How to integrate Folk MCP with Autogen

Trusted by
AWS
Glean
Zoom
Airtable
GET STARTED FOR FREEGET A DEMO

30 min · no commitment · see it on your stack

Folk logo
AutoGen logo
divider

Introduction

This guide walks you through connecting Folk to AutoGen using the Composio tool router. By the end, you'll have a working Folk agent that can list all companies added this week, add a new company called acme corp, get details for person with email john@acme.com through natural language commands.

This guide will help you understand how to give your AutoGen agent real control over a Folk account through Composio's Folk MCP server.

Before we dive in, let's take a quick look at the key ideas and tools involved.

Also integrate Folk 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 Folk
  • Wire that MCP URL into Autogen using McpWorkbench and StreamableHttpServerParams
  • Configure an Autogen AssistantAgent that can call Folk tools
  • Run a live chat loop where you ask the agent to perform Folk 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 Folk MCP server, and what's possible with it?

The Folk MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Folk account. It provides structured and secure access to your CRM workspace, so your agent can perform actions like managing contacts, organizing companies, retrieving group info, and handling custom fields on your behalf.

  • Contact management and retrieval: Let your agent list, fetch, or delete people in your workspace, ensuring your contact database stays relevant and up to date.
  • Company and organization operations: Effortlessly create new companies, retrieve details, or remove outdated organizations from your workspace via your agent.
  • Workspace group insights: Ask your agent to list workspace groups and explore available group custom fields for efficient segmentation and tracking.
  • User profile and context access: Allow your agent to pull current workspace user details, making personalized automations and actions possible.
  • Custom field exploration: Enable your agent to list and understand custom fields for groups and entity types, powering more tailored CRM workflows.

Supported Tools & Triggers

Tools
Create CompanyCreates a new company in the Folk workspace with the specified details.
Create NoteTool to create a new note in the Folk workspace.
Create PersonCreates a new person in the Folk workspace with the specified details.
Delete CompanyTool to delete a company from the workspace (irreversible).
Delete NoteTool to delete an existing note in the workspace (irreversible).
Delete PersonTool to delete an existing person in the workspace (irreversible).
Delete ReminderTool to delete an existing reminder in the workspace (irreversible).
Get CompanyTool to retrieve an existing company by its ID.
Get Current Workspace UserTool to get details of the current authenticated workspace user.
Get NoteTool to retrieve an existing note by its ID.
Get PersonTool to retrieve an existing person by their ID.
Get UserTool to retrieve a user by their unique identifier.
List CompaniesTool to list companies in the workspace.
List Group Custom FieldsTool to list custom fields for a specific group and entity type.
List GroupsTool to list workspace groups.
List NotesTool to list notes in the workspace.
List PeopleTool to list people in the workspace.
List RemindersTool to list reminders in the workspace.
List UsersTool to list workspace users.
List WebhooksTool to list webhooks in the workspace.
Update CompanyTool to update an existing company in the workspace.
Update NoteTool to update an existing note in the workspace.
Update PersonTool to update an existing person in the workspace.

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 Folk 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 Folk 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 Folk 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 Folk session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["folk"]
    )
    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 Folk 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 Folk assistant agent with MCP tools
    agent = AssistantAgent(
        name="folk_assistant",
        description="An AI assistant that helps with Folk 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 Folk 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 Folk 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 Folk 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 Folk 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 Folk session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["folk"]
    )
    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 Folk assistant agent with MCP tools
        agent = AssistantAgent(
            name="folk_assistant",
            description="An AI assistant that helps with Folk 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 Folk 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 Folk 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 Folk, you can reuse the same structure for other MCP-enabled apps with minimal code changes.

How to build Folk MCP Agent with another framework

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Folk MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Folk MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use Folk MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Folk MCP with Claude Cowork

Codex logo

Codex

Use Folk MCP with Codex

OpenClaw logo

OpenClaw

Use Folk MCP with OpenClaw

Hermes logo

Hermes

Use Folk MCP with Hermes

CLI logo

CLI

Use Folk MCP with CLI

Google ADK logo

Google ADK

Use Folk MCP with Google ADK

LangChain logo

LangChain

Use Folk MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Folk MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Folk MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Folk MCP with LlamaIndex

CrewAI logo

CrewAI

Use Folk MCP with CrewAI

FAQ

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

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

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

Yes, absolutely. You can configure which Folk 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 Folk 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.

Get started for freeGet a demo↗