> ## Documentation Index
> Fetch the complete documentation index at: https://mintlify.com/composiohq/composio/llms.txt
> Use this file to discover all available pages before exploring further.

# Python OpenAI Example

> Use Composio with OpenAI Agents in Python to create powerful AI assistants

This example demonstrates how to use Composio with OpenAI Agents framework in Python to create AI agents that can execute tools via MCP (Model Context Protocol).

## Overview

In this example, you'll learn how to:

* Create a Composio session with MCP server
* Integrate Composio with OpenAI Agents
* Use MCP for tool execution
* Build agents that can access external APIs

## Prerequisites

<Steps>
  <Step title="Install dependencies">
    ```bash theme={null}
    pip install composio openai-agents
    ```
  </Step>

  <Step title="Set up environment variables">
    Create a `.env` file with your API keys:

    ```bash theme={null}
    COMPOSIO_API_KEY=your_composio_api_key
    OPENAI_API_KEY=your_openai_api_key
    ```
  </Step>

  <Step title="Authenticate with Gmail">
    ```bash theme={null}
    composio add gmail
    ```
  </Step>
</Steps>

## Complete Example

```python theme={null}
from agents import Agent, HostedMCPTool, Runner
from composio import Composio

# Initialize Composio and create a session
composio = Composio()
session = composio.create(
    user_id="user_123",
)

print(session.mcp)

# Create MCP tool with Composio session
composio_mcp = HostedMCPTool(
    tool_config={
        "type": "mcp",
        "server_label": "tool_router",
        "server_url": session.mcp.url,
        "require_approval": "never",
        "headers": session.mcp.headers,
    }
)

# Create an agent with Composio tools
agent = Agent(
    name="My Agent",
    instructions="You are a helpful assistant that can use the tools provided to you.",
    tools=[composio_mcp],
)

# Run the agent
result = Runner.run_sync(
    starting_agent=agent,
    input="Find my last email and summarize it.",
)

print(result.final_output)
```

## How It Works

<Steps>
  <Step title="Create Composio Session">
    Initialize Composio and create a session for a specific user. This session provides an MCP server URL that the agent can connect to.

    ```python theme={null}
    composio = Composio()
    session = composio.create(user_id="user_123")
    ```
  </Step>

  <Step title="Configure MCP Tool">
    Create a `HostedMCPTool` that connects to Composio's MCP server. This tool gives the agent access to all Composio tools.

    ```python theme={null}
    composio_mcp = HostedMCPTool(
        tool_config={
            "type": "mcp",
            "server_url": session.mcp.url,
            "headers": session.mcp.headers,
        }
    )
    ```
  </Step>

  <Step title="Create Agent">
    Instantiate an OpenAI Agent with instructions and the MCP tool.
  </Step>

  <Step title="Run Agent">
    Use `Runner.run_sync()` to execute the agent with your input. The agent will automatically use the appropriate Composio tools to complete the task.
  </Step>
</Steps>

## What is MCP?

<Info>
  **Model Context Protocol (MCP)** is an open standard for connecting AI models to external tools and data sources. Composio provides an MCP server that exposes all your connected tools through a standardized interface.
</Info>

## Session Configuration

The `session.mcp` object contains:

<ResponseField name="url" type="string">
  The MCP server URL for this session
</ResponseField>

<ResponseField name="headers" type="dict">
  Authentication headers for the MCP server
</ResponseField>

## Expected Output

```bash theme={null}
MCPSession(
  url='https://mcp.composio.dev/v1/session/abc123',
  headers={'Authorization': 'Bearer ...'}
)

Summarizing your last email:

From: john@example.com
Subject: Project Update
Received: 2 hours ago

Summary: John provided an update on the Q1 project timeline...
```

## Multi-User Support

Each user gets their own session with isolated credentials:

```python theme={null}
# Create sessions for different users
user1_session = composio.create(user_id="alice@company.com")
user2_session = composio.create(user_id="bob@company.com")

# Each session has different connected accounts
agent1 = Agent(
    name="Alice's Assistant",
    tools=[HostedMCPTool(tool_config={
        "server_url": user1_session.mcp.url,
        "headers": user1_session.mcp.headers,
    })],
)

agent2 = Agent(
    name="Bob's Assistant",
    tools=[HostedMCPTool(tool_config={
        "server_url": user2_session.mcp.url,
        "headers": user2_session.mcp.headers,
    })],
)
```

## Advanced Configuration

<CodeGroup>
  ```python Tool Approval theme={null}
  # Require approval for tool execution
  composio_mcp = HostedMCPTool(
      tool_config={
          "type": "mcp",
          "server_url": session.mcp.url,
          "require_approval": "always",  # or "never", "on_error"
          "headers": session.mcp.headers,
      }
  )
  ```

  ```python Async Execution theme={null}
  import asyncio

  async def main():
      result = await Runner.run(
          starting_agent=agent,
          input="Find my last email and summarize it.",
      )
      print(result.final_output)

  asyncio.run(main())
  ```
</CodeGroup>

## Available Tools

The agent automatically has access to all tools in the user's connected accounts:

* Gmail: Send/read emails, search, manage labels
* Slack: Send messages, create channels, manage users
* GitHub: Create issues, PRs, manage repositories
* Google Calendar: Create events, manage schedules
* And 200+ more integrations

## Best Practices

<Check>**User-Specific Sessions**: Always create separate sessions for different users to maintain data isolation</Check>

<Check>**Error Handling**: Wrap agent execution in try-catch blocks to handle authentication or API errors</Check>

<Check>**Clear Instructions**: Provide clear, specific instructions to help the agent choose the right tools</Check>

## Next Steps

<CardGroup cols={2}>
  <Card title="LangChain Example" icon="link" href="/examples/python/langchain">
    Use Composio with LangChain in Python
  </Card>

  <Card title="CrewAI Example" icon="users" href="/examples/python/crewai">
    Build multi-agent systems with CrewAI
  </Card>
</CardGroup>