How to Use the EPO Open Patent Services MCP in Pydantic AI

Q: How do I set up the EPO Open Patent Services toolset with Pydantic AI?

You just instantiate the MCPToolset with your Vinkius server URL and pass it to your agent's toolsets list. Pydantic AI handles the rest, including fetching the tool definitions and validating all inputs and outputs.

Q: What happens if the EPO API changes its response format for getpatentlegalstatus?

Your Pydantic AI agent will immediately throw a ValidationError on the first call after the change. You'll know exactly which field is wrong, instead of discovering the problem later through corrupted data. It makes your system robust.

Get type-safe, validated patent data from the EPO into your Pydantic AI agent. No more guessing API response schemas.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect EPO Open Patent Services MCP to Pydantic AI

Create your Vinkius account to connect EPO Open Patent Services 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 EPO Open Patent Services with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run Searches with Guaranteed Structure

The `search_epo_patents` tool lets your agent query the EPO database. But when you use it with Pydantic AI, it's different. The response isn't just a JSON blob; it's an object that has been validated against a strict schema. If the EPO API ever returns something unexpected, your code will raise a `ValidationError` immediately. You won't have to debug silent data corruption downstream. This is how you build reliable systems, and this MCP server makes it possible.

Type-Safe Data Models

Use `get_patent_bibliographic` and `get_patent_legal_status` to fetch specific details for a patent. Your Pydantic AI agent gets back clean, typed data models. You get IDE autocompletion and static analysis for patent data. Imagine getting a patent's filing date and it's actually a `datetime` object, not a string you have to parse. That's what this setup does. It makes working with the EPO data as safe as your own models. This MCP server provides the bridge.

Reliable API Checks for Pydantic AI

The `check_api_status` tool confirms the EPO service is up. In a Pydantic AI context, the response is a validated boolean or simple status model. It's a small thing, but it means every single interaction with the API is type-checked. You can build this check into a pre-flight routine for your agent. Before it starts a batch job of `search_epo_patents` calls, it verifies the service is healthy. This prevents a cascade of failed requests and makes your agent's behavior predictable.

Setup guide

Set up EPO Open Patent Services 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": {
        "epo-open-patent-services-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent EPO Open Patent Services 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 EPO Open Patent Services. 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 EPO Open Patent Services 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 EPO Open Patent Services MCP in Pydantic AI

Pydantic AI automatically validates the JSON response from every tool call against a Pydantic model. If the data from `get_patent_bibliographic` is missing a field or has the wrong type, your code will raise an exception instantly.

Yes. Pydantic AI is model-agnostic. This MCP server handles the connection to the EPO patent data, and you can plug that into an agent powered by any LLM you choose.

You just instantiate the `MCPToolset` with your Vinkius server URL and pass it to your agent's `toolsets` list. Pydantic AI handles the rest, including fetching the tool definitions and validating all inputs and outputs.

Your Pydantic AI agent will immediately throw a `ValidationError` on the first call after the change. You'll know exactly which field is wrong, instead of discovering the problem later through corrupted data. It makes your system robust.

Your agent's queries are proxied to the EPO's public database. The server processes request details like patent numbers to fetch the corresponding public bibliographic and legal status data. No query data is retained on our servers.

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