How to integrate Writer 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

Writer logo
Pydantic AI logo
divider

Introduction

This guide walks you through connecting Writer to Pydantic AI using the Composio tool router. By the end, you'll have a working Writer agent that can summarize key findings from uploaded medical notes, generate chat responses using enterprise llm, list all knowledge graphs in your workspace through natural language commands.

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

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

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

The Writer MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Writer account. It provides structured and secure access to your Writer AI platform, so your agent can perform actions like querying knowledge graphs, generating chat completions, extracting medical concepts, managing files, and orchestrating enterprise AI workflows on your behalf.

  • Conversational AI and content generation: Use your agent to generate chat-based completions and natural language responses using Writer's advanced LLMs.
  • Enterprise knowledge graph management: Create, retrieve, list, or delete knowledge graphs to organize and access structured knowledge within your organization.
  • Automated data extraction from clinical text: Extract medical entities and standardized codes (like SNOMED CT) from unstructured clinical or healthcare text for downstream analysis.
  • Application and model discovery: List available no-code agent applications and LLM models to streamline how your agent selects tools for specific tasks.
  • File management and inspection: Retrieve and review uploaded files, filter by attributes, and manage your enterprise content for further AI-driven actions.

Supported Tools & Triggers

Tools
Add File to Knowledge GraphTool to add a file to a knowledge graph for indexing and retrieval.
Analyze ImagesTool to analyze images using Writer's vision capabilities.
Ask Question to Knowledge GraphTool to send a question to the knowledge graph and retrieve the answer.
Chat CompletionTool to generate chat-based completions.
Create Knowledge GraphTool to create a new knowledge graph.
Delete FileTool to delete a file by its ID.
Delete GraphTool to delete a knowledge graph by its ID.
Detect AI ContentTool to detect whether content was generated by AI.
Download FileTool to download the binary content of a file.
Get FileTool to retrieve detailed information about a specific file by its ID.
List ApplicationsTool to list all no-code agent applications.
List FilesTool to list all uploaded files.
List Knowledge GraphsTool to retrieve a list of knowledge graphs.
List ModelsTool to list all available language models.
Medical Text ComprehensionTool to extract medical entities and concepts from unstructured clinical text.
Parse PDFTool to parse and extract text content from a previously uploaded PDF file.
Remove File From GraphTool to remove a file from a Knowledge Graph.
Retrieve Knowledge GraphTool to retrieve a knowledge graph by its ID.
Text GenerationTool to generate text based on a given prompt.
Translate TextTool to translate text from one language to another with support for formality, length control, and profanity masking.
Update Knowledge GraphTool to update an existing knowledge graph.
Upload FileTool to upload a file to Writer.
Web SearchTool to perform a web search.

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

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Writer MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Writer MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use Writer MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Writer MCP with Claude Cowork

Codex logo

Codex

Use Writer MCP with Codex

OpenClaw logo

OpenClaw

Use Writer MCP with OpenClaw

Hermes logo

Hermes

Use Writer MCP with Hermes

CLI logo

CLI

Use Writer MCP with CLI

Google ADK logo

Google ADK

Use Writer MCP with Google ADK

LangChain logo

LangChain

Use Writer MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Writer MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Writer MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Writer MCP with LlamaIndex

CrewAI logo

CrewAI

Use Writer MCP with CrewAI

FAQ

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

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

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

Yes, absolutely. You can configure which Writer 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 Writer 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↗