How to integrate Flowiseai MCP with Autogen

This guide walks you through connecting Flowiseai to AutoGen using the Composio tool router. By the end, you'll have a working Flowiseai agent that can list all chatflows available in your account, clone an existing chatflow for testing, delete chat messages from a specific chatflow through natural language commands. This guide will help you understand how to give your AutoGen agent real control over a Flowiseai account through Composio's Flowiseai MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved.

Get started for freeGet a demo
Flowiseai logoFlowiseai
Api Key

FlowiseAI is an open-source platform for building generative AI agents and LLM workflows. It lets teams visually design, deploy, and manage AI pipelines fast.

29 Tools

Introduction

This guide walks you through connecting Flowiseai to AutoGen using the Composio tool router. By the end, you'll have a working Flowiseai agent that can list all chatflows available in your account, clone an existing chatflow for testing, delete chat messages from a specific chatflow through natural language commands.

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

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

Also integrate Flowiseai with

OpenAI Agents SDKClaude Agent SDKClaude CodeClaude CoworkCodexOpenClawHermesCLIGoogle ADKLangChainVercel AI SDKMastra AILlamaIndexCrewAI

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

The Flowiseai MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Flowiseai account. It provides structured and secure access to your FlowiseAI workspace, so your agent can manage chatflows, automate workflow creation, clone or delete existing flows, and handle tool configurations on your behalf.

  • Automated chatflow creation and management: Instantly create new chatflows, fetch details of existing ones, or update and organize your LLM workflows programmatically.
  • Seamless cloning and exporting of chatflows: Duplicate any chatflow with a single request or export them for backup, sharing, or versioning across projects.
  • Easy clean-up and deletion: Direct your agent to delete chatflows, remove outdated tools, or erase chat messages to keep your workspace tidy and relevant.
  • Tool and workflow introspection: Retrieve detailed metadata for specific tools or chatflows so your agent can make informed decisions about which components to use or modify.
  • Effortless import and migration: Import chatflows from exported JSON files, making it simple to migrate or restore entire AI workflows with minimal manual effort.

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

Step by step08 STEPS
1

Prerequisites

You will need:

  • A Composio API key
  • An OpenAI API key (used by Autogen's OpenAIChatCompletionClient)
  • A Flowiseai account you can connect to Composio
  • Some basic familiarity with Autogen and Python async
2

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.
3

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 Flowiseai via MCP
  • autogen-agentchat provides the AssistantAgent class
  • autogen-ext-openai provides the OpenAI model client
  • autogen-ext-tools provides MCP workbench support

4

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 Flowiseai connections to use
5

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 Flowiseai session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["flowiseai"]
    )
    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 Flowiseai tools
  • session.mcp.url is the MCP endpoint that Autogen will connect to
6

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
7

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 Flowiseai assistant agent with MCP tools
    agent = AssistantAgent(
        name="flowiseai_assistant",
        description="An AI assistant that helps with Flowiseai 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 Flowiseai tools from the workbench
8

Run the interactive chat loop

python
print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
print("Ask any Flowiseai 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 Flowiseai 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 Flowiseai 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 Flowiseai session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["flowiseai"]
    )
    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 Flowiseai assistant agent with MCP tools
        agent = AssistantAgent(
            name="flowiseai_assistant",
            description="An AI assistant that helps with Flowiseai 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 Flowiseai 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 Flowiseai 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 Flowiseai, you can reuse the same structure for other MCP-enabled apps with minimal code changes.
TOOLS

Supported Tools

Every Flowiseai action and event your agent gets out of the box.

Clone Chatflow

Tool to clone an existing chatflow.

Create Chatflow

Creates a new chatflow in FlowiseAI.

Create Document Store

Creates a new document store in FlowiseAI.

Create Lead

Tool to create a new lead in a chatflow.

Create Tool

Tool to create a new FlowiseAI tool.

Create Variable

Creates a new variable in FlowiseAI.

Delete Chatflow

Tool to delete a chatflow by its ID.

Delete Chat Messages

Tool to delete chat messages for a specific chatflow.

Delete Document Store

Tool to delete a specific document store by its ID.

