How to integrate Griptape MCP with Autogen

Trusted by
AWS
Glean
Zoom
Airtable

30 min · no commitment · see it on your stack

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 your workspace, start a run for assistant 'codegenpro' with input data 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.

Also integrate Griptape with

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 CreationCreates a new assistant run to execute a conversation turn with a Griptape Cloud assistant.
Get Assistant Run Error DetailsTool to fetch detailed error information for a specific assistant run.
List Assistant RunsTool to list all runs for a given assistant.
Assistant Run Logs RetrievalRetrieve the complete execution logs for an assistant run in Griptape Cloud.
Retrieve Assistant RunTool to retrieve an assistant run's status and details.
Retry Assistant RunTool to attempt retrying a failed assistant run.
Cancel Data JobTool to cancel a running or queued data job.
Create BucketTool to create a new bucket in Griptape Cloud.
Create Bucket AssetTool to create a new asset in a Griptape Cloud bucket.
Create Data ConnectorTool to create a new data connector in Griptape Cloud.
Create Data Connector JobTool to create a data job for a data connector in Griptape Cloud.
Create Export JobTool to create a new export job in Griptape Cloud.
Create FunctionTool to create a new function in Griptape Cloud.
Create Function DeploymentTool to create a new deployment for a function from a code source.
Create Import JobTool to create a new import job in Griptape Cloud.
Create IntegrationTool to create a new integration in Griptape Cloud.
Create Knowledge BaseTool to create a new knowledge base in Griptape Cloud.
Create Knowledge Base JobTool to create a knowledge base job for ingesting data into a knowledge base.
Create LibraryTool to create a new library in Griptape Cloud.
Create Model ConfigurationTool to create a new model configuration in Griptape Cloud.
Create Model Auth ConfigTool to create a model authentication configuration in Griptape Cloud.
Create Organization API KeyTool to create a new API key for a specific organization.
Create RetrieverTool to create a new retriever in Griptape Cloud.
Create RuleTool to create a new rule in Griptape Cloud.
Create SecretTool to create a new secret in Griptape Cloud.
Create StructureTool to create a new structure in Griptape Cloud.
Create Structure DeploymentTool to create a new deployment for a structure.
Create ThreadTool to create a new thread in Griptape Cloud.
Create Thread MessageTool to create a new message in a specific thread.
Create Tool DeploymentCreate a new deployment for a tool from a GitHub repository.
Delete API KeyTool to delete an API key by ID.
Delete AssistantTool to delete an assistant by ID.
Delete BucketTool to delete a bucket by ID.
Delete Bucket AssetTool to delete a specific asset from a Griptape Cloud bucket.
Delete Data ConnectorTool to delete a data connector.
Delete FunctionTool to delete a function from Griptape Cloud.
Delete IntegrationTool to delete an integration by ID.
Delete Knowledge BaseTool to delete a Knowledge Base from Griptape Cloud.
Delete LibraryTool to delete a library from Griptape Cloud.
Delete MessageTool to delete a message by its ID.
Delete Model ConfigurationTool to delete a model configuration from Griptape Cloud.
Delete Model Auth ConfigTool to delete a model auth config by ID.
Delete RuleTool to delete a rule by its ID.
Delete RulesetTool to permanently delete a ruleset from Griptape Cloud by its ID.
Delete SecretTool to delete a secret from Griptape Cloud.
Delete StructureTool to delete a structure from Griptape Cloud.
Delete ThreadTool to delete a thread by its ID.
Delete ToolTool to delete a tool from Griptape Cloud.
Get API KeyTool to retrieve an API key's details.
Get AssistantTool to retrieve a specific assistant's details by ID.
Get Billing Management URLTool to retrieve the billing management portal URL.
Get BucketTool to retrieve a bucket's details by its ID.
Get Bucket AssetTool to retrieve a specific asset from a Griptape Cloud bucket.
Get Bucket Asset URLTool to generate a signed URL for accessing or uploading bucket assets.
Get ConfigurationTool to retrieve Griptape Cloud configuration.
Get Credits BalanceTool to retrieve the current credits balance.
Get Data ConnectorTool to retrieve a data connector's configuration and details from Griptape Cloud.
Get Data JobTool to retrieve a data job's status and details by its ID.
Get Export JobTool to retrieve an export job by ID.
Get FunctionTool to retrieve a function's details.
Get Import JobTool to retrieve an import job's status and details.
Get IntegrationTool to retrieve a specific integration's details by ID.
Get Knowledge BaseTool to retrieve a knowledge base's configuration and details from Griptape Cloud.
Get Knowledge Base JobTool to retrieve a knowledge base job's status and details by its ID.
Get Knowledge Base SearchTool to retrieve details of a specific knowledge base search by its ID.
Get LibraryTool to retrieve a specific library's details by ID.
Get MessageTool to retrieve a specific message's details by ID.
Get Model ConfigurationTool to retrieve a model configuration's details by its ID.
Get Model Auth ConfigTool to retrieve a model auth config by ID.
Get OrganizationTool to retrieve an organization's details by its ID.
Get RetrieverTool to retrieve a retriever's details by its ID.
Get Retriever ComponentTool to retrieve a retriever component's details by its ID.
