How to Use the Alphamoon MCP in Pydantic AI

Q: How do I configure Alphamoon for Pydantic AI?

Install the slim package with MCP extras. Create an MCPToolset pointing to your Vinkius HTTP endpoint. Pass it to the toolsets array in your Agent definition.

Q: How do I list processed documents in Pydantic AI using Alphamoon?

Your agent calls the listdocumentsbyprocess tool. It returns an array of document IDs that the framework automatically validates against your schema.

Build strict, type-safe OCR agents that extract form data using Alphamoon and Pydantic AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Alphamoon MCP to Pydantic AI

Create your Vinkius account to connect Alphamoon 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 Alphamoon with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe OCR with Pydantic AI

Getting raw text from images requires the `get_ocr_results` tool. Pydantic AI intercepts the server response and validates the payload against your defined schemas. If the API returns a string instead of an array, the framework throws a loud validation error. Sending files happens via `upload_document`. Your agent pushes the PDF, and the strict typing guarantees the file path and metadata match the exact expected format. This prevents silent failures in the middle of long extraction jobs.

Extract precise invoice fields

The `get_extraction_results` tool pulls totals and dates from your documents. Because Pydantic AI forces strict schemas, your agent never hallucinates missing invoice numbers. Failure happens immediately if the data mismatches the model. You configure extraction rules using `list_templates` and `get_template`. The agent queries the available schemas and maps them to your local models. Working across different LLMs changes nothing about this validation process.

Track document pipelines securely

Monitoring extraction jobs relies on `list_processes` and `get_process`. The agent checks the status of your batch uploads and updates your local database. Every status update passes through the same rigorous runtime validation. Deleting records takes a single call to `delete_document`. You pass the unified `MCPToolset` to your agent, ensuring the MCP connection remains stable. The system verifies connectivity using `check_alphamoon_status` before any destructive actions occur.

Setup guide

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

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

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

Install the slim package with MCP extras. Create an `MCPToolset` pointing to your Vinkius HTTP endpoint. Pass it to the `toolsets` array in your Agent definition.

The framework throws a runtime validation error. Your agent stops execution immediately rather than passing malformed OCR data downstream.

Yes. Pydantic AI is completely model-agnostic. You can extract invoice data using OpenAI today and switch to a local model tomorrow without changing your tool configuration.

Your agent calls the `list_documents_by_process` tool. It returns an array of document IDs that the framework automatically validates against your schema.

The V8 isolate sandbox isolates every OCR request. Vinkius destroys the execution environment right after the text parsing finishes. No personal information from your forms stays on the server.

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