Riksdag-Regering
MCP-server that provides LLMs with easy access to open data from the Swedish Government Offices and Parliament.
claude mcp add --transport stdio isakskogstad-riksdag-regering-mcp npx riksdag-regering-mcp
How to use
Riksdag-Regering MCP-server provides access to 32 specialized tools that fetch and aggregate open data from Sweden's Parliament (Riksdagen) and the Government Offices (Regeringskansliet). The server is built as a Node.js package that can be used remotely or locally. When connected through MCP-compatible clients, you can query for members, parliamentary documents, speeches, votes, and government documents (such as SOU, propositions, and press releases) in real-time. The npm package version is designed to be easy to install and update, while the remote host option allows you to start using the service immediately without any installation. Use the provided tools to cross-reference documents and extract relevant information for research, compliance, or application development.
How to install
Prerequisites:
- Node.js 20+ (for local development) or npm (for package installation)
- Git (for cloning the source repository, if you wish to modify the server)
Installation options:
Option A - Global install from npm (recommended for developers):
# Install globally
npm install -g riksdag-regering-mcp
Option B - Local install in a project:
npm install riksdag-regering-mcp
Option C - Local development from source:
# Clone repository
git clone https://github.com/KSAklfszf921/Riksdag-Regering.AI.git
cd Riksdag-Regering.AI
# Install dependencies for MCP server
npm run mcp:install
# Build and start (mcp server)
cd mcp
npm run build
npm start
STDIO configuration (for Claude Desktop, as shown in the README):
{
"mcpServers": {
"riksdag-regering": {
"command": "node",
"args": ["/abs/path/to/Riksdag-Regering.AI/mcp/dist/index.js"]
}
}
}
Option D - Remote usage (no installation):
# Use the remote MCP server via Claude, ChatGPT, or Codex integrations as described in the README
Additional notes
Notes and tips:
- The server relies on open data sources from Riksdagen (data.riksdagen.se) and g0v.se for Regeringskansliet data. Ensure you have network access to these APIs.
- If you run locally, you can customize the config or extend the server with additional tools using the MCP SDK.
- The health endpoint for the remote server is available at /health; monitor it to ensure uptime when deploying in production.
- When using the npm package locally, you can run the server in different environments (development, production) by setting standard Node.js environment variables (e.g., NODE_ENV).
- If you need to run the server behind a proxy or load balancer, ensure appropriate CORS settings and firewall rules allow MCP clients to access the HTTP interface.
- For debugging, consult the MCP logs (Winston-based) to trace tool queries and data sources used for responses.
Related MCP Servers
flyto-core
The open-source execution engine for AI agents. 412 modules, MCP-native, triggers, queue, versioning, metering.
turbular
A MCP server allowing LLM agents to easily connect and retrieve data from any database
mcp-typescribe
An MCP server implementation enabling LLMs to work with new APIs and frameworks
mockloop
Intelligent Model Context Protocol (MCP) server for AI-assisted API development. Generate mock servers from OpenAPI specs with advanced logging, performance analytics, and server discovery. Optimized for AI development workflows with comprehensive testing insights and automated analysis.
mcp
🌐 MCP Server for Semantic Search of Macro Data for Quant Research AI Agents
Skolverket
MCP server for Swedish National Agency for Education (Skolverket) open data. Tuned for LLMs to query, parse, and integrate info, data, and stats from three public API endpoints.