Get RuleTool to retrieve a specific rule's details by ID.
Get RulesetTool to retrieve a specific ruleset's details by ID.
Get Ruleset by AliasRetrieve a ruleset from Griptape Cloud by its unique alias identifier.
Get SecretTool to retrieve a secret's details from Griptape Cloud.
Get StructureTool to retrieve a structure's configuration and details from Griptape Cloud.
Get Structures DashboardTool to retrieve dashboard metrics for structures.
Get ThreadTool to retrieve a specific thread's details by ID.
Get ToolTool to retrieve a specific tool's details by ID.
Get UsageTool to retrieve current usage statistics.
Get UserTool to retrieve a user's details by their ID.
List Assistant Run EventsTool to list events for an assistant run with pagination support.
List Bucket AssetsTool to list assets in a bucket.
List BucketsTool to list all buckets in Griptape Cloud.
List ConnectionsTool to list all connections.
List Data ConnectorsTool to list all data connectors.
List Embedding DriversTool to list available embedding drivers.
List Export JobsTool to list export jobs from Griptape Cloud.
List Function DeploymentsTool to list all deployments for a specific function.
List FunctionsTool to list all functions with optional pagination.
List Import JobsTool to list import jobs in Griptape Cloud.
List IntegrationsTool to list all integrations.
List Knowledge Base JobsTool to list knowledge base jobs for a specific knowledge base.
List Knowledge Base QueriesTool to list all queries made to a specific Griptape Cloud knowledge base.
List Knowledge BasesTool to list all knowledge bases.
List Knowledge Base SearchesTool to list all searches performed on a specific knowledge base.
List LibrariesTool to list all libraries in Griptape Cloud.
List Model Auth ConfigsTool to list all model authentication configurations with optional pagination.
List ModelsTool to list all models in Griptape Cloud.
List Organization API KeysTool to list all API keys in a specific organization.
List OrganizationsTool to list all organizations in Griptape Cloud.
List Retriever ComponentsTool to list all retriever components in Griptape Cloud.
List RetrieversTool to list all retrievers in Griptape Cloud.
List RulesTool to list all rules in Griptape Cloud with optional pagination and filtering.
List SecretsTool to list all secrets in Griptape Cloud.
List Structure DeploymentsTool to list all deployments for a specific structure.
List Structure RunsTool to list all runs for a specific structure with optional pagination and status filtering.
List StructuresTool to list all structures in Griptape Cloud.
List Thread MessagesTool to list all messages in a specific thread.
List ThreadsTool to list all threads.
List Tool DeploymentsTool to list all deployments for a specific tool.
List Tool RunsTool to list all runs for a specific tool with optional pagination and status filtering.
List UsersTool to list all users in Griptape Cloud.
Query knowledge basePerforms semantic search against a Griptape Cloud knowledge base using natural language.
Query RetrieverTool to query a retriever in Griptape Cloud with a natural-language query.
Ruleset CreationCreates a new ruleset in Griptape Cloud.
Search Knowledge BaseSearches a Griptape Cloud Knowledge Base with a natural-language query and returns a synthesized answer.
Create ToolCreate a new tool resource in Griptape Cloud.
Get Tool Deployment StatusTool to retrieve status of a specific tool deployment.
List ToolsTool to list all tools.
Update AssistantTool to update an existing assistant's configuration.
Update BucketTool to update a bucket's properties by its ID.
Update Data ConnectorTool to update a data connector's configuration in Griptape Cloud.
Update FunctionTool to update an existing function's configuration.
Update IntegrationTool to update an existing integration's configuration.
Update Knowledge BaseTool to update a knowledge base's configuration in Griptape Cloud.
Update LibraryTool to update an existing library's configuration in Griptape Cloud.
Update MessageTool to update a message's input, output, and metadata by its ID.
Update Model ConfigurationTool to update a model configuration's properties by its ID.
Update Model Auth ConfigTool to update an existing model auth config's properties.
Update OrganizationTool to update an organization's properties by its ID.
Update RetrieverTool to update an existing retriever's configuration in Griptape Cloud.
Update Retriever ComponentTool to update a retriever component's configuration by its ID.
Update RuleTool to update an existing rule's configuration.
Update RulesetTool to update an existing ruleset's configuration.
Update SecretTool to update a secret's properties by its ID.
Update StructureTool to update an existing structure's configuration.
Update ThreadTool to update an existing thread's configuration.
Update ToolTool to update an existing tool's configuration.

What is the Composio tool router, and how does it fit here?

What is Composio SDK?

Composio's Composio SDK 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 Composio SDK

The tool router generates a secure MCP URL that your agents can access to perform actions.

How the Composio SDK works

The Composio SDK 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:

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

    # 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

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.