# How to integrate Folk MCP with Autogen

```json
{
  "title": "How to integrate Folk MCP with Autogen",
  "toolkit": "Folk",
  "toolkit_slug": "folk",
  "framework": "AutoGen",
  "framework_slug": "autogen",
  "url": "https://composio.dev/toolkits/folk/framework/autogen",
  "markdown_url": "https://composio.dev/toolkits/folk/framework/autogen.md",
  "updated_at": "2026-05-12T10:12:00.414Z"
}
```

## 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

- [OpenAI Agents SDK](https://composio.dev/toolkits/folk/framework/open-ai-agents-sdk)
- [Claude Agent SDK](https://composio.dev/toolkits/folk/framework/claude-agents-sdk)
- [Claude Code](https://composio.dev/toolkits/folk/framework/claude-code)
- [Claude Cowork](https://composio.dev/toolkits/folk/framework/claude-cowork)
- [Codex](https://composio.dev/toolkits/folk/framework/codex)
- [OpenClaw](https://composio.dev/toolkits/folk/framework/openclaw)
- [Hermes](https://composio.dev/toolkits/folk/framework/hermes-agent)
- [CLI](https://composio.dev/toolkits/folk/framework/cli)
- [Google ADK](https://composio.dev/toolkits/folk/framework/google-adk)
- [LangChain](https://composio.dev/toolkits/folk/framework/langchain)
- [Vercel AI SDK](https://composio.dev/toolkits/folk/framework/ai-sdk)
- [Mastra AI](https://composio.dev/toolkits/folk/framework/mastra-ai)
- [LlamaIndex](https://composio.dev/toolkits/folk/framework/llama-index)
- [CrewAI](https://composio.dev/toolkits/folk/framework/crew-ai)

## 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

| Tool slug | Name | Description |
|---|---|---|
| `FOLK_CREATE_COMPANY` | Create Company | Creates a new company in the Folk workspace with the specified details. Required: company name (unique identifier). Optional: description, industry, funding details, employee range, contact info (emails, phones, urls, addresses), group assignments, and custom field values. Returns the created company with a unique ID, all provided fields, timestamps, and creator information. |
| `FOLK_CREATE_NOTE` | Create Note | Tool to create a new note in the Folk workspace. Use when you need to add a note to a person, company, or deal entity. |
| `FOLK_CREATE_PERSON` | Create Person | Creates a new person in the Folk workspace with the specified details. Optional fields include: first name, last name, emails, phones, group assignments, and custom field values. The first email/phone in the list is treated as the primary contact. Returns the created person with a unique ID, all provided fields, timestamps, and creator information. |
| `FOLK_DELETE_COMPANY` | Delete Company | Tool to delete a company from the workspace (irreversible). Use after confirming this company should be removed. |
| `FOLK_DELETE_NOTE` | Delete Note | Tool to delete an existing note in the workspace (irreversible). Use after confirming this note should be permanently removed. |
| `FOLK_FOLK_DELETE_PERSON` | Delete Person | Tool to delete an existing person in the workspace (irreversible). Use after confirming this person should be permanently removed. |
| `FOLK_DELETE_REMINDER` | Delete Reminder | Tool to delete an existing reminder in the workspace (irreversible). Use after confirming this reminder should be permanently removed. |
| `FOLK_GET_COMPANY` | Get Company | Tool to retrieve an existing company by its ID. Use after authentication has been verified. |
| `FOLK_GET_CURRENT_WORKSPACE_USER` | Get Current Workspace User | Tool to get details of the current authenticated workspace user. Use after authentication to retrieve the user's profile information. |
| `FOLK_GET_NOTE` | Get Note | Tool to retrieve an existing note by its ID. Use when you need the full content and metadata of a specific note. |
| `FOLK_GET_PERSON` | Get Person | Tool to retrieve an existing person by their ID. Use when you need full profile details of a person by their unique identifier. |
| `FOLK_GET_USER` | Get User | Tool to retrieve a user by their unique identifier. Use when you need to get details of a specific workspace user. |
| `FOLK_FOLK_LIST_COMPANIES` | List Companies | Tool to list companies in the workspace. Use when you need a paginated overview of companies, optionally filtered. |
| `FOLK_LIST_GROUP_CUSTOM_FIELDS` | List Group Custom Fields | Tool to list custom fields for a specific group and entity type. Use after selecting a group and entity type to inspect available custom fields. |
| `FOLK_LIST_GROUPS` | List Groups | Tool to list workspace groups. Use when you need to retrieve a paginated list of all workspace groups after authentication. |
| `FOLK_LIST_NOTES` | List Notes | Tool to list notes in the workspace. Use when you need to retrieve notes with pagination support. |
| `FOLK_LIST_PEOPLE` | List People | Tool to list people in the workspace. Use when you need to paginate through contacts after authentication. |
| `FOLK_LIST_REMINDERS` | List Reminders | Tool to list reminders in the workspace. Use when you need a paginated overview of reminders, optionally filtered by entity. |
| `FOLK_LIST_USERS` | List Users | Tool to list workspace users. Use when you need to paginate through users list. |
| `FOLK_LIST_WEBHOOKS` | List Webhooks | Tool to list webhooks in the workspace. Use when you need to retrieve configured webhooks with pagination support. |
| `FOLK_UPDATE_COMPANY` | Update Company | Tool to update an existing company in the workspace. Use after confirming the company ID; only provided fields are updated and list fields replace existing values. |
| `FOLK_UPDATE_NOTE` | Update Note | Tool to update an existing note in the workspace. Use after confirming the note ID; only provided fields are updated. |
| `FOLK_UPDATE_PERSON` | Update Person | Tool to update an existing person in the workspace. Use after confirming the person ID; only provided fields are updated and list fields replace existing values. |

