How to integrate Grafbase MCP with Claude Agent SDK

BOOK A CALLGET STARTED FOR FREE
Framework Integration Gradient
Grafbase Logo
Claude Agent SDK Logo
divider

Introduction

This guide walks you through connecting Grafbase to the Claude Agent SDK using the Composio tool router. By the end, you'll have a working Grafbase agent that can retrieve the latest audit log entry, delete a specific api key by id, get the current federated graph schema, enable the mcp server for my project through natural language commands.

This guide will help you understand how to give your Claude Agent SDK agent real control over a Grafbase account through Composio's Grafbase 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 and set up your Claude/Anthropic and Composio API keys
  • Install the necessary dependencies
  • Initialize Composio and create a Tool Router session for Grafbase
  • Configure an AI agent that can use Grafbase as a tool
  • Run a live chat session where you can ask the agent to perform Grafbase operations

What is Claude Agent SDK?

The Claude Agent SDK is Anthropic's official framework for building AI agents powered by Claude. It provides a streamlined interface for creating agents with MCP tool support and conversation management.

Key features include:

  • Native MCP Support: Built-in support for Model Context Protocol servers
  • Permission Modes: Control tool execution permissions
  • Streaming Responses: Real-time response streaming for interactive applications
  • Context Manager: Clean async context management for sessions

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

The Grafbase MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, and more directly to your Grafbase account. It provides structured and secure access to your GraphQL API management, so your agent can perform actions like enabling or disabling MCP, managing API keys, retrieving schemas, and working with audit logs on your behalf.

  • Enable or disable MCP server: Instantly activate or turn off the Model Context Protocol for your Grafbase project, all by agent command.
  • API key management: Let your agent securely delete existing API keys to control and rotate access as needed.
  • Schema and federation management: Retrieve federated graph schemas or remove unwanted schemas for streamlined development workflows.
  • Audit log retrieval: Fetch specific audit log entries, giving your agent the power to surface key changes or events in your Grafbase environment.
  • Extension and server configuration cleanup: Delete extension configurations or obsolete MCP server setups to keep your backend lean and secure.

Supported Tools & Triggers

Tools
Delete Grafbase API KeyTool to delete an existing API key.
Delete Grafbase Audit LogTool to delete a specific Grafbase audit log entry.
Delete ExtensionTool to delete an extension configuration.
Delete MCP ServerTool to delete a Grafbase MCP server configuration by its unique ID.
Delete Grafbase SchemaTool to delete a Grafbase schema.
Delete Schema CheckTool to delete a Grafbase schema check.
Disable MCP serverTool to disable the Model Context Protocol server.
Enable Grafbase MCP ServerTool to enable the Model Context Protocol (MCP) server for a Grafbase project.
Get Grafbase Audit LogTool to retrieve a specific Grafbase audit log entry.
Get Federated SchemaTool to retrieve the composed federated graph schema.
Get Grafbase Schema CheckTool to retrieve the result of a schema check by its ID.
Get Subgraph SchemaTool to retrieve the GraphQL SDL of a specific subgraph.
List API KeysTool to list all API keys for a project.
List Grafbase Audit LogsTool to list all audit logs for a project.
List ExtensionsTool to list all extensions configured for a Grafbase project.
List MCP ServersTool to list all MCP servers configured for a project.
List Grafbase Schema ChecksTool to list all Grafbase schema checks for a project.
List Grafbase SchemasTool to list all Grafbase schemas.
List Grafbase SubgraphsTool to list published subgraphs in a branch.

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:
  • Composio API Key and Claude/Anthropic API Key
  • Primary know-how of Claude Agents SDK
  • A Grafbase account
  • Some knowledge of Python

Getting API Keys for Claude/Anthropic and Composio

Claude/Anthropic API Key
  • Go to the Anthropic Console and create an API key. You'll need credits to use the models.
  • Keep the API key safe.
Composio API Key
  • Log in to the Composio dashboard.
  • Navigate to your API settings and generate a new API key.
  • Store this key securely as you'll need it for authentication.

Install dependencies

pip install composio-anthropic claude-agent-sdk python-dotenv

Install the Composio SDK and the Claude Agents SDK.

What's happening:

  • composio-anthropic provides Composio integration for Anthropic
  • claude-agent-sdk is the core agent framework
  • python-dotenv loads environment variables

Set up environment variables

bash
COMPOSIO_API_KEY=your_composio_api_key_here
USER_ID=your_user_id_here
ANTHROPIC_API_KEY=your_anthropic_api_key_here

Create a .env file in your project root.

