Traktamente MCP Server
Provides access to Swedish per diem (traktamente) rates from Skatteverket's official API, enabling queries by country, year, or country code for international travel expense calculations.
README
Traktamente MCP Server
An MCP server that provides access to Swedish traktamente (per diem) rates from Skatteverket's official API.
Features
- 🔍 Query per diem rates by country, year, or country code
- 🌍 Search across all available countries
- 📊 Access official data from Skatteverket
- ⚡ Fast and lightweight implementation using Bun
- 🔒 Type-safe with Zod schema validation
Installation
pnpm install traktamente-mcp
Or with Bun:
bun add traktamente-mcp
Usage
With Claude Desktop
Add this configuration to your Claude Desktop config file:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%/Claude/claude_desktop_config.json
{
"mcpServers": {
"traktamente": {
"command": "npx",
"args": ["traktamente-mcp"]
}
}
}
Restart Claude Desktop, and you'll have access to three new tools:
- get_traktamente - Query per diem rates with filters (country, year, country code)
- get_all_countries - List all available countries
- search_traktamente - Search for countries using regex patterns
With Streamable HTTP (Remote Server)
The server is available as a hosted service at https://traktamente.app/mcp, which you can connect to without installing anything locally.
Claude Code
The easiest way to add the server to Claude Code is using the CLI:
claude mcp add --transport http traktamente https://traktamente.app/mcp
Alternatively, you can manually add it to your Claude Code settings (~/.config/claude/config.json or via UI settings):
{
"mcpServers": {
"traktamente": {
"transport": "http",
"url": "https://traktamente.app/mcp"
}
}
}
Standalone Usage
# Start the server
bun start
# Development mode with hot reload
bun dev
# Test with MCP Inspector (interactive web UI)
bun run inspector
With Docker
The server can run in a Docker container, useful for isolated environments or deployment:
# Build the Docker image
docker build -t traktamente-mcp .
# Run with stdio transport (interactive)
docker run -i traktamente-mcp
# Or use Docker Compose
docker-compose up
Docker with Claude Desktop
To use the Docker container with Claude Desktop, configure it like this:
macOS/Linux: ~/Library/Application Support/Claude/claude_desktop_config.json
{
"mcpServers": {
"traktamente": {
"command": "docker",
"args": ["run", "-i", "--rm", "traktamente-mcp"]
}
}
}
Note: You need to build the Docker image first using docker build -t traktamente-mcp . in the project directory.
Available Tools
get_traktamente
Query traktamente rates with optional filters:
land(string, optional): Country name or regex patternår(string, optional): Yearlandskod(string, optional): Country code (e.g., "US", "GB")limit(number, optional): Maximum number of results (default: 100)offset(number, optional): Pagination offset (default: 0)
get_all_countries
List all countries with available per diem data. No parameters required.
search_traktamente
Search for countries using a regex pattern:
search(string, required): Search term or regex patternlimit(number, optional): Maximum number of results (default: 50)
Development
Prerequisites
- Bun runtime (v1.0.0 or later)
Setup
# Clone the repository
git clone https://github.com/johnie/traktamente-mcp.git
cd traktamente-mcp
# Install dependencies
bun install
# Start development server
bun dev
Testing with MCP Inspector
The MCP Inspector provides an interactive web UI for testing the server:
bun run inspector
This will open a browser where you can test all available tools and see real-time responses.
Data Source
This server fetches data from Skatteverket's official API:
- API URL: https://skatteverket.entryscape.net/rowstore/dataset/70ccea31-b64c-4bf5-84c7-673f04f32505
- Data: Per diem rates for international travel
- Language: Swedish (country names and field names)
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
- Fork the repository
- Create your feature branch (
git checkout -b feature/amazing-feature) - Commit your changes (
git commit -m 'feat: add some amazing feature') - Push to the branch (
git push origin feature/amazing-feature) - Open a Pull Request
Development Guidelines
- Use Bun for all commands (not Node.js or npm)
- Follow the existing code style (enforced by Biome)
- Add tests for new features
- Update documentation as needed
License
MIT © Johnie Hjelm
Support
- Issues: GitHub Issues
- Discussions: GitHub Discussions
Acknowledgments
- Data provided by Skatteverket
- Built with Model Context Protocol SDK
- Powered by Bun
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.