declares that you are using Google ADK as the agent runtime
  • Agent is the Google ADK LLM agent class
  • McpToolset lets the ADK agent call MCP tools over HTTP

Create Composio client and Tool Router session

python
print("Initializing Composio client...")
composio_client = Composio(api_key=COMPOSIO_API_KEY, provider=GoogleProvider())

print("Creating Composio session...")
composio_session = composio_client.create(
    user_id=COMPOSIO_USER_ID,
    toolkits=["langbase"],
)

COMPOSIO_MCP_URL = composio_session.mcp.url
print(f"Composio MCP HTTP URL: {COMPOSIO_MCP_URL}")
What's happening:
  • Authenticates to Composio with your API key
  • Declares Google ADK as the provider
  • Spins up a short-lived MCP endpoint for your user and selected toolkit
  • Stores the MCP HTTP URL for the ADK MCP integration

Set up the McpToolset and create the Agent

python
print("Creating Composio toolset for the agent...")
composio_toolset = McpToolset(
    connection_params=StreamableHTTPConnectionParams(
        url=COMPOSIO_MCP_URL,
        headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")}
    )
)

root_agent = Agent(
    model="gemini-2.5-pro",
    name="composio_agent",
    description="An agent that uses Langbase tools to perform actions.",
    instruction=(
        "You are a helpful assistant connected to Composio. "
        "You have the following tools available: "
        "COMPOSIO_SEARCH_TOOLS, COMPOSIO_MULTI_EXECUTE_TOOL, "
        "COMPOSIO_MANAGE_CONNECTIONS, COMPOSIO_REMOTE_BASH_TOOL, COMPOSIO_REMOTE_WORKBENCH. "
        "Use these tools to help users with Langbase operations."
    ),
    tools=[composio_toolset],
)

print("\nAgent setup complete. You can now run this agent directly ;)")
What's happening:
  • Connects the ADK agent to the Composio MCP endpoint through McpToolset
  • Uses Gemini as the model powering the agent
  • Lists exact tool names in instruction to reduce misnamed tool calls

Run the agent

bash
# Run in CLI mode
adk run my_agent

# Or run in web UI mode
adk web
Execute the agent from the project root. The web command opens a web portal where you can chat with the agent. What's happening:
  • adk run runs the agent in CLI mode
  • adk web opens a web UI for interactive testing

Complete Code

Here's the complete code to get you started with Langbase and Google ADK:

python
import os
import warnings

from composio import Composio
from composio_google import GoogleProvider
from dotenv import load_dotenv
from google.adk.agents.llm_agent import Agent
from google.adk.tools.mcp_tool.mcp_session_manager import StreamableHTTPConnectionParams
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset

def main():
    try:
        load_dotenv()

        warnings.filterwarnings("ignore", message=".*BaseAuthenticatedTool.*")

        GOOGLE_API_KEY = os.getenv("GOOGLE_API_KEY")
        COMPOSIO_API_KEY = os.getenv("COMPOSIO_API_KEY")
        COMPOSIO_USER_ID = os.getenv("COMPOSIO_USER_ID")

        if not GOOGLE_API_KEY:
            raise ValueError("GOOGLE_API_KEY is not set in the environment.")
        if not COMPOSIO_API_KEY:
            raise ValueError("COMPOSIO_API_KEY is not set in the environment.")
        if not COMPOSIO_USER_ID:
            raise ValueError("COMPOSIO_USER_ID is not set in the environment.")

        print("Initializing Composio client...")
        composio_client = Composio(api_key=COMPOSIO_API_KEY, provider=GoogleProvider())

        print("Creating Composio session...")
        composio_session = composio_client.create(
            user_id=COMPOSIO_USER_ID,
            toolkits=["langbase"],
        )

        COMPOSIO_MCP_URL = composio_session.mcp.url
        print(f"Composio MCP HTTP URL: {COMPOSIO_MCP_URL}")

        print("Creating Composio toolset for the agent...")
        composio_toolset = McpToolset(
            connection_params=StreamableHTTPConnectionParams(
                url=COMPOSIO_MCP_URL,
                headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")}
            )
        )

        root_agent = Agent(
            model="gemini-2.5-pro",
            name="composio_agent",
            description="An agent that uses Langbase tools to perform actions.",
            instruction=(
                "You are a helpful assistant connected to Composio. "
                "You have the following tools available: "
                "COMPOSIO_SEARCH_TOOLS, COMPOSIO_MULTI_EXECUTE_TOOL, "
                "COMPOSIO_MANAGE_CONNECTIONS, COMPOSIO_REMOTE_BASH_TOOL, COMPOSIO_REMOTE_WORKBENCH. "
                "Use these tools to help users with Langbase operations."
            ),
            tools=[composio_toolset],
        )

        print("\nAgent setup complete. You can now run this agent directly ;)")

    except Exception as e:
        print(f"\nAn error occurred during agent setup: {e}")

if __name__ == "__main__":
    main()

Conclusion

You've successfully integrated Langbase with the Google ADK through Composio's MCP Tool Router. Your agent can now interact with Langbase using natural language commands.

Key takeaways:

  • The Tool Router approach dynamically routes requests to the appropriate Langbase tools
  • Environment variables keep your credentials secure and separate from code
  • Clear agent instructions reduce tool calling errors
  • The ADK web UI provides an interactive interface for testing and development

You can extend this setup by adding more toolkits to the toolkits array in your session configuration.

How to build Langbase MCP Agent with another framework

OpenAI Agents SDK

OpenAI Agents SDK

Use Langbase MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Langbase MCP with Claude Agent SDK

LangChain

LangChain

Use Langbase MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Langbase MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Langbase MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Langbase MCP with LlamaIndex

CrewAI

CrewAI

Use Langbase MCP with CrewAI

FAQ

What are the differences in Tool Router MCP and Langbase MCP?

With a standalone Langbase MCP server, the agents and LLMs can only access a fixed set of Langbase tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Langbase and many other apps based on the task at hand, all through a single MCP endpoint.

Can I use Tool Router MCP with Google ADK?

Yes, you can. Google ADK fully supports MCP integration. You get structured tool calling, message history handling, and model orchestration while Tool Router takes care of discovering and serving the right Langbase tools.

Can I manage the permissions and scopes for Langbase while using Tool Router?

Yes, absolutely. You can configure which Langbase scopes and actions are allowed when connecting your account to Composio. You can also bring your own OAuth credentials or API configuration so you keep full control over what the agent can do.

How safe is my data with Composio Tool Router?

All sensitive data such as tokens, keys, and configuration is fully encrypted at rest and in transit. Composio is SOC 2 Type 2 compliant and follows strict security practices so your Langbase data and credentials are handled as safely as possible.

Used by agents from

Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai

Never worry about agent reliability

We handle tool reliability, observability, and security so you never have to second-guess an agent action.

Book a call↗Get started for free