Bring Company Data
to Pydantic AI
Learn how to connect Pappers to Pydantic AI and start using 12 AI agent tools in minutes. Fully managed, enterprise secure, and ready to use without writing a single line of code.
What is the Pappers MCP Server?
Connect your Pappers.fr account to any AI agent and take full control of your French corporate research and business intelligence through natural conversation. Pappers provides the most comprehensive database for French company legal and financial information, and this integration allows you to retrieve detailed profiles (SIREN/SIRET), monitor officer changes, and access official BODACC publications directly from your chat interface.
What you can do
- Company Discovery & Search — Search for French businesses programmatically by name, NAF code, or location to ensure your market research is always synchronized.
- Legal & Compliance Intelligence — Access and monitor officer profiles, ultimate beneficial owners (UBOs), and share capital metadata directly from the AI interface to maintain high-fidelity due diligence.
- Financial Analysis Control — Retrieve key financial metrics including turnover and net income via natural language to track competitor health or qualify B2B leads.
- Official Document Oversight — Access legal documents and monitor BODACC publications using simple AI commands to stay informed about corporate events.
- Operational Monitoring — Track system responses and manage monitored company lists to ensure your business intelligence is always optimized.
How it works
1. Subscribe to this server
2. Enter your Pappers API Key from your account settings at pappers.fr
3. Start querying French corporate data from Claude, Cursor, or any MCP-compatible client
No more manual SIREN searching on government portals. Your AI acts as a dedicated corporate researcher or compliance analyst.
Who is this for?
- Business Analysts — quickly retrieve financial summaries and monitor French market trends without switching apps.
- Legal & Compliance Teams — automate the retrieval of UBO metadata and track officer changes via natural conversation.
- Sales Teams — streamline the qualification of French B2B leads and monitor prospect health directly within the chat.
Built-in capabilities (12)
fr service API. Verify Pappers API status
Get Pappers account details
Access legal documents (Articles of Association)
Get financial data for a company
Get details for a specific establishment
Get details for a French company
Autocomplete search suggestions
Search BODACC publications
List companies in your monitoring list
Search for company directors and managers
Search for companies in France
Search for UBOs
Why Pydantic AI?
Pydantic AI validates every Pappers tool response against typed schemas, catching data inconsistencies at build time. Connect 12 tools through Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code. full type safety, structured output guarantees, and dependency injection for testable agents.
- —
Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application
- —
Model-agnostic architecture. switch between OpenAI, Anthropic, or Gemini without changing your Pappers integration code
- —
Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors
- —
Dependency injection system cleanly separates your Pappers connection logic from agent behavior for testable, maintainable code
Pappers in Pydantic AI
Pappers and 3,400+ other MCP servers. One platform. One governance layer.
Teams that connect Pappers to Pydantic AI through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.
Raw MCP | Vinkius | |
|---|---|---|
| Server catalog | Find and host yourself | 3,400+ managed |
| Infrastructure | Self-hosted | Sandboxed V8 isolates |
| Credential handling | Plaintext in config | Vault + runtime injection |
| Data loss prevention | None | Configurable DLP policies |
| Kill switch | None | Global instant shutdown |
| Financial circuit breakers | None | Per-server limits + alerts |
| Audit trail | None | Ed25519 signed logs |
| SIEM log streaming | None | Splunk, Datadog, Webhook |
| Honeytokens | None | Canary alerts on leak |
| Custom domains | Not applicable | DNS challenge verified |
| GDPR compliance | Manual effort | Automated purge + export |
Why teams choose Vinkius for Pappers in Pydantic AI
The Pappers MCP Server runs on Vinkius-managed infrastructure inside AWS — a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts. All 12 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in Pydantic AI only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
How Vinkius secures
Pappers for Pydantic AI
Every tool call from Pydantic AI to the Pappers MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
Can my AI automatically find the financial details for a company by its SIREN?
Yes! Use the get_company_financials tool with the 9-digit SIREN. Your agent will respond with complete metadata, including turnover, profit, and debt ratios in seconds.
How do I find my Pappers API Key?
Log in to your Pappers account, navigate to the API Subscription page, and you will find your unique secret token there.
Does this work for international companies?
This MCP server specifically targets the Pappers France API. For international European company data, Pappers provides a separate API (pappers.in).
How does Pydantic AI discover MCP tools?
Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.
Does Pydantic AI validate MCP tool responses?
Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.
Can I switch LLM providers without changing MCP code?
Absolutely. Pydantic AI abstracts the model layer. your Pappers MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.
MCPServerHTTP not found
Update: pip install --upgrade pydantic-ai