How to Use the Extracta MCP in Pydantic AI

Q: How does Pydantic AI ensure type safety with Extracta?

Your agent calls getresults to fetch the JSON payload, which Pydantic AI then parses directly into a strongly-typed Python model. This guarantees that your extraction data always matches your application's expected structure.

Q: Can I validate document categories using Extracta and Pydantic AI?

Yes, use createclassification to define your document types, then check getclassificationresults which Pydantic AI validates against a Python Enum to ensure strict routing.

Q: How do I initialize the Extracta MCP Server in Pydantic AI?

Register the server using the MCPToolset with your Vinkius endpoint URL. Pass this toolset to your Pydantic AI Agent to expose tools like uploadfileurl for document processing.

Q: What tool do I use to remove old schemas?

Use deleteextraction to clean up configurations. Once deleted, any calls to process files against that extraction ID will result in a validation error.

Validate every document extraction against strict Pydantic schemas using Pydantic AI and Extracta.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Extracta MCP to Pydantic AI

Create your Vinkius account to connect Extracta 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 Extracta with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe document parsing with Pydantic AI and Extracta

`create_extraction` is the tool used to register your target fields with the extraction engine. This MCP tool sets up the schema that your agent will use to process incoming files. When your agent calls `get_results`, Pydantic AI validates the returned JSON against your Python models at runtime. If the engine returns an unexpected field format, the agent fails immediately to prevent data corruption.

Strict document classification validation

`create_classification` defines the document categories your pipeline expects. You pass the target classes directly through your type-safe MCP agent configuration. The agent queries `get_classification_results` to get the predicted category. Pydantic AI ensures the returned string matches your defined Enum before routing the document further.

Audit your extraction schemas safely

`view_extraction` fetches the exact configuration of an active extraction process. This lets your agent check if the remote schema matches your local Pydantic models. If there is a mismatch, the agent can call `update_extraction` to align the remote configuration with your updated Python code.

Setup guide

Set up Extracta 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": {
        "extracta-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Extracta 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 Extracta. 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 Extracta 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 Extracta MCP in Pydantic AI

Your agent calls `get_results` to fetch the JSON payload, which Pydantic AI then parses directly into a strongly-typed Python model. This guarantees that your extraction data always matches your application's expected structure.

Yes, use `create_classification` to define your document types, then check `get_classification_results` which Pydantic AI validates against a Python Enum to ensure strict routing.

Register the server using the `MCPToolset` with your Vinkius endpoint URL. Pass this toolset to your Pydantic AI Agent to expose tools like `upload_file_url` for document processing.

Use `delete_extraction` to clean up configurations. Once deleted, any calls to process files against that extraction ID will result in a validation error.

Extracta processes document files to extract structured JSON data according to your schema. Vinkius ensures secure transmission via ephemeral MCP isolates, meaning your document contents are processed in memory and never stored persistently on the platform.

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