## Supported Triggers

None listed.

## Creating MCP Server - Stand-alone vs Composio SDK

The Folk MCP server is an implementation of the Model Context Protocol that connects your AI agents and assistants directly to Folk. Instead of manually wiring Folk APIs, OAuth, and scopes yourself, you get a structured, tool-based interface that an LLM can call safely.
With Composio's managed implementation, you don't have to create your own developer app. For production, if you're building an end product, we recommend using your own credentials. The managed server helps you prototype fast and go from 0-1 faster.

## Step-by-step Guide

### 1. 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

### 1. Getting API Keys for OpenAI and Composio

OpenAI API Key
- Go to the [OpenAI dashboard](https://platform.openai.com/settings/organization/api-keys) 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](https://dashboard.composio.dev?utm_source=toolkits&utm_medium=framework_docs).
- Navigate to your API settings and generate a new API key.
- Store this key securely as you'll need it for authentication.

### 2. Install dependencies

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

### 3. Set up environment variables

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

### 4. Import dependencies and create Tool Router session

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
```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
```

### 5. Configure MCP parameters for Autogen

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
```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")}
)
```

### 6. Create the model client and agent

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
```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
    )
```

### 7. Run the interactive chat loop

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
```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")
```

## Complete Code

```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](https://composio.dev/toolkits/folk/framework/open-ai-agents-sdk)
- [Claude Agent SDK](https://composio.dev/toolkits/folk/framework/claude-agents-sdk)
- [Claude Code](https://composio.dev/toolkits/folk/framework/claude-code)
- [Claude Cowork](https://composio.dev/toolkits/folk/framework/claude-cowork)
- [Codex](https://composio.dev/toolkits/folk/framework/codex)
- [OpenClaw](https://composio.dev/toolkits/folk/framework/openclaw)
- [Hermes](https://composio.dev/toolkits/folk/framework/hermes-agent)
- [CLI](https://composio.dev/toolkits/folk/framework/cli)
- [Google ADK](https://composio.dev/toolkits/folk/framework/google-adk)
- [LangChain](https://composio.dev/toolkits/folk/framework/langchain)
- [Vercel AI SDK](https://composio.dev/toolkits/folk/framework/ai-sdk)
- [Mastra AI](https://composio.dev/toolkits/folk/framework/mastra-ai)
- [LlamaIndex](https://composio.dev/toolkits/folk/framework/llama-index)
- [CrewAI](https://composio.dev/toolkits/folk/framework/crew-ai)

## Related Toolkits

- [Hubspot](https://composio.dev/toolkits/hubspot) - HubSpot is an all-in-one marketing, sales, and customer service platform. It lets teams nurture leads, automate outreach, and track every customer interaction in one place.
- [Pipedrive](https://composio.dev/toolkits/pipedrive) - Pipedrive is a sales management platform offering pipeline visualization, lead tracking, and workflow automation. It helps sales teams keep deals moving forward efficiently and never miss a follow-up.
- [Salesforce](https://composio.dev/toolkits/salesforce) - Salesforce is a leading CRM platform that helps businesses manage sales, service, and marketing. It centralizes customer data, enabling teams to drive growth and build strong relationships.
- [Apollo](https://composio.dev/toolkits/apollo) - Apollo is a CRM and lead generation platform that helps businesses discover contacts and manage sales pipelines. Use it to streamline customer outreach and track your deals from one place.
