How to integrate Flowiseai MCP with Pydantic AI

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

30 min · no commitment · see it on your stack

Flowiseai logo
Pydantic AI logo
divider

Introduction

This guide walks you through connecting Flowiseai to Pydantic AI 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 Pydantic AI 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

TL;DR

Here's what you'll learn:
  • How to set up your Composio API key and User ID
  • How to create a Composio Tool Router session for Flowiseai
  • How to attach an MCP Server to a Pydantic AI agent
  • How to stream responses and maintain chat history
  • How to build a simple REPL-style chat interface to test your Flowiseai workflows

What is Pydantic AI?

Pydantic AI is a Python framework for building AI agents with strong typing and validation. It leverages Pydantic's data validation capabilities to create robust, type-safe AI applications.

Key features include:

  • Type Safety: Built on Pydantic for automatic data validation
  • MCP Support: Native support for Model Context Protocol servers
  • Streaming: Built-in support for streaming responses
  • Async First: Designed for async/await patterns

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  • Easy clean-up and deletion: Direct your agent to delete chatflows, remove outdated tools, or erase chat messages to keep your workspace tidy and relevant.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.

Supported Tools & Triggers

Tools
Clone ChatflowTool to clone an existing chatflow.
Create ChatflowCreates a new chatflow in FlowiseAI.
Create Document StoreCreates a new document store in FlowiseAI.
Create LeadTool to create a new lead in a chatflow.
Create ToolTool to create a new FlowiseAI tool.
Create VariableCreates a new variable in FlowiseAI.
Delete ChatflowTool to delete a chatflow by its ID.
Delete Chat MessagesTool to delete chat messages for a specific chatflow.
Delete Document StoreTool to delete a specific document store by its ID.
Delete Tool By IDPermanently deletes a FlowiseAI tool by its unique ID.
Delete VariableTool to delete a variable by its unique ID.
Edit Document Store File ChunkTool to update a specific chunk in a FlowiseAI document store.
Get All ChatflowsRetrieves all chatflows from the authenticated FlowiseAI account.
Get All Chat Message FeedbackTool to list all chat message feedbacks for a chatflow.
Get All Leads for ChatflowTool to retrieve all leads for a specific chatflow.
Get All Upsert HistoryTool to retrieve all upsert history records for a specific chatflow.
Get All VariablesTool to retrieve a list of all variables.
Get Document Store By IDTool to retrieve a document store by its ID.
Get Document Store File ChunksTool to get chunks from a specific document loader.
Get Single ChatflowTool to retrieve a chatflow by its ID.
Get Tool By IDTool to retrieve a specific FlowiseAI tool by its ID.
List All ToolsTool to retrieve a list of all tools.
List AssistantsTool to retrieve a list of all assistants.
List Chat MessagesTool to list chat messages of a chatflow.
Ping ServerTool to ping the FlowiseAI server to verify it is running and accessible.
Update Chatflow DetailsTool to update details of an existing chatflow.
Update Document StoreTool to update a specific document store.
Update Tool By IDUpdates a FlowiseAI tool's properties by its ID.
Update VariableTool to update a variable by its ID.

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

Before starting, make sure you have:
  • Python 3.9 or higher
  • A Composio account with an active API key
  • Basic familiarity with Python and async programming

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 pydantic-ai python-dotenv

Install the required libraries.

What's happening:

  • composio connects your agent to external SaaS tools like Flowiseai
  • pydantic-ai lets you create structured AI agents with tool support
  • python-dotenv loads your environment variables securely from a .env file

Set up environment variables

bash
COMPOSIO_API_KEY=your_composio_api_key_here
USER_ID=your_user_id_here
OPENAI_API_KEY=your_openai_api_key

Create a .env file in your project root.

What's happening:

  • COMPOSIO_API_KEY authenticates your agent to Composio's API
  • USER_ID associates your session with your account for secure tool access
  • OPENAI_API_KEY to access OpenAI LLMs

Import dependencies

python
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerStreamableHTTP

load_dotenv()
What's happening:
  • We load environment variables and import required modules
  • Composio manages connections to Flowiseai
  • MCPServerStreamableHTTP connects to the Flowiseai MCP server endpoint
  • Agent from Pydantic AI lets you define and run the AI assistant

Create a Tool Router Session

python
async def main():
    api_key = os.getenv("COMPOSIO_API_KEY")
    user_id = os.getenv("USER_ID")
    if not api_key or not user_id:
        raise RuntimeError("Set COMPOSIO_API_KEY and USER_ID in your environment")

