How to Use the Pappers MCP in LlamaIndex

Q: Can LlamaIndex query historical Pappers financial records?

Yes, your LlamaIndex agent can call getcompanyfinancials and index the results. This lets you run natural language queries over past balance sheets without manually parsing French financial statements every time.

Q: How is my French registry search history secured when using Pappers with LlamaIndex?

All calls to searchultimatebeneficialowners and other endpoints run through this MCP Server's isolated V8 sandbox. Your search terms, company IDs, and retrieved UBO structures are never cached, ensuring your LlamaIndex corporate intelligence gathering remains confidential.

Turn raw French corporate registry data from Pappers into a searchable knowledge index using LlamaIndex.

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 LlamaIndex

Create your Vinkius account to connect Pappers to LlamaIndex — 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Index French corporate filings with LlamaIndex

Retrieving official documents via `get_company_document` lets your LlamaIndex agent index files directly into your vector store. Reading through Pappers disclosures retrieved by your LlamaIndex agent is a drag when they are buried in legal jargon. Once indexed in your vector store, you do not need to keep querying the live French registry for the same company. You can run LlamaIndex semantic searches over past corporate filings to find hidden details in articles of association without running up your Pappers API bill.

Build LlamaIndex RAG pipelines with Pappers data

Integrating `get_french_company_details` directly into your LlamaIndex RAG pipeline keeps your AI client's answers grounded. Using the Pappers MCP Server inside a LlamaIndex RAG pipeline lets the agent pull verified corporate structures to answer complex compliance questions instead of guessing. The framework takes the raw JSON payload from tools like `search_ultimate_beneficial_owners` and formats it into clean context nodes. This means your LlamaIndex compliance reports are always backed by official, real-time registry facts from Pappers.

Query historical corporate data with LlamaIndex

Exposing `get_company_financials` lets your LlamaIndex agent pull historical records and build a chronological index. Tracking French corporate histories in LlamaIndex requires looking at more than just current registration files. You can query this LlamaIndex vector index to find trends or sudden drops in revenue over the years. By combining live Pappers tool calls with indexed historical data, your LlamaIndex agent gets a complete view of a company's trajectory.

Setup guide

Set up Pappers MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Pappers MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Pappers tools.",
)
response = await agent.run("List recent Pappers data")

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 LlamaIndex

Initialize the basic MCP client with your Vinkius endpoint, then wrap it in `McpToolSpec`. From there, load the tools using `to_tool_list_async()` and pass them to your LlamaIndex agent to start indexing French company data.

Yes, your LlamaIndex agent can call `get_company_financials` and index the results. This lets you run natural language queries over past balance sheets without manually parsing French financial statements every time.

It forces your LlamaIndex agent to pull live data from the French registry using `get_french_company_details` before answering. The retrieved facts are injected directly into the prompt context, keeping the agent grounded.

Yes, you can restrict access using the allowed tools filter in LlamaIndex. If you only want your agent doing basic research, you can limit it to `search_french_companies` and block document downloads.

All calls to `search_ultimate_beneficial_owners` and other endpoints run through this MCP Server's isolated V8 sandbox. Your search terms, company IDs, and retrieved UBO structures are never cached, ensuring your LlamaIndex corporate intelligence gathering remains confidential.

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