How to integrate LLMWhisperer MCP with OpenAI Agents SDK

GET STARTED FOR FREE
Framework Integration Gradient
LLMWhisperer Logo
open-ai-agents-sdk Logo
divider

Introduction

This guide walks you through connecting LLMWhisperer to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working LLMWhisperer agent that can summarize main points from uploaded contract, extract key dates from legal document, classify sections of this technical report through natural language commands.

This guide will help you understand how to give your OpenAI Agents SDK agent real control over a LLMWhisperer account through Composio's LLMWhisperer 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 LLMWhisperer
  • Configure an AI agent that can use LLMWhisperer as a tool
  • Run a live chat session where you can ask the agent to perform LLMWhisperer 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 LLMWhisperer MCP server, and what's possible with it?

The LLMWhisperer MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your LLMWhisperer account. It provides structured and secure access so your agent can perform LLMWhisperer operations on your behalf.

Supported Tools & Triggers

Tools
Get Usage InformationTool to check usage metrics of your LLMWhisperer account.
Get Usage StatisticsTool to retrieve usage statistics for your LLMWhisperer account based on a specific tag.
Delete WebhookTool to delete a registered webhook from LLMWhisperer system.
Get Webhook DetailsTool to retrieve registered webhook details for LLMWhisperer.
Register WebhookTool to register a new webhook endpoint for LLMWhisperer async notifications.
Update Webhook ConfigurationTool to update an existing webhook configuration for document conversion callbacks.
Check Whisper StatusTool to check the status of a text extraction process in LLMWhisperer.
Convert Document to TextTool to convert PDFs and scanned documents into LLM-optimized text format asynchronously.
Get Whisper DetailTool to retrieve comprehensive details about ongoing or completed text extraction process.
Retrieve Whisper TextTool to retrieve extracted text from asynchronous whisper processing.

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 LLMWhisperer 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 LLMWhisperer.

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 LLMWhisperer Tool Router session
session = composio.create(
    user_id=user_id,
    toolkits=["llmwhisperer"]
)

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 llmwhisperer.
  • The router checks the user's LLMWhisperer connection and prepares the MCP endpoint.
  • The returned session.mcp.url is the MCP URL that your agent will use to access LLMWhisperer.
  • This approach keeps things lightweight and lets the agent request LLMWhisperer 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 LLMWhisperer. "
        "Help users perform LLMWhisperer 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 LLMWhisperer 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 LLMWhisperer 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 LLMWhisperer.
  • 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 LLMWhisperer 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=["llmwhisperer"]
)
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 LLMWhisperer. "
        "Help users perform LLMWhisperer 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 LLMWhisperer MCP with OpenAI Agents SDK to build a functional AI agent that can interact with LLMWhisperer.

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 LLMWhisperer MCP Agent with another framework

Claude Agent SDK

Claude Agent SDK

Use LLMWhisperer MCP with Claude Agent SDK

Google ADK

Google ADK

Use LLMWhisperer MCP with Google ADK

LangChain

LangChain

Use LLMWhisperer MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use LLMWhisperer MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use LLMWhisperer MCP with Mastra AI

LlamaIndex

LlamaIndex

Use LLMWhisperer MCP with LlamaIndex

CrewAI

CrewAI

Use LLMWhisperer MCP with CrewAI

Claude Code

Claude Code

Use LLMWhisperer MCP with Claude Code

Codex

Codex

Use LLMWhisperer MCP with Codex

FAQ

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

With a standalone LLMWhisperer MCP server, the agents and LLMs can only access a fixed set of LLMWhisperer tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from LLMWhisperer 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 LLMWhisperer tools.

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

Yes, absolutely. You can configure which LLMWhisperer 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 LLMWhisperer data and credentials are handled as safely as possible.

Used by agents from

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