Swemo MCP

🚀 A Swedish Monetary Policy Data MCP Server

This project creates a Model Context Protocol (MCP) server for the data of the Swedish central bank (Riksbank), enabling access to the Riksbank's monetary policy data through a consistent and robust interface.

🚀 Quick Start

This is a Model Context Protocol (MCP) server designed for the data of the Swedish central bank (Riksbank). It offers access to the Riksbank's monetary policy data via a consistent and powerful interface.

✨ Features

• Provides approximately 30 different data series related to monetary policy.
• Supports specifying a particular time - series version (policy cycle) or retrieving the full historical data.
• Easy to integrate, can be used directly in Python code or run via a Docker container.

📦 Installation

⚠️ Important Note

• Python ≥ 3.12 (using typing.TypeAlias/PEP 604 unions)
• Astral uv ≥ 0.2.0

Cloning and setting up the project only requires one command:

uv sync

uv sync installs all the production and development dependencies declared in pyproject.toml, creates a virtual environment if necessary, and locks the same versions for each contributor or CI pipeline.

💻 Usage Examples

Integration with Claude Desktop

Edit your claude_desktop_config.json file to add the Swemo 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 local directory:

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

Restart Claude Desktop after the update.

Using as a Library

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])  # First 5 observations

asyncio.run(main())

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

Docker

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

docker build -t swemo-mcp:latest .

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

If you prefer Docker Compose for development, an example compose.yaml shows how to mount the source directory and hot - reload changes.

Development

1. Set up the environment:

uv sync --dev

2. Run in developer mode:

uv run

3. Rebuild and start the service after making code changes:

uv sync && uv run

⚠️ Important Note

• All code examples in the documentation were tested on Ubuntu 22.04 LTS.
• Ensure that you have installed the latest versions of Python and the dependency management tool.

This project allows developers to easily access the Swedish central bank's monetary policy data, supports multiple integration methods, and provides detailed documentation. Whether running via a Docker container or using the library directly, developers can access these important data sources in a flexible way.