How to integrate Manus MCP with Pydantic AI

This guide walks you through connecting Manus to Pydantic AI using the Composio tool router. By the end, you'll have a working Manus agent that can create manus task for competitor research, list pending manus workflow tasks, summarize completed manus automation runs through natural language commands. This guide will help you understand how to give your Pydantic AI agent real control over a Manus account through Composio's Manus 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
Manus logoManus
Api Key

Manus is an AI-powered task automation and workflow management platform. It helps teams delegate complex work, track progress, and run repeatable workflows.

14 Tools

Introduction

This guide walks you through connecting Manus to Pydantic AI using the Composio tool router. By the end, you'll have a working Manus agent that can create manus task for competitor research, list pending manus workflow tasks, summarize completed manus automation runs through natural language commands.

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

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

Also integrate Manus with

OpenAI Agents SDKClaude Agent SDKClaude CodeClaude CoworkCodexOpenClawHermesCLIGoogle ADKLangChainVercel AI SDKMastra AILlamaIndexCrewAI

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 Manus
  • 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 Manus 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 Manus MCP server, and what's possible with it?

The Manus MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Manus account. It provides structured and secure access to your projects and AI tasks, so your agent can create projects, start tasks, review task details, monitor progress, and list existing tasks on your behalf.

  • Project creation: Have your agent create a new Manus project with default instructions whenever you need a fresh workspace.
  • AI task creation: Direct your agent to start custom AI tasks with instructions, attachments, and optional connectors.
  • Task progress monitoring: Let the agent check a task's status, output messages, credit usage, and related details.
  • Task discovery: Instruct your agent to list and filter existing tasks so you can quickly find the work that matters.
  • Webhook verification support: Have your agent retrieve the public key needed to verify that webhook updates came from Manus.

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 step09 STEPS
1

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
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 pydantic-ai python-dotenv

Install the required libraries.

What's happening:

  • composio connects your agent to external SaaS tools like Manus
  • pydantic-ai lets you create structured AI agents with tool support
  • python-dotenv loads your environment variables securely from a .env file
4

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
5

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 Manus
  • MCPServerStreamableHTTP connects to the Manus MCP server endpoint
  • Agent from Pydantic AI lets you define and run the AI assistant
6

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 Manus
    composio = Composio(api_key=api_key)
    session = composio.create(
        user_id=user_id,
        toolkits=["manus"],
    )
    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 Manus 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
7

Initialize the Pydantic AI Agent

python
# Attach the MCP server to a Pydantic AI Agent
manus_mcp = MCPServerStreamableHTTP(url, headers={"x-api-key": COMPOSIO_API_KEY})
agent = Agent(
    "openai:gpt-5",
    toolsets=[manus_mcp],
    instructions=(
        "You are a Manus assistant. Use Manus tools to help users "
        "with their requests. Ask clarifying questions when needed."
    ),
)
What's happening:
  • The MCP client connects to the Manus endpoint
  • The agent uses GPT-5 to interpret user commands and perform Manus operations
  • The instructions field defines the agent's role and behavior
8

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 Manus.\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
  • Manus API calls happen automatically under the hood
  • The model keeps conversation history to maintain context across turns
9

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 Manus 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 Manus
    composio = Composio(api_key=api_key)
    session = composio.create(
        user_id=user_id,
        toolkits=["manus"],
    )
    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
    manus_mcp = MCPServerStreamableHTTP(url, headers={"x-api-key": COMPOSIO_API_KEY})
    agent = Agent(
        "openai:gpt-5",
        toolsets=[manus_mcp],
        instructions=(
            "You are a Manus assistant. Use Manus 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 Manus.\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 Manus through Composio's Tool Router. With this setup, your agent can perform real Manus 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 + Manus for workflow automation)
This architecture makes your AI agent "agent-native", able to securely use APIs in a unified, composable way without custom integrations.
TOOLS

Supported Tools

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

Create File

Tool to create a file record and obtain a presigned URL for uploading file content to S3.

Create New Project

Tool to create a new project with default instructions.

Create New Task

Creates a new AI task with custom parameters, attachments, and optional connectors.

Create Webhook

Tool to register a webhook to receive real-time task notifications.

Delete a file

Deletes a file by ID.

Delete task

Permanently delete a task by its ID.

Delete Webhook

Removes a webhook subscription.

Get file details

Retrieves details of a specific file by ID, including its status and metadata.

Get Task

Retrieves details of a specific task by ID, including status, output messages, credit usage, and metadata.

Get Webhook Public Key

Retrieves the RSA public key used for verifying webhook signatures.

List uploaded files

Retrieves a list of the 10 most recently uploaded files.

List Projects

Retrieve a list of all projects in your account with optional pagination.

List tasks

Retrieves a list of tasks with optional filtering and pagination.

Update Task

Updates a task's metadata such as title, sharing settings, and visibility in the task list.

FRAMEWORKS

How to build Manus MCP Agent with another framework

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Manus MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Manus MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use Manus MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Manus MCP with Claude Cowork

Codex logo

Codex

Use Manus MCP with Codex

OpenClaw logo

OpenClaw

Use Manus MCP with OpenClaw

Hermes logo

Hermes

Use Manus MCP with Hermes

CLI logo

CLI

Use Manus MCP with CLI

Google ADK logo

Google ADK

Use Manus MCP with Google ADK

LangChain logo

LangChain

Use Manus MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Manus MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Manus MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Manus MCP with LlamaIndex

CrewAI logo

CrewAI

Use Manus MCP with CrewAI

FAQ

Frequently asked questions

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

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 Manus tools.

Yes, absolutely. You can configure which Manus 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 Manus data and credentials are handled as safely as possible.

Start with Manus.It takes 30 seconds.

Managed auth, hosted MCP servers, and every Manus 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