How to integrate Affinda MCP with Pydantic AI

This guide walks you through connecting Affinda to Pydantic AI using the Composio tool router. By the end, you'll have a working Affinda agent that can extract invoice data from uploaded pdf, delete a document no longer needed, create a new tag for hr documents through natural language commands. This guide will help you understand how to give your Pydantic AI agent real control over a Affinda account through Composio's Affinda 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
Affinda logoAffinda
Api Key

Affinda is an AI-powered document processing platform that automates data extraction from resumes, invoices, and more. It streamlines document-heavy workflows by turning files into structured, actionable data.

105 Tools

Introduction

This guide walks you through connecting Affinda to Pydantic AI using the Composio tool router. By the end, you'll have a working Affinda agent that can extract invoice data from uploaded pdf, delete a document no longer needed, create a new tag for hr documents through natural language commands.

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

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

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

The Affinda MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Affinda account. It provides structured and secure access to your document processing workflows, so your agent can upload files, extract data, organize workspaces, label documents, and automate annotation management on your behalf.

  • AI-powered document upload and extraction: Instantly have your agent upload new documents for parsing and extract structured data from various formats using Affinda's advanced AI models.
  • Workspace and collection management: Let your agent create, group, and organize documents into collections and workspaces, keeping your document processing streamlined and organized.
  • Automated annotation updates: Empower your agent to batch update or modify multiple document annotations in a single request, saving you time on manual corrections.
  • Document tagging and organization: Direct your agent to create tags and label documents, making it easy to categorize and quickly retrieve important files.
  • Effortless cleanup and resource management: Have your agent delete unwanted documents or collections, ensuring your Affinda account stays tidy and relevant at all times.

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

Add Tag to Documents

Tool to add a tag to multiple documents in a single operation.

Batch Update Annotations

Batch update multiple document annotations in a single API call.

Create API User

Tool to create a new API user within an organization.

Batch Create Annotations

Batch create multiple document annotations in a single API call.

Create Collection

Tool to create a new collection.

Create Data Field For Collection

Tool to create a data field for a collection along with a new data point.

Create Data Source

Tool to create a custom mapping data source.

Create Data Source Value

Tool to add a new value to a mapping data source.

Create Document

Upload a document to Affinda for parsing and data extraction.

Create Document Type

Tool to create a new document type in the specified organization.

Create Extractor

Tool to create a new extractor.

Create Document from Data

Create a document from structured resume or job description data for Search & Match.

Create Index

Tool to create a new index for search and match functionality.

Create Invitation

Tool to create a new organization invitation.

Create Job Description Search

Search through parsed job descriptions using custom criteria or resume matching.

Create Job Description Search Embed URL

Tool to create and return a signed URL for the embeddable job description search tool.

Create Organization

Tool to create a new organization.

Create RESTHook Subscription

Tool to create a new RESTHook subscription.

Create Resume Search

Tool to search through parsed resumes using three methods: match to a job description, match to a resume, or custom criteria.

Create Resume Search Embed URL

Tool to create and return a signed URL for the embeddable resume search tool.

Create Tag

Creates a new tag in the specified workspace.

Create Validation Result

Create a validation result for document annotations in Affinda.

Batch Create Validation Results

Batch create multiple validation results for document annotations in a single API call.

Create Workspace

Tool to create a new workspace.

Create Workspace Membership

Tool to add a user to a workspace by creating a membership.

Batch Delete Annotations

Batch delete multiple document annotations in a single API call.

Delete Collection

Permanently delete a collection from Affinda by its identifier.

Delete Data Source

Permanently delete a mapping data source from the database by its identifier.

Delete Data Source Value

Tool to delete a specific value from a mapping data source.

Delete Document

Tool to delete a specific document by its ID.

Delete Document Type

Tool to permanently delete a document type by its identifier.

Delete Index

Tool to permanently delete an index from Affinda by its name.

Delete Invitation

Tool to delete an invitation by its identifier.

Delete Organization

Permanently deletes an organization from Affinda.

Delete Resthook Subscription

Tool to delete a specific resthook subscription by ID.

Delete Tag

Permanently delete a tag from Affinda by its ID.

Delete Validation Results

Delete multiple validation results in a single API call.

Delete Workspace

Tool to delete a specific workspace by its ID.

Delete Workspace Membership

Tool to remove a user from a workspace by membership ID.

Get All API Users

Tool to retrieve a list of all API users.

Get All Document Splitters

Tool to get a list of all document splitters.

Get All Invitations

Tool to retrieve all invitations you created or sent to you.

Get Organization Memberships

Retrieve all organization memberships across the account.

Get Tags

Tool to list all tags.

Get All Validation Results

Tool to list validation results for documents.

Get Workspace Memberships

Retrieve all workspace memberships across the account.

Get Annotations

Retrieves all annotations for a specific document.

Get Collection

Tool to retrieve details of a specific collection by its ID.

