How to Use the Pappers MCP in LangChain

Run deep due diligence on French corporations by linking Pappers registry tools directly into your LangChain reasoning loops.

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 LangChain

Create your Vinkius account to connect Pappers to LangChain — 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Chain French corporate lookups in LangChain

This MCP Server exposes `search_french_companies` to let your LangChain agent find French businesses instantly. Your LangChain agent grabs the registration code and immediately passes that ID to `get_french_company_details` without you writing a single line of glue code. LangSmith catches every step of this process, showing you the exact inputs and outputs of each Pappers tool. If a French company looks shady, your LangChain agent automatically triggers `search_ultimate_beneficial_owners` to map out who actually pulls the strings behind the scenes.

Track French corporate events via LangChain agents

Pulling recent official filings is straightforward when using the `list_bodacc_publications` tool inside your LangChain chain. You no longer need to check French registry sites manually and hope you didn't miss something in Pappers. Because LangChain handles state transitions naturally, your agent can compare these fresh Pappers filings against previous runs. It flags new bankruptcies or ownership changes instantly, saving your LangChain pipeline from manual registry monitoring.

Inspect financial health in multi-tool chains

Accessing raw financial data via `get_company_financials` lets your LangChain agent bypass manual French registry data entry entirely. Your LangChain agent extracts balance sheets directly and feeds them straight into your analytical chains. You can combine this with `get_company_document` to pull the actual articles of association when the LangChain agent flags weird numbers. The LangChain agent handles the whole sequence, giving you a complete picture of a French company's financial status in seconds.

Setup guide

Set up Pappers MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Pappers tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "pappers-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Pappers transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

You start by installing the LangChain MCP adapter package and initializing the multi-server client. After that, pull the tools with `client.get_tools()` and pass them directly to your LangChain agent to run queries like `search_french_companies`.

Yes, LangChain chains do this naturally. Your LangChain agent can take the output of `search_french_companies`, extract the registration number, and pipe it straight into `get_company_financials` in a single run.

LangSmith traces every single call your LangChain agent makes to the French registries. You will see the exact parameters sent to `search_ultimate_beneficial_owners` and the raw JSON payload returned, making it easy to debug failed lookups.

Absolutely, you can mix and match. Your LangChain agent can query French corporate data using `get_french_company_details` and then instantly send those details to a CRM database or an email tool in the same chain.

Your queries go straight to the Pappers API via the secure Vinkius sandbox. No sensitive company registration numbers or financial document requests are stored on our servers, keeping your LangChain compliance investigations strictly private.

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