Delete Tool By ID

Permanently deletes a FlowiseAI tool by its unique ID.

Delete Variable

Tool to delete a variable by its unique ID.

Edit Document Store File Chunk

Tool to update a specific chunk in a FlowiseAI document store.

Get All Chatflows

Retrieves all chatflows from the authenticated FlowiseAI account.

Get All Chat Message Feedback

Tool to list all chat message feedbacks for a chatflow.

Get All Leads for Chatflow

Tool to retrieve all leads for a specific chatflow.

Get All Upsert History

Tool to retrieve all upsert history records for a specific chatflow.

Get All Variables

Tool to retrieve a list of all variables.

Get Document Store By ID

Tool to retrieve a document store by its ID.

Get Document Store File Chunks

Tool to get chunks from a specific document loader.

Get Single Chatflow

Tool to retrieve a chatflow by its ID.

Get Tool By ID

Tool to retrieve a specific FlowiseAI tool by its ID.

List All Tools

Tool to retrieve a list of all tools.

List Assistants

Tool to retrieve a list of all assistants.

List Chat Messages

Tool to list chat messages of a chatflow.

Ping Server

Tool to ping the FlowiseAI server to verify it is running and accessible.

Update Chatflow Details

Tool to update details of an existing chatflow.

Update Document Store

Tool to update a specific document store.

Update Tool By ID

Updates a FlowiseAI tool's properties by its ID.

Update Variable

Tool to update a variable by its ID.

FRAMEWORKS

How to build Flowiseai MCP Agent with another framework

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Flowiseai MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Flowiseai MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use Flowiseai MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Flowiseai MCP with Claude Cowork

Codex logo

Codex

Use Flowiseai MCP with Codex

OpenClaw logo

OpenClaw

Use Flowiseai MCP with OpenClaw

Hermes logo

Hermes

Use Flowiseai MCP with Hermes

CLI logo

CLI

Use Flowiseai MCP with CLI

Google ADK logo

Google ADK

Use Flowiseai MCP with Google ADK

LangChain logo

LangChain

Use Flowiseai MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Flowiseai MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Flowiseai MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Flowiseai MCP with LlamaIndex

CrewAI logo

CrewAI

Use Flowiseai MCP with CrewAI

FAQ

Frequently asked questions

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

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 Flowiseai tools.

Yes, absolutely. You can configure which Flowiseai 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.

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 Flowiseai data and credentials are handled as safely as possible.

Start with Flowiseai.It takes 30 seconds.

Managed auth, hosted MCP servers, and every Flowiseai tool your agent needs.Free to start.

Start building
Customer stories

Teams ship real agents on Composio

GET STARTED FOR FREEBOOK A DEMO
agent.aiZoomLettaGleanHubSpotAWSWabi

Karan skipped his own birthday party to fix our critical issue. It was 10pm and he diverted his Waymo to help us instead. This really sets the bar — it shows the commitment you need when users rely on your software.

Harsha Gaddipati
Harsha Gaddipati
Co-founder, Slashy

A lot of students tell us that the moment their connected tools start talking to each other inside Opennote feels almost magical. The agent just knows them, and it's immensely helped keep new users on the platform.

Abhi Arya
Abhi Arya
Co-founder, Opennote

We chose Composio over Pipedream because it delivered depth where it mattered — niche tools and tricky edge cases other platforms simply ignored. That gave us confidence to scale without compromising.

Nirman Dave
Nirman Dave
CEO, Zams

As a solo builder, shipping fast is life or death. The only way I can outcompete incumbents is by outmanoeuvring them. Getting bogged down managing agent auth would have been a death sentence.

Ryan Yu
Ryan Yu
Founder, Extra Thursday

Before Composio, adding tool integrations was slow and resource-intensive. Each one could take weeks of engineering time, and maintaining them meant constantly keeping up with API changes.

Tomisin Jenrola
Tomisin Jenrola
Founder & CEO, SwarmZero

With hands-on help from their founder, we integrated Gmail and Google Drive in just 30 minutes. This level of personal support and commitment is exactly what startups should strive for.

Jerome Leclanche
Jerome Leclanche
Co-Founder, Ingram Technologies