How to integrate Griptape MCP with Autogen

BOOK A CALLGET STARTED FOR FREE
Framework Integration Gradient
Griptape Logo
AutoGen Logo
divider

Introduction

This guide walks you through connecting Griptape to AutoGen using the Composio tool router. By the end, you'll have a working Griptape agent that can create a new assistant named 'dochelper', list all assistants available in my workspace, start a run for assistant 'codegenpro' with input data, fetch logs from the latest assistant run through natural language commands.

This guide will help you understand how to give your AutoGen agent real control over a Griptape account through Composio's Griptape 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 required dependencies for Autogen and Composio
  • Initialize Composio and create a Tool Router session for Griptape
  • Wire that MCP URL into Autogen using McpWorkbench and StreamableHttpServerParams
  • Configure an Autogen AssistantAgent that can call Griptape tools
  • Run a live chat loop where you ask the agent to perform Griptape operations

What is AutoGen?

Autogen is a framework for building multi-agent conversational AI systems from Microsoft. It enables you to create agents that can collaborate, use tools, and maintain complex workflows.

Key features include:

  • Multi-Agent Systems: Build collaborative agent workflows
  • MCP Workbench: Native support for Model Context Protocol tools
  • Streaming HTTP: Connect to external services through streamable HTTP
  • AssistantAgent: Pre-built agent class for tool-using assistants

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

The Griptape MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Griptape account. It provides structured and secure access to your Griptape platform, so your agent can create assistants, launch and monitor AI runs, retrieve logs, and analyze results automatically on your behalf.

  • Automated assistant creation and management: Easily direct your agent to create new assistants or list existing ones, making it simple to manage your AI resources in Griptape Cloud.
  • Launching and controlling assistant runs: Let your agent start new assistant runs, cancel ongoing executions, or fetch the status of any run for streamlined AI workflow management.
  • Real-time monitoring of assistant activities: Have your agent stream live run events, monitor progress, or retrieve detailed logs to keep tabs on every step of your generative AI processes.
  • Error handling and diagnostics: Ask your agent to fetch detailed error reports for failed runs, helping you troubleshoot and resolve issues quickly and efficiently.
  • Result retrieval and historical analysis: Automatically pull final outputs from completed runs and review historical execution data, empowering you to analyze and improve your generative AI pipelines over time.

Supported Tools & Triggers

Tools
Assistant CreationTool to create a new assistant.
List AssistantsTool to list all assistants.
Cancel Assistant RunTool to cancel an ongoing assistant run.
Assistant Run CreationTool to initiate a new assistant run.
Get Assistant Run Error DetailsTool to fetch detailed error information for a specific assistant run.
Stream Assistant Run EventsTool to stream real-time events for a specific Assistant run.
List Assistant RunsTool to list all runs for a given assistant.
Assistant Run Logs RetrievalTool to retrieve logs generated during the execution of a specific assistant run.
Assistant Run Result RetrievalTool to fetch the final result of a completed assistant run.
Retrieve Assistant RunTool to retrieve an assistant run's status and details.
Retry Assistant RunTool to retry a previously failed assistant run.
Get Ruleset by AliasTool to retrieve a ruleset by its alias.
List Embedding DriversTool to list available embedding drivers.
Ruleset CreationTool to create a new ruleset.
Create ToolTool to create a new tool in Griptape Cloud.
Get Tool Deployment StatusTool to retrieve status of a specific tool deployment.
List ToolsTool to list all tools.

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

You will need:

  • A Composio API key
  • An OpenAI API key (used by Autogen's OpenAIChatCompletionClient)
  • A Griptape account you can connect to Composio
  • Some basic familiarity with Autogen and Python async

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
  • 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

bash
pip install composio python-dotenv
pip install autogen-agentchat autogen-ext-openai autogen-ext-tools

Install Composio, Autogen extensions, and dotenv.

What's happening:

  • composio connects your agent to Griptape via MCP
  • autogen-agentchat provides the AssistantAgent class
  • autogen-ext-openai provides the OpenAI model client
  • autogen-ext-tools provides MCP workbench support

Set up environment variables

bash
COMPOSIO_API_KEY=your-composio-api-key
OPENAI_API_KEY=your-openai-api-key
USER_ID=your-user-identifier@example.com

Create a .env file in your project folder.

What's happening:

  • COMPOSIO_API_KEY is required to talk to Composio
  • OPENAI_API_KEY is used by Autogen's OpenAI client
  • USER_ID is how Composio identifies which user's Griptape connections to use

Import dependencies and create Tool Router session

python
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio

from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient
from autogen_ext.tools.mcp import McpWorkbench, StreamableHttpServerParams

load_dotenv()

async def main():
    # Initialize Composio and create a Griptape session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["griptape"]
    )
    url = session.mcp.url
What's happening:
  • load_dotenv() reads your .env file
  • Composio(api_key=...) initializes the SDK
  • create(...) creates a Tool Router session that exposes Griptape tools
  • session.mcp.url is the MCP endpoint that Autogen will connect to

Configure MCP parameters for Autogen

python
# Configure MCP server parameters for Streamable HTTP
server_params = StreamableHttpServerParams(
    url=url,
    timeout=30.0,
    sse_read_timeout=300.0,
    terminate_on_close=True,
    headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")}
)

Autogen expects parameters describing how to talk to the MCP server. That is what StreamableHttpServerParams is for.