- [Attio](https://composio.dev/toolkits/attio) - Attio is a customizable CRM and workspace for managing your team's relationships and workflows. It helps teams organize contacts, automate tasks, and collaborate more efficiently.
- [Acculynx](https://composio.dev/toolkits/acculynx) - AccuLynx is a cloud-based roofing business management software for contractors. It streamlines project tracking, lead management, and document sharing.
- [Addressfinder](https://composio.dev/toolkits/addressfinder) - Addressfinder is a data quality platform for verifying addresses, emails, and phone numbers. It helps you ensure accurate customer and contact data every time.
- [Affinity](https://composio.dev/toolkits/affinity) - Affinity is a relationship intelligence CRM that helps private capital investors find, manage, and close more deals. It streamlines deal flow and surfaces key connections to help you win opportunities.
- [Agencyzoom](https://composio.dev/toolkits/agencyzoom) - AgencyZoom is a sales and performance platform built for P&C insurance agencies. It helps agents boost sales, retain clients, and analyze producer results in one place.
- [Bettercontact](https://composio.dev/toolkits/bettercontact) - Bettercontact is a smart contact enrichment tool for finding emails and phone numbers. It helps boost lead generation with automated, waterfall search across multiple sources.
- [Blackbaud](https://composio.dev/toolkits/blackbaud) - Blackbaud provides cloud-based software for nonprofits, schools, and healthcare institutions. It streamlines fundraising, donor management, and mission-driven operations.
- [Brilliant directories](https://composio.dev/toolkits/brilliant_directories) - Brilliant Directories is an all-in-one platform for building and managing online membership communities and business directories. It streamlines listings, member management, and engagement tools into a single, easy interface.
- [Capsule crm](https://composio.dev/toolkits/capsule_crm) - Capsule CRM is a user-friendly CRM platform for managing contacts and sales pipelines. It helps businesses organize relationships and streamline their sales process efficiently.
- [Centralstationcrm](https://composio.dev/toolkits/centralstationcrm) - CentralStationCRM is an easy-to-use CRM software focused on collaboration and long-term customer relationships. It helps teams manage contacts, deals, and communications all in one place.
- [Clientary](https://composio.dev/toolkits/clientary) - Clientary is a platform for managing clients, invoices, projects, proposals, and more. It streamlines client work and saves you serious admin time.
- [Close](https://composio.dev/toolkits/close) - Close is a CRM platform built for sales teams, combining calling, email automation, and predictive dialers. It streamlines sales workflows and boosts productivity with all-in-one communication tools.
- [Dropcontact](https://composio.dev/toolkits/dropcontact) - Dropcontact is a B2B email finder and data enrichment service for professionals. It delivers verified email addresses and enriches contact info with up-to-date data.
- [Dynamics365](https://composio.dev/toolkits/dynamics365) - Dynamics 365 is Microsoft's platform combining CRM, ERP, and productivity apps. It streamlines sales, marketing, service, and operations in one place.
- [Espocrm](https://composio.dev/toolkits/espocrm) - EspoCRM is an open-source web application for managing customer relationships. It helps businesses organize contacts, track leads, and streamline their sales process.
- [Fireberry](https://composio.dev/toolkits/fireberry) - Fireberry is a CRM platform that streamlines customer and sales management. It helps businesses organize contacts, automate sales, and integrate with other business tools.

## Frequently Asked Questions

### 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.

---
[See all toolkits](https://composio.dev/toolkits) · [Composio docs](https://docs.composio.dev/llms.txt)
