How do I use INSEE MCP Server?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@INSEE MCP Server search for company with SIRET 44302124100072" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

INSEE MCP Server

by KerryanOPMace

Overview Schema Related Servers Score Discussions

Python

Remote

INSEE MCP Server

MCP (Model Context Protocol) server for accessing INSEE data via the SIRENE API, BDM, and official nomenclatures.

One-line Installation

With uv (recommended)

# Install and launch directly
API_KEY="your_insee_api_key" uv run --with insee-mcp insee-mcp

or if you prefer to use uvx

# Install and launch directly
API_KEY="your_insee_api_key" uvx insee-mcp insee-mcp

Standard MCP Configuration

Add this to your MCP configuration (e.g., Claude Desktop, or Copilot):

{
  "mcpServers": {
    "insee": {
      "command": "uvx",
      "args": ["insee-mcp", "insee-mcp"],
      "env": {
        "API_KEY": "your_insee_api_key"
      }
    }
  }
}

With pipx

API_KEY="your_insee_api_key" pipx run --spec git+https://github.com/KerryanOPMace/mcp-insee.git insee-mcp

Related MCP server: mcp-insee-entreprises

Quick Installation

Direct Installation (recommended)

# Install directly from GitHub
pip install git+https://github.com/KerryanOPMace/mcp-insee.git

# Set your INSEE API key
export API_KEY="your_insee_api_key"

# Start the server
insee-mcp

Installation with pipx (isolated)

# Install with pipx (isolated environment)
pipx install git+https://github.com/KerryanOPMace/mcp-insee.git

# Set the API key
export API_KEY="your_insee_api_key"

# Start the server
insee-mcp

Developer Installation

# Clone the repository
git clone https://github.com/KerryanOPMace/mcp-insee.git
cd mcp-insee

# Install in development mode
pip install -e .

If you wish to contribute to the project, please create issues and branches. You can merge request and then a supervisor will review it before merging

Configuration

INSEE API Key

You must obtain an API key from the INSEE API portal and configure it:

Linux/Mac:

export API_KEY="your_insee_api_key"

Windows (PowerShell):

$env:API_KEY="your_insee_api_key"

Windows (CMD):

set API_KEY=your_insee_api_key

Available Tools

search_company: Search for companies in the SIRENE database
- By SIREN, SIRET, or company name
- Fuzzy search available

STREAMABLE-HTTP TRANSPORT

Server Access

Once started, the MCP server is accessible at:

URL: http://127.0.0.1:8000/mcp
Transport: Streamable HTTP

Client Test

from fastmcp import Client
import asyncio

async def test():
    client = Client("http://127.0.0.1:8000/mcp")
    async with client:
        # List tools
        tools = await client.list_tools()
        print(tools)
        
        # Search for a company
        result = await client.call_tool("search_company", {
            "siret": "44302124100072"
        })
        print(result)

asyncio.run(test())

Requirements

Python 3.8+
Valid INSEE API key
Internet access for API requests

STDIO TRANSPORT

Server Access

Once started, the MCP server runs locally according to the standard io protocol

Client Test

from fastmcp import Client
import asyncio

async def test():
    client = Client("http://127.0.0.1:8000/mcp")
    async with client:
        # List tools
        tools = await client.list_tools()
        print(tools)
        
        # Search for a company
        result = await client.call_tool("search_company", {
            "siret": "44302124100072"
        })
        print(result)

asyncio.run(test())

Requirements

Python 3.8+
Valid INSEE API key
Internet access for API requests

License

MIT License

Available Tools

1 tool

search_companyB

Recherche une entreprise dans la base SIRENE selon SIREN, SIRET ou nom.

ParametersJSON Schema

Name	Required	Description
`company_name`	No	Nom de l'entreprise.
`siren`	No	Code SIREN.
`siret`	No	Code SIRET.
`fuzzy`	No	Active la recherche approximative si nom partiel.

