# MCP Server: French Companies (Pappers + Sirene) (`dltik/mcp-server-pappers`) Actor

Apify-hosted MCP server exposing 5 tools for AI agents: search/get/dirigeants/by-NAF/by-city across 26M+ French companies. Backed by official gov API, no key required, $0.01 per tool call.

- **URL**: https://apify.com/dltik/mcp-server-pappers.md
- **Developed by:** [Walid](https://apify.com/dltik) (community)
- **Categories:** AI, Business, Developer tools
- **Features:** Limited permissions
- **Stats:** 9 total users, 1 monthly users, 100.0% runs succeeded, 1 bookmarks
- **User rating**: No ratings yet

## Pricing

$10.00 / 1,000 tool calls

This Actor is paid per event. You are not charged for the Apify platform usage, but only a fixed price for specific events.

Learn more: https://docs.apify.com/actors/running/actors-in-store.md#pay-per-event

## What's an Apify Actor?

An Actor is a serverless cloud program that runs on the Apify platform. It has two run modes.
In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours,
and optionally produces a well-defined JSON output, datasets with results, or files in key-value store.
In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server.

Apify vocabulary and the platform model are defined once, in the agent quickstart at https://apify.com/agents.md.

## How to integrate an Actor?

If asked about integration, you help developers integrate Actors into their projects.
You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready.

Do not guess an integration path. Every one of them is in the agent quickstart at https://apify.com/agents.md: the Apify MCP server, Agent Skills with the Apify CLI, the JavaScript and Python clients, the REST API, and the account-free path for an agent with no human to sign in. It also carries the rule on stating cost before the first paid run.

For examples already wired to this Actor's own input schema, see the [API](#api) section below.

Each client library has reference documentation the quickstart does not restate: [JavaScript/TypeScript](https://docs.apify.com/api/client/js/docs.md) (`npm install apify-client`) and [Python](https://docs.apify.com/api/client/python/docs.md) (`pip install apify-client`).

# README

## Pappers MCP Server — 26M French Companies (SIREN/SIRET) for AI Agents

> Apify-hosted **MCP server** giving AI agents (Claude, Cursor, Continue) instant access to 26M+ French companies via the official Sirene API. Search by name, SIREN, SIRET, NAF code, city, or executive (dirigeant). No API key, no proxy, free official government data. **$0.01 per tool call**.

⭐ **Bookmark this Pappers MCP Server** — Apify ranks actors by bookmarks, so it directly helps the visibility of this server on the Apify Store.

### What is the Pappers MCP Server?

The **Pappers MCP Server** is an Apify actor implementing the [Model Context Protocol](https://modelcontextprotocol.io/) for the [Pappers / Sirene database](https://www.pappers.fr/) — France's official company registry. It exposes 5 tools your AI agent can call to search, fetch, and enrich French company records (Pappers data + Sirene data combined). Backed by the free official endpoint at `recherche-entreprises.api.gouv.fr` — no API key, no rate limit headaches, no proxy.

Use it standalone via the Apify API, or wire it into Claude Desktop / Cursor / Continue.dev as an MCP server to give your agent live B2B intelligence on French companies.

### Use cases

- **B2B prospecting agents** — let your AI agent build SIREN-keyed lead lists by NAF code, city, or executive name.
- **KYC / compliance copilots** — verify SIRET, get registered address, dirigeants, legal form, in one tool call.
- **CRM enrichment bots** — auto-fill missing fields (NAF, GPS, headcount band) on existing France records.
- **Market sizing** — count active companies by NAF, by department, by employee band.
- **Investigative journalism / OSINT** — find all companies of a given executive across France.

### Tools available

| Tool | What it returns |
|---|---|
| `search_companies(query, limit)` | Up to 25 companies matching free-text query |
| `get_company(siren_or_siret)` | One full company record (SIREN-resolved) |
| `find_dirigeants(name, limit)` | Companies linked to a person's name |
| `companies_by_naf(naf_code, limit)` | Companies by activity code (e.g. `62.01Z`) |
| `companies_by_city(city, limit)` | Companies by `libelle_commune` |
| `list_tools` | Free — schema discovery |

### Input

```json
{
  "mode": "call_tool",
  "tool_name": "search_companies",
  "arguments": { "query": "Decathlon", "limit": 5 }
}
```

Set `mode: "list_tools"` to get the full input schema for every tool — that call is free.

