Riksbank MCP

🚀 A Swedish Monetary Policy Data Server: Kolada MCP

This project is an unofficial MCP (Monetary Policy Protocol) server that provides access to Sveriges Riksbank data. It allows users to query and analyze the Swedish central bank's monetary policy data through modern APIs and toolchains.

✨ Features

• Modern API: Based on Python's asynchronous design, it offers a clean and efficient interface.
• Type Safety: Utilizes Python's type system (e.g., typing.TypeAlias) to ensure code security and maintainability.
• Containerization Support: Provides one - click deployment via Docker, facilitating the integration and management of dependencies.
• Development Toolchain: Integrates various tools including uv, simplifying the process from development to testing.

📦 Installation

Prerequisites

• Python version 3.12 or higher
• Astral's uv tool version 0.2.0 or higher

Install using uv sync

uv sync

This command will install all production and development dependencies of the project, create a virtual environment if necessary, and lock the exact versions of all dependencies to ensure that each contributor or CI pipeline uses the same dependency stack.

Integration with Claude Desktop

Edit your claude_desktop_config.json file to add the Kolada MCP Server:

Docker Image (Locally Built)

"SwemoMCP": {
  "args": [
    "run",
    "-i",
    "--rm",
    "--name",
    "swemo-mcp-managed",
    "swemo-mcp:local"
  ],
  "command": "docker",
  "env": {}
}

Pre - built Container (via PyPI)

"SwemoPyPI": {
  "args": ["swemo-mcp"],
  "command": "/Users/hugi/.cargo/bin/uvx"
}

Local UV Execution (Without Docker)

Replace [path to kolada-mcp] with your actual path:

"SwemoLocal": {
  "args": [
    "--directory",
    "[path to kolada-mcp]/src/kolada_mcp",
    "run",
    "kolada-mcp"
  ],
  "command": "uv"
}

Restart Claude Desktop after the update.

💻 Usage Examples

Basic Usage

import asyncio
from swemo_mcp.tools import get_policy_rate_data

async def main():
    from swemo_mcp.query import ForecastRequest
    req = ForecastRequest(policy_round="2023:4", include_realised=True)
    data = await get_policy_rate_data(req)
    print(data.vintages[0].observations[:5])  # Print the first 5 observations

asyncio.run(main())

Since everything is typed and asynchronous, you can directly integrate the tools into notebooks, dashboards, or other services.

Docker Support

The project provides a multi - stage Dockerfile that uses uv in the final layer, so container builds can benefit from deterministic dependency resolution.

docker build -t swemo-mcp:latest .

docker run -i --rm swemo-mcp:latest | mcp chat

If you prefer to use Docker Compose during development, a sample compose.yaml file shows how to mount the source directory and enable hot reloading.

Development Guide

1. Set up the environment

   uv sync --dev
   

2. Run the server in development mode with live reloading (Requires installation of mcp dev):

   uv run mcp dev src/swemo_mcp/server.py
   

3. Open the MCP monitor for testing and debugging:

   http://localhost:5173

4. Run the test suite (Using pytest and asyncio):

   uv run pytest -q
   

5. Format and check the code automatically using Ruff:

   uv run ruff check . --fix
   

📄 License

The project is released under the Apache 2.0 license. The full license text can be found in the LICENSE file.

Disclaimer

• This is an unofficial MCP server for accessing Sveriges Riksbank data. The underlying API may change, and this project may not always reflect the latest updates.
• Sveriges Riksbank is not involved in the development of this project. The data provided is "as is" without any form of warranty.
• All errors and inaccuracies are the responsibility of the author, and any feedback or corrections are welcome.