What's happening:

  • url points to the Tool Router MCP endpoint from Composio
  • timeout is the HTTP timeout for requests
  • sse_read_timeout controls how long to wait when streaming responses
  • terminate_on_close=True cleans up the MCP server process when the workbench is closed

Create the model client and agent

python
# Create model client
model_client = OpenAIChatCompletionClient(
    model="gpt-5",
    api_key=os.getenv("OPENAI_API_KEY")
)

# Use McpWorkbench as context manager
async with McpWorkbench(server_params) as workbench:
    # Create Griptape assistant agent with MCP tools
    agent = AssistantAgent(
        name="griptape_assistant",
        description="An AI assistant that helps with Griptape operations.",
        model_client=model_client,
        workbench=workbench,
        model_client_stream=True,
        max_tool_iterations=10
    )

What's happening:

  • OpenAIChatCompletionClient wraps the OpenAI model for Autogen
  • McpWorkbench connects the agent to the MCP tools
  • AssistantAgent is configured with the Griptape tools from the workbench

Run the interactive chat loop

python
print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
print("Ask any Griptape related question or task to the agent.\n")

# Conversation loop
while True:
    user_input = input("You: ").strip()

    if user_input.lower() in ["exit", "quit", "bye"]:
        print("\nGoodbye!")
        break

    if not user_input:
        continue

    print("\nAgent is thinking...\n")

    # Run the agent with streaming
    try:
        response_text = ""
        async for message in agent.run_stream(task=user_input):
            if hasattr(message, "content") and message.content:
                response_text = message.content

        # Print the final response
        if response_text:
            print(f"Agent: {response_text}\n")
        else:
            print("Agent: I encountered an issue processing your request.\n")

    except Exception as e:
        print(f"Agent: Sorry, I encountered an error: {str(e)}\n")
What's happening:
  • The script prompts you in a loop with You:
  • Autogen passes your input to the model, which decides which Griptape tools to call via MCP
  • agent.run_stream(...) yields streaming messages as the agent thinks and calls tools
  • Typing exit, quit, or bye ends the loop

Complete Code

Here's the complete code to get you started with Griptape and AutoGen:

import asyncio
import os
from dotenv import load_dotenv
from composio import Composio

from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient
from autogen_ext.tools.mcp import McpWorkbench, StreamableHttpServerParams

load_dotenv()

async def main():
    # Initialize Composio and create a Griptape session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["griptape"]
    )
    url = session.mcp.url

    # Configure MCP server parameters for Streamable HTTP
    server_params = StreamableHttpServerParams(
        url=url,
        timeout=30.0,
        sse_read_timeout=300.0,
        terminate_on_close=True,
        headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")}
    )

    # Create model client
    model_client = OpenAIChatCompletionClient(
        model="gpt-5",
        api_key=os.getenv("OPENAI_API_KEY")
    )

    # Use McpWorkbench as context manager
    async with McpWorkbench(server_params) as workbench:
        # Create Griptape assistant agent with MCP tools
        agent = AssistantAgent(
            name="griptape_assistant",
            description="An AI assistant that helps with Griptape operations.",
            model_client=model_client,
            workbench=workbench,
            model_client_stream=True,
            max_tool_iterations=10
        )

        print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
        print("Ask any Griptape related question or task to the agent.\n")

        # Conversation loop
        while True:
            user_input = input("You: ").strip()

            if user_input.lower() in ['exit', 'quit', 'bye']:
                print("\nGoodbye!")
                break

            if not user_input:
                continue

            print("\nAgent is thinking...\n")

            # Run the agent with streaming
            try:
                response_text = ""
                async for message in agent.run_stream(task=user_input):
                    if hasattr(message, 'content') and message.content:
                        response_text = message.content

                # Print the final response
                if response_text:
                    print(f"Agent: {response_text}\n")
                else:
                    print("Agent: I encountered an issue processing your request.\n")

            except Exception as e:
                print(f"Agent: Sorry, I encountered an error: {str(e)}\n")

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

Conclusion

You now have an Autogen assistant wired into Griptape through Composio's Tool Router and MCP. From here you can:
  • Add more toolkits to the toolkits list, for example notion or hubspot
  • Refine the agent description to point it at specific workflows
  • Wrap this script behind a UI, Slack bot, or internal tool
Once the pattern is clear for Griptape, you can reuse the same structure for other MCP-enabled apps with minimal code changes.

How to build Griptape MCP Agent with another framework

OpenAI Agents SDK

OpenAI Agents SDK

Use Griptape MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Griptape MCP with Claude Agent SDK

Google ADK

Google ADK

Use Griptape MCP with Google ADK

LangChain

LangChain

Use Griptape MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Griptape MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Griptape MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Griptape MCP with LlamaIndex

CrewAI

CrewAI

Use Griptape MCP with CrewAI

FAQ

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

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

Can I use Tool Router MCP with Autogen?

Yes, you can. Autogen 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 Griptape tools.

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

Yes, absolutely. You can configure which Griptape 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 Griptape 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