### Output

```json
{
  "siren": "306138900",
  "siret": "30613890051571",
  "name": "DECATHLON FRANCE",
  "naf_code": "47.64Z",
  "naf_label": "Commerce de détail d'articles de sport",
  "headquarters": { "city": "VILLENEUVE-D'ASCQ", "postal_code": "59650" },
  "dirigeants": [{ "first_name": "Barbara", "last_name": "MARTIN COIA", "role": "Présidente" }],
  "pappers_url": "https://www.pappers.fr/entreprise/306138900"
}
```

### Pricing

**PAY_PER_EVENT — $0.01 per tool call** (= $10 per 1,000). Free actor starts. The `list_tools` discovery call is free. No charge if a tool returns an error.

### FAQ

**Pappers API or Sirene — which one?** Both. The actor uses `recherche-entreprises.api.gouv.fr`, which fuses Sirene data with INSEE data, executives data (dirigeants), and BODACC events. You get richer records than the raw Sirene API.

**Why MCP instead of a regular scraper?** MCP lets an AI agent *decide* which tool to call dynamically. For deterministic batch enrichment, see the standalone [Pappers / Sirene Scraper](https://apify.com/dltik/pappers-sirene-scraper).

**Does it work in Claude Desktop?** Yes — wire the Apify actor URL as an MCP server and your AI agent gets the 5 tools instantly.

***

⭐ **Found this useful? Bookmark this Pappers MCP Server** — it's the strongest signal for Apify Store ranking.

#### Related actors

- [Pappers / Sirene Scraper](https://apify.com/dltik/pappers-sirene-scraper) — bulk batch version, same data, no MCP wrapper
- [BODACC MCP Server](https://apify.com/dltik/mcp-server-bodacc) — French court announcements (M\&A, distress, new businesses)
- [SEC EDGAR MCP Server](https://apify.com/dltik/mcp-server-sec-edgar) — same pattern for US public companies

License: MIT · Author: [dltik](https://apify.com/dltik)

- [HackerNews MCP Server](https://apify.com/dltik/mcp-server-hackernews) - 30M HN stories + comments
- [Data Gouv FR MCP Server](https://apify.com/dltik/mcp-server-data-gouv) - DPE, DVF, BAN, INSEE - 6 tools

# Actor input Schema

## `mode` (type: `string`):

list_tools (free, returns tool catalog) or call_tool (charged $0.01 per call).

## `tool_name` (type: `string`):

Tool to call. Use mode=list_tools to discover available tools.

## `arguments` (type: `object`):

Arguments for the chosen tool. See list_tools mode for full schema.

## Actor input object example

```json
{
  "mode": "call_tool",
  "tool_name": "search_companies",
  "arguments": {
    "query": "Decathlon",
    "limit": 5
  }
}
```

# API

You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup.

## JavaScript example

```javascript
import { ApifyClient } from 'apify-client';

// Initialize the ApifyClient with your Apify API token
// Replace the '<YOUR_API_TOKEN>' with your token
const client = new ApifyClient({
    token: '<YOUR_API_TOKEN>',
});

// Prepare Actor input
const input = {
    "arguments": {
        "query": "Decathlon",
        "limit": 5
    }
};

// Run the Actor and wait for it to finish
const run = await client.actor("dltik/mcp-server-pappers").call(input);

// Fetch and print Actor results from the run's dataset (if any)
console.log('Results from dataset');
console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`);
const { items } = await client.dataset(run.defaultDatasetId).listItems();
items.forEach((item) => {
    console.dir(item);
});

// 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs

```

## Python example

```python
from apify_client import ApifyClient

# Initialize the ApifyClient with your Apify API token
# Replace '<YOUR_API_TOKEN>' with your token.
client = ApifyClient("<YOUR_API_TOKEN>")

# Prepare the Actor input
run_input = { "arguments": {
        "query": "Decathlon",
        "limit": 5,
    } }

# Run the Actor and wait for it to finish
run = client.actor("dltik/mcp-server-pappers").call(run_input=run_input)

# Fetch and print Actor results from the run's dataset (if there are any)
print(f"💾 Check your data here: https://console.apify.com/storage/datasets/{run.default_dataset_id}")
for item in client.dataset(run.default_dataset_id).iterate_items():
    print(item)

# 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start

```

## CLI example

```bash
echo '{
  "arguments": {
    "query": "Decathlon",
    "limit": 5
  }
}' |
apify call dltik/mcp-server-pappers --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,dltik/mcp-server-pappers"
        }
    }
}
```

The hosted server signs you in with OAuth on first connect, so no API token belongs in this config. Clients without OAuth support can send an `Authorization: Bearer <APIFY_API_TOKEN>` header instead, using a token from API & Integrations in Apify Console (https://console.apify.com/settings/integrations).

## OpenAPI specification

Download the OpenAPI definition: https://api.apify.com/v2/actors/sf6VzJlWzMadaLuzm/builds/VmNfWEZZmwE3CkjCc/openapi.json