TDQS

B3.1/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description must disclose behavioral traits. It only states 'search' but does not clarify whether exact or fuzzy matching is default, how results are returned, or any side effects. The fuzzy parameter is in the schema but not highlighted in the description.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single concise sentence in French, efficient and to the point. However, it could be slightly more structured by separating the search criteria or mentioning the database context more explicitly.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 4 parameters, no output schema, and no annotations, the description is incomplete. It does not explain the search behavior when multiple parameters are provided, the structure of results, or any limitations. More details are needed for complete understanding.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so baseline is 3. The tool description adds no extra meaning beyond the schema's parameter descriptions, which are adequate but minimal. No additional context is provided for parameter usage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'search' and the resource 'company in the SIRENE database' along with the search criteria (SIREN, SIRET, or name). It is specific enough to distinguish from generic search tools, though no siblings are provided.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies the tool is used to search for companies using the given identifiers but does not provide explicit guidance on when to use each parameter or when to avoid this tool. No alternatives are mentioned, which is acceptable without siblings.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

B3.2/5.0

Disambiguation5/5

With only one tool, there is no ambiguity. The agent cannot confuse it with any other tool.

Naming Consistency5/5

Single tool name 'search_company' follows a clear verb_noun pattern, consistent within itself.

Tool Count2/5

A single search tool is too sparse for a domain like INSEE company data, which typically requires multiple operations (e.g., get details, list results, paginate).

Completeness1/5

The server covers only a basic search, missing essential operations like retrieving full company details, filtering, or pagination, making it severely incomplete for practical use.

Maintenance

ActivityInactive

ResponsivenessNo issues

Resources

GitHub Repository

Need Help?

Related Servers

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Insee A
io.github.pipeworx-io
INSEE MCP — France's SIRENE business registry (INSEE).
Government Data Open Data
322
insourcia A
io.insourcia
Search French companies: financials, directors, ownership, M&A and insolvency events.
Finance Search Research & Data
181
Sirenic A
eu.sirenic
French & European company registry for AI agents: KYB, sanctions, annual accounts. x402, no API key.
Government Data Open Data
772
Dataroia Data Trust A
com.dataroia
Vérification B2B française : SIRET, SIRENE, dirigeants RNE, santé d'entreprise. Hébergé en France.
Government Data Open Data Databases
82

Related MCP Servers

MCP Recherche d'entreprises
Government Data Search
yoanbernabeu
A
license
B
quality
F
maintenance
Enables interaction with the French business search API from data.gouv.fr, allowing users to search for French companies by text or geographical criteria and access essential business information.
Updated 6 months ago (2026-02-26 10:40 UTC)
2
18
19
MIT
mcp-insee-entreprises
Government Data Open Data Search
DavidScanu
F
license
Not graded
quality
D
maintenance
MCP server to query the INSEE SIRENE API and search for French companies, supporting searches by SIREN, SIRET, and advanced filters like name, location, and activity.
Updated 8 months ago (2026-01-05 10:00 UTC)
1
mcp-recherche-entreprise
Government Data Open Data
thomas-servais
F
license
Not graded
quality
D
maintenance
Enables searching for French companies using the official data.gouv.fr API, with filters for name, location, activity, and certifications.
Updated a year ago (2025-07-20 19:46 UTC)
1
France Business Intelligence
Government Data Open Data Search
fzthiait-ai
F
license
Not graded
quality
C
maintenance
Enables AI agents to search and retrieve detailed profiles of 25 million French companies from the official government registry, including directors, activity codes, and establishment data, without requiring an API key.
Updated 2 months ago (2026-07-12 17:10 UTC)

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/KerryanOPMace/mcp-insee'

If you have feedback or need assistance with the MCP directory API, please join our Discord server

INSEE MCP Server

One-line Installation

With uv (recommended)

Standard MCP Configuration

With pipx

Quick Installation

Direct Installation (recommended)

Installation with pipx (isolated)

Developer Installation

Configuration

INSEE API Key

Available Tools

STREAMABLE-HTTP TRANSPORT

Server Access

Client Test

Requirements

STDIO TRANSPORT

Server Access

Client Test

Requirements

License

Available Tools

TDQS

TDQS

Maintenance

Resources

Looking for Admin?

Related MCP Connectors

Related MCP Servers

MCP Recherche d'entreprises

mcp-insee-entreprises

mcp-recherche-entreprise

France Business Intelligence

Latest Blog Posts

MCP directory API