How to integrate Grafbase MCP with OpenAI Agents SDK

BOOK A CALLGET STARTED FOR FREE
Framework Integration Gradient
Grafbase Logo
open-ai-agents-sdk Logo
divider

Introduction

This guide walks you through connecting Grafbase to the OpenAI Agents 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 OpenAI Agents 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 OpenAI 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 open-ai-agents-sdk?

The OpenAI Agents SDK is a lightweight framework for building AI agents that can use tools and maintain conversation state. It provides a simple interface for creating agents with hosted MCP tool support.

Key features include:

  • Hosted MCP Tools: Connect to external services through hosted MCP endpoints
  • SQLite Sessions: Persist conversation history across interactions
  • Simple API: Clean interface with Agent, Runner, and tool configuration
  • Streaming Support: Real-time response streaming for interactive applications

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 OpenAI API Key
  • Primary know-how of OpenAI Agents SDK
  • A live Grafbase project
  • Some knowledge of Python or Typescript

Getting API Keys for OpenAI and Composio

OpenAI API Key
  • Go to the OpenAI dashboard and create an API key. You'll need credits to use the models, or you can connect to another model provider.
  • Keep the API key safe.
Composio API Key

Install dependencies

pip install composio_openai_agents openai-agents python-dotenv

Install the Composio SDK and the OpenAI Agents SDK.

Set up environment variables

bash
OPENAI_API_KEY=sk-...your-api-key
COMPOSIO_API_KEY=your-api-key
USER_ID=composio_user@gmail.com

Create a .env file and add your OpenAI and Composio API keys.

Import dependencies

import asyncio
import os
from dotenv import load_dotenv

from composio import Composio
from composio_openai_agents import OpenAIAgentsProvider
from agents import Agent, Runner, HostedMCPTool, SQLiteSession
What's happening:
  • You're importing all necessary libraries.
  • The Composio and OpenAIAgentsProvider classes are imported to connect your OpenAI agent to Composio tools like Grafbase.

Set up the Composio instance

load_dotenv()

api_key = os.getenv("COMPOSIO_API_KEY")
user_id = os.getenv("USER_ID")

if not api_key:
    raise RuntimeError("COMPOSIO_API_KEY is not set. Create a .env file with COMPOSIO_API_KEY=your_key")

# Initialize Composio
composio = Composio(api_key=api_key, provider=OpenAIAgentsProvider())
What's happening:
  • load_dotenv() loads your .env file so OPENAI_API_KEY and COMPOSIO_API_KEY are available as environment variables.
  • Creating a Composio instance using the API Key and OpenAIAgentsProvider class.

Create a Tool Router session

# Create a Grafbase Tool Router session
session = composio.create(
    user_id=user_id,
    toolkits=["grafbase"]
)

mcp_url = session.mcp.url

What is happening:

  • You give the Tool Router the user id and the toolkits you want available. Here, it is only grafbase.
  • The router checks the user's Grafbase connection and prepares the MCP endpoint.
  • The returned session.mcp.url is the MCP URL that your agent will use to access Grafbase.
  • This approach keeps things lightweight and lets the agent request Grafbase tools only when needed during the conversation.

Configure the agent

# Configure agent with MCP tool
agent = Agent(
    name="Assistant",
    model="gpt-5",
    instructions=(
        "You are a helpful assistant that can access Grafbase. "
        "Help users perform Grafbase operations through natural language."
    ),
    tools=[
        HostedMCPTool(
            tool_config={
                "type": "mcp",
                "server_label": "tool_router",
                "server_url": mcp_url,
                "headers": {"x-api-key": api_key},
                "require_approval": "never",
            }
        )
    ],
)
What's happening:
  • We're creating an Agent instance with a name, model (gpt-5), and clear instructions about its purpose.
  • The agent's instructions tell it that it can access Grafbase and help with queries, inserts, updates, authentication, and fetching database information.
  • The tools array includes a HostedMCPTool that connects to the MCP server URL we created earlier.
  • The headers dict includes the Composio API key for secure authentication with the MCP server.
  • require_approval: 'never' means the agent can execute Grafbase operations without asking for permission each time, making interactions smoother.

Start chat loop and handle conversation

print("\nComposio Tool Router session created.")

chat_session = SQLiteSession("conversation_openai_toolrouter")

print("\nChat started. Type your requests below.")
print("Commands: 'exit', 'quit', or 'q' to end\n")

async def main():
    try:
        result = await Runner.run(
            agent,
            "What can you help me with?",
            session=chat_session
        )
        print(f"Assistant: {result.final_output}\n")
    except Exception as e:
        print(f"Error: {e}\n")

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

        result = await Runner.run(
            agent,
            user_input,
            session=chat_session
        )
        print(f"Assistant: {result.final_output}\n")

asyncio.run(main())
What's happening:
  • The program prints a session URL that you visit to authorize Grafbase.
  • After authorization, the chat begins.
  • Each message you type is processed by the agent using Runner.run().
  • The responses are printed to the console, and conversations are saved locally using SQLite.
  • Typing exit, quit, or q cleanly ends the chat.

Complete Code

Here's the complete code to get you started with Grafbase and open-ai-agents-sdk:

import asyncio
import os
from dotenv import load_dotenv

from composio import Composio
from composio_openai_agents import OpenAIAgentsProvider
from agents import Agent, Runner, HostedMCPTool, SQLiteSession

load_dotenv()

api_key = os.getenv("COMPOSIO_API_KEY")
user_id = os.getenv("USER_ID")

if not api_key:
    raise RuntimeError("COMPOSIO_API_KEY is not set. Create a .env file with COMPOSIO_API_KEY=your_key")

# Initialize Composio
composio = Composio(api_key=api_key, provider=OpenAIAgentsProvider())

# Create Tool Router session
session = composio.create(
    user_id=user_id,
    toolkits=["grafbase"]
)
mcp_url = session.mcp.url

# Configure agent with MCP tool
agent = Agent(
    name="Assistant",
    model="gpt-5",
    instructions=(
        "You are a helpful assistant that can access Grafbase. "
        "Help users perform Grafbase operations through natural language."
    ),
    tools=[
        HostedMCPTool(
            tool_config={
                "type": "mcp",
                "server_label": "tool_router",
                "server_url": mcp_url,
                "headers": {"x-api-key": api_key},
                "require_approval": "never",
            }
        )
    ],
)

print("\nComposio Tool Router session created.")

chat_session = SQLiteSession("conversation_openai_toolrouter")

print("\nChat started. Type your requests below.")
print("Commands: 'exit', 'quit', or 'q' to end\n")

async def main():
    try:
        result = await Runner.run(
            agent,
            "What can you help me with?",
            session=chat_session
        )
        print(f"Assistant: {result.final_output}\n")
    except Exception as e:
        print(f"Error: {e}\n")

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

        result = await Runner.run(
            agent,
            user_input,
            session=chat_session
        )
        print(f"Assistant: {result.final_output}\n")

asyncio.run(main())

Conclusion

This was a starter code for integrating Grafbase MCP with OpenAI Agents SDK to build a functional AI agent that can interact with Grafbase.

Key features:

  • Hosted MCP tool integration through Composio's Tool Router
  • SQLite session persistence for conversation history
  • Simple async chat loop for interactive testing
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

Claude Agent SDK

Claude Agent SDK

Use Grafbase MCP with Claude Agent 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 OpenAI Agents SDK?

Yes, you can. OpenAI Agents 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 callā†—Get started for free