How do I find my Affinda API Key?

Log in to Affinda, click on your profile avatar, and go to **Settings** > **API Keys**. You can generate a new token there. Remember to copy it immediately, as it is only shown once.

What document types are supported?

Affinda supports dozens of specialized models including Resumes, Invoices, Receipts, Passports, Driver Licenses, and Purchase Orders. Use the `list_document_types` tool to see the full list for your account.

Can I parse a document via a public URL?

Yes! The `create_document` tool accepts a `url` parameter. Simply provide the direct link to the PDF or image, and Affinda will retrieve and parse it automatically.

Affinda MCP Server for Pydantic AI 5 tools — connect in under 2 minutes

Name: Affinda
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 5 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Affinda through Vinkius and every tool is automatically validated against Pydantic schemas. catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to Affinda "
            "(5 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Affinda?"
    )
    print(result.data)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Affinda MCP Server

Connect your Affinda account to your AI agent to unlock powerful intelligent document processing (IDP). From automatically extracting details from resumes and invoices to auditing document statuses across your workspaces, your agent handles structured data extraction through natural conversation.

Pydantic AI validates every Affinda tool response against typed schemas, catching data inconsistencies at build time. Connect 5 tools through Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code. full type safety, structured output guarantees, and dependency injection for testable agents.

What you can do

Automated Document Parsing — Upload PDFs or images of resumes, invoices, and passports for high-accuracy JSON extraction
Workspace Oversight — List and audit documents within your specific workspaces to maintain organizational control
Extraction Model Management — List available document types (Resume, Invoice, Receipt, etc.) supported by your account
Real-time Status Tracking — Retrieve the parsing status and technical metadata for any uploaded document
Metadata Insights — Quickly identify processing errors or missing data across your document library directly from chat

The Affinda MCP Server exposes 5 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Affinda to Pydantic AI via MCP

Follow these steps to integrate the Affinda MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 5 tools from Affinda with type-safe schemas

Why Use Pydantic AI with the Affinda MCP Server

Pydantic AI provides unique advantages when paired with Affinda through the Model Context Protocol.

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

Model-agnostic architecture. switch between OpenAI, Anthropic, or Gemini without changing your Affinda integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your Affinda connection logic from agent behavior for testable, maintainable code

Affinda + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the Affinda MCP Server delivers measurable value.

Type-safe data pipelines: query Affinda with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple Affinda tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query Affinda and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock Affinda responses and write comprehensive agent tests

Affinda MCP Tools for Pydantic AI (5)

These 5 tools become available when you connect Affinda to Pydantic AI via MCP:

create_document

Defaults to synchronous waiting for the output. Upload and parse a PDF or image into Affinda via its public URL for high-accuracy JSON extraction

get_document

Retrieve the fully structured JSON data and status for a specific processed document in Affinda

list_document_types

Retrieve exactly which parsing models the Affinda account supports (e.g. Resume, Invoice, Passport)

list_documents

Retrieve all parsed documents in an Affinda workspace with their processing status

list_workspaces

Retrieve all container workspaces for documents created within your Affinda account

Example Prompts for Affinda in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with Affinda immediately.

"List all documents in my 'HR Recruitment' workspace."

"Parse this resume URL: https://example.com/cv.pdf using the 'resume' model."

"List the available document types in my account."

Troubleshooting Affinda MCP Server with Pydantic AI

Common issues when connecting Affinda to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Affinda + Pydantic AI FAQ

Common questions about integrating Affinda MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer. your Affinda MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.