MCP NIF.PT
Query and analyze Portuguese companies using the NIF.PT public API. Supports search by NIF, company name, and city.
MCP NIF.PT
This project implements an intelligent server based on FastMCP, allowing you to query and analyze information about Portuguese companies using the NIF.PT public API. It supports multiple useful tools such as search by NIF, company name or city, checking company status, and identifying accounting-related businesses.
Features
- Retrieve complete company data by NIF
- Check if a company is active or closed
- Identify if a company is related to accounting
- Search companies by name and city
- Get the NIF based on the exact company name
- Access external links (Google Maps, Racius, Portugalio)
Project Structure
.
├── main.py
├── models.py
├── nif_client.py
├── utils.py
├── requirements.txt
├── Dockerfile
├── package.json
└── .smithery.profile.json
Technologies Used
- FastMCP
- FastAPI
- httpx
- Pydantic
- Docker
- Python 3.10+
How to Run
Locally
python3 -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt
python main.py
The application uses transport="stdio" by default, making it compatible with Claude Desktop or terminal-based environments.
Usage Examples
- Qual é a empresa com o NIF 504426744?
- A empresa com o NIF 504426744 está ativa?
- A empresa com o NIF 504426744 é de contabilidade?
- Procurar empresas com o nome "contabilidade" em Lisboa
- Qual é o NIF da empresa "XPTO LDA"?
Output Format
The responses include details such as:
- Nome, cidade, atividade e estado
- Morada com link para Google Maps
- Contactos (telefone, email, website)
- CAE (Código de Atividade Económica)
- Ligações externas (Racius, Portugalio)
Claude Desktop Integration
To integrate this MCP with Claude Desktop:
-
Install Claude Desktop
Download and install from: https://claude.ai/download -
Open Configuration
Go toFile > Settings > Developerand click Edit Configuration -
Add the MCP server configuration
In theclaude_desktop_config.json, insert the following configuration:
{
"mcpServers": {
"nif-pt-server": {
"command": "uv",
"args": [
"--directory",
"/ABSOLUTE/PATH/TO/YOUR/PROJECT/FOLDER",
"run",
"main.py"
]
}
}
}
Replace
/ABSOLUTE/PATH/TO/YOUR/PROJECT/FOLDERwith the actual absolute path where yourmain.pyfile is located.
- Restart Claude Desktop
After saving the configuration, restart Claude Desktop. Yournif-pt-serverMCP should now be available in the Claude Desktop interface.
One-Click Installation via Smithery
(https://smithery.ai/server/@ruicarvalho1/mcp_nif)
With Claude Desktop open, you can install this MCP directly using the Smithery CLI.
Just paste the following command into your terminal:
npx -y @smithery/cli@latest install @ruicarvalho1/mcp_nif --client claude
This will automatically install the MCP and register it with Claude Desktop.
Author
Developed by Rui Carvalho.
License
This project is licensed under the MIT License.
相關伺服器
NS Travel Information MCP Server
Access real-time travel information for the Dutch railways (NS).
招投标大数据服务
Provides comprehensive bidding and tender information query services, including statistics, searches, and planned project queries.
Movie Search Tool
A search tool for movies and TV shows that provides AI clients with validated, playable video links and supports real-time notifications.
MCP Domain Availability Checker
Check the availability of domain names across over 50 popular TLDs using DNS and WHOIS verification.
招投标大数据服务
Query comprehensive enterprise information from e-commerce platforms, including store details, sales data, and product statistics.
ArtistLens
Access the Spotify Web API to search and retrieve information about tracks, albums, artists, and playlists.
Azure AI Agent & Search
Search content using Azure AI Agent Service and Azure AI Search.
arch-mcp
An AI-powered bridge to the Arch Linux ecosystem that enables intelligent package management, AUR access, and Arch Wiki queries through the Model Context Protocol (MCP).
Tavily MCP Server
Web search using the Tavily API.
SmartHomeExplorer Product Intelligence
Smart home product intelligence for AI assistants. 1,080+ products with consensus scores from 12 expert sources, cross-ecosystem compatibility engine, and 340+ buying guides.