How to integrate HackMD MCP with Pydantic AI

This guide walks you through connecting HackMD to Pydantic AI using the Composio tool router. By the end, you'll have a working HackMD agent that can create notes, read your notes, list your folders, trash notes, and restore deleted notes through natural language commands. This guide will help you understand how to give your Pydantic AI agent real control over a HackMD account through Composio's HackMD MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved.

HackMD logoHackMD
Api Key

HackMD is a collaborative Markdown workspace for personal and team notes. Use it to write, organize, and share living docs without leaving Markdown.

8 Tools

Introduction

This guide walks you through connecting HackMD to Pydantic AI using the Composio tool router. By the end, you'll have a working HackMD agent that can create notes, read your notes, list your folders, trash notes, and restore deleted notes through natural language commands.

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

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

Also integrate HackMD 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 HackMD
  • 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 HackMD 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 HackMD MCP server, and what's possible with it?

The HackMD MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your HackMD account. It provides structured and secure access to your personal and team notes, folders, trash, and account details, so your agent can create notes, read content, browse workspaces, move notes to trash, and restore deleted notes on your behalf.

  • Markdown note creation: Have your agent create Markdown notes in your personal workspace or a selected team workspace.
  • Note discovery and reading: Instruct your agent to list available notes and retrieve the full Markdown content of a chosen note.
  • Workspace and folder browsing: Let the agent view your HackMD profile, visible teams, and folders across personal or team workspaces.
  • Note cleanup: Direct your agent to move an unwanted personal or team note to the trash.
  • Deleted note recovery: Have your agent review trashed personal notes and restore one or more notes when needed.

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 HackMD
  • 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 HackMD
  • MCPServerStreamableHTTP connects to the HackMD 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 HackMD
    composio = Composio(api_key=api_key)
    session = composio.create(
        user_id=user_id,
        toolkits=["hackmd"],
    )
    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 HackMD 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
hackmd_mcp = MCPServerStreamableHTTP(url, headers={"x-api-key": COMPOSIO_API_KEY})
agent = Agent(
    "openai:gpt-5",
    toolsets=[hackmd_mcp],
    instructions=(
        "You are a HackMD assistant. Use HackMD tools to help users "
        "with their requests. Ask clarifying questions when needed."
    ),
)
What's happening:
  • The MCP client connects to the HackMD endpoint
  • The agent uses GPT-5 to interpret user commands and perform HackMD 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 HackMD.\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
  • HackMD 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 HackMD 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 HackMD
    composio = Composio(api_key=api_key)
    session = composio.create(
        user_id=user_id,
        toolkits=["hackmd"],
    )
    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
    hackmd_mcp = MCPServerStreamableHTTP(url, headers={"x-api-key": COMPOSIO_API_KEY})
    agent = Agent(
        "openai:gpt-5",
        toolsets=[hackmd_mcp],
        instructions=(
            "You are a HackMD assistant. Use HackMD 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 HackMD.\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 HackMD through Composio's Tool Router. With this setup, your agent can perform real HackMD 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 + HackMD 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 HackMD action and event your agent gets out of the box.

Create Note

Create a Markdown note in the personal workspace or a specified team workspace.

Get Account

Return the HackMD profile for the connected token and the teams visible to it.

Get Note

Get a note by ID, including its Markdown content.

List Folders

List all folders in the personal workspace, or in one team workspace when team_path is supplied.

List Notes

List all notes in the personal workspace, or in one team workspace when team_path is supplied.

List Trash

List soft-deleted notes in the personal workspace.

Move Note to Trash

Soft-delete a note by moving it to trash in the personal workspace or an explicitly selected team workspace.

Restore Notes

Restore one or more personal notes from HackMD trash.

FAQ

Frequently asked questions

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

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

Start with HackMD.It takes 30 seconds.

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

Start building