How to integrate Ragie MCP with Pydantic AI

GET STARTED FOR FREE
Framework Integration Gradient
Ragie Logo
Pydantic AI Logo
divider

Introduction

This guide walks you through connecting Ragie to Pydantic AI using the Composio tool router. By the end, you'll have a working Ragie agent that can ingest new product documentation into ragie, run a semantic search for project roadmap, summarize key findings from all q2 reports through natural language commands.

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

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

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

The Ragie MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Ragie account. It provides structured and secure access so your agent can perform Ragie operations on your behalf.

Supported Tools & Triggers

Tools
Create DocumentTool to upload and process a document file in Ragie.
Create Document From URLTool to ingest a document from a publicly accessible URL.
Create Document RawTool to ingest a document as raw text or JSON.
Create InstructionTool to create a new instruction that applies natural language directives to documents as they're ingested or updated.
Create OAuth Redirect URLTool to create an OAuth redirect URL for initializing embedded connector OAuth flows.
Create PartitionTool to create a new partition for scoping documents and connections in Ragie.
Delete DocumentTool to delete a document from Ragie.
Delete InstructionTool to delete an instruction and all associated entities.
Delete PartitionTool to delete a partition and all associated data irreversibly.
Get DocumentTool to retrieve a specific document by its unique identifier.
Get Document ChunkTool to retrieve a specific document chunk by its document and chunk ID.
Get Document Chunk ContentTool to retrieve document chunk content in requested format with streaming support for media.
Get Document ChunksTool to retrieve document chunks with pagination support.
Get Document ContentTool to retrieve the content of a document by its ID.
Get Document SummaryTool to retrieve an LLM-generated summary of a document by its ID.
Get PartitionTool to retrieve a partition by ID with usage statistics and resource limits.
Get ResponseTool to retrieve a response by its unique identifier.
List ConnectionsTool to list all connections sorted by creation date descending with pagination support.
List Connection Source TypesTool to list available connection source types like 'google_drive' and 'notion' along with their metadata.
List DocumentsTool to list all documents sorted by creation date (descending) with pagination support.
List Entities By DocumentTool to retrieve all extracted entities from a specific document with pagination support.
List Entities by InstructionTool to retrieve entities generated by a specific instruction.
List InstructionsTool to retrieve all instruction records from the Ragie system.
List PartitionsTool to retrieve a paginated list of all partitions sorted by name in ascending order.
Patch Document MetadataTool to update metadata for a specific document with partial update support.
Retrieve Document ChunksTool to retrieve relevant document chunks based on a query.
Set Partition LimitsTool to set usage limits on partition pages and media.
Update Document From URLTool to update an existing document by fetching content from a publicly accessible URL.
Update Document RawTool to update a document's content from raw text or JSON data.
Update InstructionTool to update an instruction's active status.
Update PartitionTool to update a partition's configuration including description, context-aware settings, and metadata schema.

What is the Composio tool router, and how does it fit here?

What is Tool Router?

Composio's Tool Router 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 Tool Router

The tool router generates a secure MCP URL that your agents can access to perform actions.

How the Tool Router works

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

OpenAI Agents SDK

OpenAI Agents SDK

Use Ragie MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Ragie MCP with Claude Agent SDK

Google ADK

Google ADK

Use Ragie MCP with Google ADK

LangChain

LangChain

Use Ragie MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Ragie MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Ragie MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Ragie MCP with LlamaIndex

CrewAI

CrewAI

Use Ragie MCP with CrewAI

Claude Code

Claude Code

Use Ragie MCP with Claude Code

Codex

Codex

Use Ragie MCP with Codex

FAQ

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

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

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

Yes, absolutely. You can configure which Ragie 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 Ragie 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.

Book a call↗Get started for free