How to Use the Airparser MCP in Pydantic AI

Get type-safe Airparser data extraction for your Pydantic AI agent.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Airparser MCP to Pydantic AI

Create your Vinkius account to connect Airparser to Pydantic AI and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Airparser with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Enforce schema safety in Pydantic AI

Define your data models and let the server output match them exactly. Because you use Pydantic models, any malformed JSON from `get_document_details` triggers an immediate validation failure. Your agent stops before it processes bad data. This prevents silent errors from propagating through your system.

Sync documents with Pydantic AI logic

Call `parse_document_sync` to get raw data and wrap it in your Pydantic objects. You define the structure, and the tool fills it with extracted information. This approach gives you total control over what your agent considers valid. You eliminate ambiguity in your document processing pipeline.

Manage webhooks for Pydantic AI

Use `list_webhooks` to monitor your automated export status. If you need to change your data flow, use `create_webhook` to point the server to a new destination. Your agent keeps the infrastructure updated. It ensures your exports stay aligned with the current state of your Pydantic models.

Setup guide

Set up Airparser MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "airparser-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Airparser tools.",
)

result = await agent.run("List recent Airparser transactions")
print(result.output)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Airparser. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Airparser now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Airparser MCP in Pydantic AI

You create a Pydantic class that mirrors the expected JSON structure from the tool. The framework checks the tool response against this class at runtime.

The framework raises a validation error immediately. This forces your agent to handle the discrepancy rather than proceeding with incorrect information.

Yes, you instantiate an MCPToolset with your server URL and include it in your agent configuration. It works across different transport types like SSE.

The server must be running externally, and your agent connects to it via the provided endpoint. This keeps your application logic separate from the extraction process.

Your extracted data is validated against your private models as soon as it enters your agent. This ensures no unverified or corrupt document information ever reaches your core business logic.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript