The KOFA MCP server is used to access Norwegian public procurement decision data and supports data synchronization and HTTP services
2 points
6.2K

What is the KOFA MCP Server?

The KOFA MCP server is a specialized data interface that connects to the official database of the Norwegian Public Procurement Board (Klagenemnda for offentlige anskaffelser, KOFA). This board is responsible for handling complaints and appeals related to public procurement. This server transforms these complex legal decision data into a format that is easy to query and analyze, allowing you to obtain key procurement case information without directly accessing the original database or understanding complex legal terms.

How to use the KOFA MCP Server?

The usage process is divided into two main stages: First, you need to synchronize data from KOFA to a local or cloud database through simple commands; then, you can start the server and query this data through the standard MCP protocol (or HTTP interface). The entire process is completed through command-line tools and is easy to configure.

Applicable scenarios

This tool is very suitable for scenarios that require researching the Norwegian public procurement market, analyzing tender disputes, tracking the case history of specific suppliers or procurement agencies, conducting legal or academic research, and any scenario that requires analysis based on actual procurement decision data.

Main Features

Data Synchronization and Scraping
You can obtain the latest procurement decision cases from the official KOFA source through the simple `kofa sync` command. Using the `--scrape` option can further obtain more detailed HTML metadata to make the case information more complete.
MCP Protocol Server
It runs as a standard MCP server and can be seamlessly integrated with AI assistants that support the MCP protocol (such as Claude Desktop), allowing you to directly query procurement data in natural language.
HTTP Interface
In addition to the MCP protocol, an optional HTTP server mode (`--http`) is also provided, which facilitates access and query through web browsers or other HTTP clients, increasing the flexibility of use.
Cloud Data Storage
It supports storing synchronized data in Supabase (a cloud database service), which is convenient for team collaboration, data persistence, and access from different devices. You only need to configure environment variables to enable it.
Status Check
You can quickly view the statistical information of data synchronization, such as the number of synchronized cases, by using the `kofa status` command to help you understand the data status.
Advantages
**Authoritative Data**: Directly connected to the Norwegian official procurement decision database, the information is accurate and reliable.
**Easy to Use**: Transforms the complex legal database into an interface that can be queried through simple commands and natural language.
**Flexible Integration**: Supports both the MCP protocol and HTTP, and can be easily integrated with AI assistants or custom applications.
**Data Portability**: Supports local and cloud (Supabase) storage to adapt to different usage scenarios.
**Open Source and Transparent**: Developed based on Python, the code can be reviewed and the functions can be extended.
Limitations
**Region-Specific**: Only covers Norwegian public procurement cases and is not applicable to other countries or regions.
**Requires Initialization**: You must perform the data synchronization step before use and cannot obtain the latest data in real-time (unless manually updated).
**Depends on External Services**: If you use Supabase cloud storage, you need to register and configure this service additionally.
**Technical Threshold**: Basic command-line operation knowledge is required for initial installation and configuration.

How to Use

Installation
Open the terminal (command-line tool) on your computer and use Python's package management tool pip for installation.
Environment Configuration (Optional)
If you want to store data in the cloud Supabase database, you need to copy the environment configuration file and fill in your Supabase service address and key.
Synchronize Data
Run the synchronization command to download KOFA's case data. It is recommended to use the `--scrape` parameter for the first time to obtain more detailed information.
Start the Server
After the data synchronization is completed, start the MCP server. You can start a pure MCP protocol server or start a server with an HTTP interface for browser access.
Start Querying
After the server is started, you can start querying. If you use the HTTP mode, open your browser and access the server address (usually http://localhost:8080). If integrated with an AI assistant, you can directly ask questions in natural language.

Usage Cases

Market Research: Analyze IT Service Procurement Trends
A software company wants to know what disputes often occur when Norwegian governments at all levels procure IT services in the past two years to evaluate market risks and opportunities.
Supplier Due Diligence
A Norwegian company wants to confirm whether a new subcontractor has been involved in any public procurement violations or complaint cases before cooperating with it.
Legal and Academic Research
A law student is writing a paper on 'The Legality of Emergency Contract Awards in Norwegian Public Procurement' and needs to find relevant actual cases as support.