    # Create a Composio Tool Router session for Flowiseai
    composio = Composio(api_key=api_key)
    session = composio.create(
        user_id=user_id,
        toolkits=["flowiseai"],
    )
    url = session.mcp.url
    if not url:
        raise ValueError("Composio session did not return an MCP URL")
What's happening:
  • We're creating a Tool Router session that gives your agent access to Flowiseai tools
  • The create method takes the user ID and specifies which toolkits should be available
  • The returned session.mcp.url is the MCP server URL that your agent will use

Initialize the Pydantic AI Agent

python
# Attach the MCP server to a Pydantic AI Agent
flowiseai_mcp = MCPServerStreamableHTTP(url, headers={"x-api-key": COMPOSIO_API_KEY})
agent = Agent(
    "openai:gpt-5",
    toolsets=[flowiseai_mcp],
    instructions=(
        "You are a Flowiseai assistant. Use Flowiseai tools to help users "
        "with their requests. Ask clarifying questions when needed."
    ),
)
What's happening:
  • The MCP client connects to the Flowiseai endpoint
  • The agent uses GPT-5 to interpret user commands and perform Flowiseai operations
  • The instructions field defines the agent's role and behavior

Build the chat interface

python
# Simple REPL with message history
history = []
print("Chat started! Type 'exit' or 'quit' to end.\n")
print("Try asking the agent to help you with Flowiseai.\n")

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", flush=True)

    async with agent.run_stream(user_input, message_history=history) as stream_result:
        collected_text = ""
        async for chunk in stream_result.stream_output():
            text_piece = None
            if isinstance(chunk, str):
                text_piece = chunk
            elif hasattr(chunk, "delta") and isinstance(chunk.delta, str):
                text_piece = chunk.delta
            elif hasattr(chunk, "text"):
                text_piece = chunk.text
            if text_piece:
                collected_text += text_piece
        result = stream_result

    print(f"Agent: {collected_text}\n")
    history = result.all_messages()
What's happening:
  • The agent reads input from the terminal and streams its response
  • Flowiseai API calls happen automatically under the hood
  • The model keeps conversation history to maintain context across turns

Run the application

python
if __name__ == "__main__":
    asyncio.run(main())
What's happening:
  • The asyncio loop launches the agent and keeps it running until you exit

Complete Code

Here's the complete code to get you started with Flowiseai and Pydantic AI:

python
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerStreamableHTTP

load_dotenv()

async def main():
    api_key = os.getenv("COMPOSIO_API_KEY")
    user_id = os.getenv("USER_ID")
    if not api_key or not user_id:
        raise RuntimeError("Set COMPOSIO_API_KEY and USER_ID in your environment")

    # Create a Composio Tool Router session for Flowiseai
    composio = Composio(api_key=api_key)
    session = composio.create(
        user_id=user_id,
        toolkits=["flowiseai"],
    )
    url = session.mcp.url
    if not url:
        raise ValueError("Composio session did not return an MCP URL")

    # Attach the MCP server to a Pydantic AI Agent
    flowiseai_mcp = MCPServerStreamableHTTP(url, headers={"x-api-key": COMPOSIO_API_KEY})
    agent = Agent(
        "openai:gpt-5",
        toolsets=[flowiseai_mcp],
        instructions=(
            "You are a Flowiseai assistant. Use Flowiseai tools to help users "
            "with their requests. Ask clarifying questions when needed."
        ),
    )

    # Simple REPL with message history
    history = []
    print("Chat started! Type 'exit' or 'quit' to end.\n")
    print("Try asking the agent to help you with Flowiseai.\n")

    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", flush=True)

        async with agent.run_stream(user_input, message_history=history) as stream_result:
            collected_text = ""
            async for chunk in stream_result.stream_output():
                text_piece = None
                if isinstance(chunk, str):
                    text_piece = chunk
                elif hasattr(chunk, "delta") and isinstance(chunk.delta, str):
                    text_piece = chunk.delta
                elif hasattr(chunk, "text"):
                    text_piece = chunk.text
                if text_piece:
                    collected_text += text_piece
            result = stream_result

        print(f"Agent: {collected_text}\n")
        history = result.all_messages()

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

Conclusion

You've built a Pydantic AI agent that can interact with Flowiseai through Composio's Tool Router. With this setup, your agent can perform real Flowiseai actions through natural language. You can extend this further by:
  • Adding other toolkits like Gmail, HubSpot, or Salesforce
  • Building a web-based chat interface around this agent
  • Using multiple MCP endpoints to enable cross-app workflows (for example, Gmail + Flowiseai for workflow automation)
This architecture makes your AI agent "agent-native", able to securely use APIs in a unified, composable way without custom integrations.

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

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

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.

Can I use Tool Router MCP with Pydantic AI?

Yes, you can. Pydantic AI 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.

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

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.

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 Flowiseai 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↗