Get Collections

Tool to retrieve a list of all collections.

Get Data Source

Tool to retrieve details of a specific mapping data source by its identifier.

Get Data Source Value

Tool to retrieve a specific value from a mapping data source.

Get Data Source Values

Tool to retrieve all values from a mapping data source.

Get Document

Retrieve full details and parsed data for a specific document by its identifier.

Get Document Redacted

Tool to retrieve the redacted version of a document as a PDF file.

Get Documents

Tool to retrieve a list of all documents.

Get Document Splitter

Tool to retrieve details of a specific document splitter by its identifier.

Get Document Type

Tool to retrieve details of a specific document type by its ID.

Get Document Type JSON Schema

Tool to generate a JSON schema from a document type by its identifier.

Get Document Type Pydantic Models

Tool to generate Pydantic model code from a document type's schema.

Get Document Types

Retrieve all document types accessible to the authenticated user.

Get Extractor

Tool to retrieve detailed information about a specific extractor by its identifier.

Get Extractors

Retrieve all extractors available for an organization.

Get Index Documents

Tool to retrieve all indexed documents for a specific index.

Get Invitation

Tool to retrieve details of a specific organization invitation by its identifier.

Get Job Description Search Config

Tool to get the configuration for the logged in user's embeddable job description search tool.

Get Mapping

Tool to retrieve a specific mapping by its identifier.

Get Organization

Tool to retrieve details of a specific organization by its ID.

Get Organization Membership

Tool to retrieve details of a specific organization membership by its ID.

Get Organizations

Retrieves all organizations accessible to the authenticated user.

Get Resthook Subscription

Tool to retrieve details of a specific resthook subscription by its ID.

Get RESTHook Subscriptions

Tool to retrieve a list of all RESTHook subscriptions.

Get Tag

Tool to retrieve details of a specific tag by its ID.

Get Usage by Workspace

Retrieves monthly document processing usage statistics for a specific workspace.

Get Workspace

Tool to retrieve details of a specific workspace by its ID.

Get Workspace Membership

Tool to retrieve details of a specific workspace membership by its ID.

Get Workspaces

Tool to retrieve a list of all workspaces.

List Data Points

Tool to retrieve all data points.

List Data Sources

Tool to retrieve the list of all custom mapping data sources.

List Indexes

Tool to retrieve a list of all search indexes.

List Mappings

Tool to retrieve the list of all custom data mappings.

List Occupation Groups

Tool to retrieve the list of searchable occupation groups.

List Resume Search Config

Tool to get the configuration for the logged in user's embeddable resume search tool.

List Resume Search Job Title Suggestions

Tool to get job title suggestions based on provided job title(s).

List Resume Search Skill Suggestions

Tool to get skill suggestions based on provided skills.

Remove Tag from Documents

Remove a tag from multiple documents in a single batch operation.

Replace Data Source Values

Tool to completely replace all values in a mapping data source.

Split Document Pages

Split a document into multiple documents by dividing its pages.

Update Annotation

Tool to update data of a single annotation in Affinda.

Update Collection

Tool to update specific fields of a collection.

Update Data Field For Collection

Tool to update a data field configuration for a collection's data point.

Update Data Source Value

Tool to update an existing value in a mapping data source.

Update Document

Tool to update specific fields of a document.

Update Document Data

Update parsed data for a resume or job description document in Affinda.

Update Document Type

Tool to update a document type by its identifier.

Update Extractor

Tool to update specific fields of an extractor.

Update Index

Tool to update the name of an existing search index.

Update Invitation

Tool to update an organization invitation's role.

Update Job Description Search Config

Tool to update the configuration for the logged in user's embeddable job description search tool.

Update Mapping

Tool to update a specific mapping's settings.

Update Organization

Tool to update specific fields of an organization.

Update Organization Membership

Tool to update an organization membership's role.

Update RESTHook Subscription

Tool to update an existing RESTHook subscription.

Update Resume Search Config

Tool to update the configuration for the logged in user's embeddable resume search tool.

Update Tag

Tool to update data of a tag.

Update Workspace

Tool to update specific fields of a workspace.

FRAMEWORKS

How to build Affinda MCP Agent with another framework

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Affinda MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Affinda MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use Affinda MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Affinda MCP with Claude Cowork

Codex logo

Codex

Use Affinda MCP with Codex

OpenClaw logo

OpenClaw

Use Affinda MCP with OpenClaw

Hermes logo

Hermes

Use Affinda MCP with Hermes

CLI logo

CLI

Use Affinda MCP with CLI

Google ADK logo

Google ADK

Use Affinda MCP with Google ADK

LangChain logo

LangChain

Use Affinda MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Affinda MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Affinda MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Affinda MCP with LlamaIndex

CrewAI logo

CrewAI

Use Affinda MCP with CrewAI

FAQ

Frequently asked questions

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

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

Start with Affinda.It takes 30 seconds.

Managed auth, hosted MCP servers, and every Affinda 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