How to Use the Pappers MCP in Pydantic AI

Get type-safe French registry data in Pydantic AI with runtime validation for your critical compliance workflows.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Pappers MCP to Pydantic AI

Create your Vinkius account to connect Pappers to Pydantic AI — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Pappers with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Type-safe Pappers tools for Pydantic AI

Use `get_french_company_details` to fetch records that are validated against your Pydantic models at runtime. If the API returns malformed data, your agent stops immediately before a bad record poisons your pipeline. You define the expected structure in your code, and the MCP server maps the registry response to your types. It removes the need for manual parsing and keeps your agent code resilient.

Verified financial data ingestion

Pull financial statements via `get_company_financials` and ensure every field matches your strict schema. It gives you the confidence that your agent is making decisions on actual, verified numbers. If a field is missing or the format changes, Pydantic AI raises an error. This prevents silent data corruption that often plagues automated research agents.

Complex registry search for agents

Utilize `get_search_suggestions` to help your agent refine its search queries before calling `search_french_companies`. It ensures your agent is always looking for the right entity. Every tool call is wrapped in the Pydantic AI validation layer. You get a reliable way to query the French business registry while maintaining strict control over the data flowing into your agent.

Setup guide

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

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

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

Every response is checked against your Pydantic schemas at runtime. This forces your agent to handle validation errors if the source data is unexpected.

You can. The server is model-agnostic, providing the same structured data to your Pydantic AI agents regardless of the underlying LLM.

The agent throws a validation error immediately. You catch this in your flow and handle it as a failed lookup rather than an inaccurate result.

It is. The server supports standard transport protocols, and the runtime validation ensures your agent doesn't hallucinate fields from the registry.

The server handles all authentication via a single token. Your data is never persisted; it is retrieved on-demand and validated in memory.

Use it with your favorite AI tools

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