What's happening:

  • COMPOSIO_API_KEY authenticates with Composio
  • USER_ID identifies the user for session management
  • ANTHROPIC_API_KEY authenticates with Anthropic/Claude

Import dependencies

import asyncio
from claude_agent_sdk import ClaudeSDKClient, ClaudeAgentOptions
import os
from composio import Composio
from dotenv import load_dotenv

load_dotenv()
What's happening:
  • We're importing all necessary libraries including the Claude Agent SDK and Composio
  • The load_dotenv() function loads environment variables from your .env file
  • This setup prepares the foundation for connecting Claude with Grafbase functionality

Create a Composio instance and Tool Router session

async def chat_with_remote_mcp():
    api_key = os.getenv("COMPOSIO_API_KEY")
    if not api_key:
        raise RuntimeError("COMPOSIO_API_KEY is not set")

    composio = Composio(api_key=api_key)

    # Create Tool Router session for Grafbase
    mcp_server = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["grafbase"]
    )

    url = mcp_server.mcp.url

    if not url:
        raise ValueError("Session URL not found")
What's happening:
  • The function checks for the required COMPOSIO_API_KEY environment variable
  • We're creating a Composio instance using our API key
  • The create method creates a Tool Router session for Grafbase
  • The returned url is the MCP server URL that your agent will use

Configure Claude Agent with MCP

# Configure remote MCP server for Claude
options = ClaudeAgentOptions(
    permission_mode="bypassPermissions",
    mcp_servers={
        "composio": {
            "type": "http",
            "url": url,
            "headers": {
                "x-api-key": os.getenv("COMPOSIO_API_KEY")
            }
        }
    },
    system_prompt="You are a helpful assistant with access to Grafbase tools via Composio.",
    max_turns=10
)
What's happening:
  • We're configuring the Claude Agent options with the MCP server URL
  • permission_mode="bypassPermissions" allows the agent to execute operations without asking for permission each time
  • The system prompt instructs the agent that it has access to Grafbase
  • max_turns=10 limits the conversation length to prevent excessive API usage

Create client and start chat loop

# Create client with context manager
async with ClaudeSDKClient(options=options) as client:
    print("\nChat started. Type 'exit' or 'quit' to end.\n")

    # Main chat loop
    while True:
        user_input = input("You: ").strip()
        if user_input.lower() in {"exit", "quit"}:
            print("Goodbye!")
            break

        # Send query
        await client.query(user_input)

        # Receive and print response
        print("Claude: ", end="", flush=True)
        async for message in client.receive_response():
            if hasattr(message, "content"):
                for block in message.content:
                    if hasattr(block, "text"):
                        print(block.text, end="", flush=True)
        print()
What's happening:
  • The Claude SDK client is created using the async context manager pattern
  • The agent processes each query and streams the response back in real-time
  • The chat loop continues until the user types 'exit' or 'quit'

Run the application

if __name__ == "__main__":
    asyncio.run(chat_with_remote_mcp())
What's happening:
  • This entry point runs the async chat_with_remote_mcp() function using asyncio.run()
  • The application will start, create the MCP connection, and begin the interactive chat session

Complete Code

Here's the complete code to get you started with Grafbase and Claude Agent SDK:

import asyncio
from claude_agent_sdk import ClaudeSDKClient, ClaudeAgentOptions
import os
from composio import Composio
from dotenv import load_dotenv

load_dotenv()

async def chat_with_remote_mcp():
    api_key = os.getenv("COMPOSIO_API_KEY")
    if not api_key:
        raise RuntimeError("COMPOSIO_API_KEY is not set")

    composio = Composio(api_key=api_key)

    # Create Tool Router session for Grafbase
    mcp_server = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["grafbase"]
    )

    url = mcp_server.mcp.url

    if not url:
        raise ValueError("Session URL not found")

    # Configure remote MCP server for Claude
    options = ClaudeAgentOptions(
        permission_mode="bypassPermissions",
        mcp_servers={
            "composio": {
                "type": "http",
                "url": url,
                "headers": {
                    "x-api-key": os.getenv("COMPOSIO_API_KEY")
                }
            }
        },
        system_prompt="You are a helpful assistant with access to Grafbase tools via Composio.",
        max_turns=10
    )

    # Create client with context manager
    async with ClaudeSDKClient(options=options) as client:
        print("\nChat started. Type 'exit' or 'quit' to end.\n")

        # Main chat loop
        while True:
            user_input = input("You: ").strip()
            if user_input.lower() in {"exit", "quit"}:
                print("Goodbye!")
                break

            # Send query
            await client.query(user_input)

            # Receive and print response
            print("Claude: ", end="", flush=True)
            async for message in client.receive_response():
                if hasattr(message, "content"):
                    for block in message.content:
                        if hasattr(block, "text"):
                            print(block.text, end="", flush=True)
            print()

if __name__ == "__main__":
    asyncio.run(chat_with_remote_mcp())

Conclusion

You've successfully built a Claude Agent SDK agent that can interact with Grafbase through Composio's Tool Router.

Key features:

  • Native MCP support through Claude's agent framework
  • Streaming responses for real-time interaction
  • Permission bypass for smooth automated workflows
You can extend this by adding more toolkits, implementing custom business logic, or building a web interface around the agent.

How to build Grafbase MCP Agent with another framework

OpenAI Agents SDK

OpenAI Agents SDK

Use Grafbase MCP with OpenAI Agents SDK

Google ADK

Google ADK

Use Grafbase MCP with Google ADK

LangChain

LangChain

Use Grafbase MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Grafbase MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Grafbase MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Grafbase MCP with LlamaIndex

CrewAI

CrewAI

Use Grafbase MCP with CrewAI

FAQ

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

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

Can I use Tool Router MCP with Claude Agent SDK?

Yes, you can. Claude Agent SDK 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 Grafbase tools.

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

Yes, absolutely. You can configure which Grafbase 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 Grafbase 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