Frequently Asked Questions

Do I need to run the `kofa serve` command all the time?
How often is the data updated?
Do I have to use Supabase?
Is it normal that `kofa sync --scrape` runs very slowly?
Is this tool official?

Related Resources

KOFA Official Website
The official website of the Norwegian Public Procurement Board, which publishes all official decisions and announcements.
Model Context Protocol (MCP) Official
The official documentation for understanding the MCP protocol, which is the basis for the communication between this server and AI assistants.
Supabase
An open-source alternative to Firebase, providing services such as cloud databases. It is an optional data storage backend for this tool.
Python Package Index (PyPI)
The release page of this tool on PyPI, where you can view the latest version and basic information.

Installation

Copy the following command to your Client for configuration
Note: Your key is sensitive information, do not share it with anyone.

Alternatives

F
Finlab Ai
FinLab AI is a quantitative financial analysis platform that helps users discover excess returns (alpha) in investment strategies through AI technology. It provides a rich dataset, backtesting framework, and strategy examples, supporting automated installation and integration into mainstream AI programming assistants.
6.5K
4 points
A
Apify MCP Server
The Apify MCP Server is a tool based on the Model Context Protocol (MCP) that allows AI assistants to extract data from websites such as social media, search engines, and e-commerce through thousands of ready-to-use crawlers, scrapers, and automation tools (Apify Actors). It supports OAuth and Skyfire proxy payment and can be integrated into MCP clients such as Claude and VS Code through HTTPS endpoints or local stdio.
TypeScript
7.5K
5 points
P
Praisonai
PraisonAI is a production-ready multi-AI agent framework with self-reflection capabilities, designed to create AI agents to automate the solution of various problems from simple tasks to complex challenges. It simplifies the construction and management of multi-agent LLM systems by integrating PraisonAI agents, AG2, and CrewAI into a low-code solution, emphasizing simplicity, customization, and effective human-machine collaboration.
Python
10.4K
5 points
M
Maverick MCP
MaverickMCP is a personal stock analysis server based on FastMCP 2.0, providing professional level financial data analysis, technical indicator calculation, and investment portfolio optimization tools for MCP clients such as Claude Desktop. It comes pre-set with 520 S&P 500 stock data, supports multiple technical analysis strategies and parallel processing, and can run locally without complex authentication.
Python
11.1K
4 points
K
Klavis
Klavis AI is an open-source project that provides a simple and easy-to-use MCP (Model Context Protocol) service on Slack, Discord, and Web platforms. It includes various functions such as report generation, YouTube tools, and document conversion, supporting non-technical users and developers to use AI workflows.
TypeScript
21.7K
5 points
S
Scrapling
Scrapling is an adaptive web scraping library that can automatically learn website changes and re - locate elements. It supports multiple scraping methods and AI integration, providing high - performance parsing and a developer - friendly experience.
Python
15.5K
5 points
A
Apple Health MCP
An MCP server for querying Apple Health data via SQL, implemented based on DuckDB for efficient analysis, supporting natural language queries and automatic report generation.
TypeScript
12.8K
4.5 points
M
MCP Server Airbnb
Certified
MCP service for Airbnb listing search and details query
TypeScript
17.0K
4 points
G
Gitlab MCP Server
Certified
The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.
TypeScript
24.4K
4.3 points
N
Notion Api MCP
Certified
A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.
Python
20.4K
4.5 points
D
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
71.7K
4.3 points
M
Markdownify MCP
Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.
TypeScript
35.3K
5 points
U
Unity
Certified
UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.
C#
32.1K
5 points
F
Figma Context MCP
Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.
TypeScript
65.4K
4.5 points
C
Context7
Context7 MCP is a service that provides real-time, version-specific documentation and code examples for AI programming assistants. It is directly integrated into prompts through the Model Context Protocol to solve the problem of LLMs using outdated information.
TypeScript
98.1K
4.7 points
M
Minimax MCP Server
The MiniMax Model Context Protocol (MCP) is an official server that supports interaction with powerful text-to-speech, video/image generation APIs, and is suitable for various client tools such as Claude Desktop and Cursor.
Python
48.5K
4.8 points
AIBase
Zhiqi Future, Your AI Solution Think Tank
© 2026AIBase