Kulturerbe

Model Context Protocol (MCP) server for searching Austrian Cultural Heritage via the Kulturpool API.

python

1

GitHub Stars

python

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "rklugsederoeaw-kulturpool_mcp_server": {
      "command": "wsl",
      "args": [
        "-e",
        "/home/username/kulturerbe_mcp/run_server.sh"
      ],
      "env": {
        "PATH": "/home/username/kulturerbe_mcp/.venv/bin:$PATH",
        "VIRTUAL_ENV": "/home/username/kulturerbe_mcp/.venv"
      }
    }
  }
}

You can access Austria’s Kulturpool cultural heritage data securely via this MCP server, using a progressive six-tool architecture to explore, filter, and retrieve detailed cultural object information and assets. It is designed for efficient context window usage, rate limiting, and safe interactions with the Kulturpool API.

How to use

Start by running the MCP server locally or via your MCP client, then use the six tools in sequence to explore, filter, and retrieve data. Begin with a broad exploration to understand available facets, then narrow results with targeted filters. Retrieve related objects, discover institutions, view institution details, and finally fetch optimized image assets when needed.

How to install

Prerequisites: Python 3.8 or higher, pip, and Git.

Step 1: Clone the project and enter the directory.

git clone https://github.com/yourusername/kulturerbe_mcp.git
cd kulturerbe_mcp

Additional setup steps

Step 2: Create and activate a virtual environment.

# Windows
python -m venv .venv
.venv\Scripts\activate

# Linux/WSL/macOS
python3 -m venv .venv
source .venv/bin/activate

Install dependencies and test the server

Step 3: Install dependencies.

pip install -r requirements.txt

Run the server for testing

Step 4: Start the server.

# Windows
python server.py

# Linux/WSL/macOS
python3 server.py

Available tools

kulturpool_explore

Initial exploration endpoint that returns facet counts by institution, type, and time period with a small sample of results.

kulturpool_search_filtered

Targeted search with comprehensive filters, returning up to 20 results.

kulturpool_get_details

Content-based search to find related objects given a set of object IDs (up to 3 IDs per request).

kulturpool_get_institutions

Complete institution directory with locations available for browsing.

kulturpool_get_institution_details

Detailed metadata for a single institution.

kulturpool_get_assets

Access optimized image assets with transformations (width, height, format, quality, fit).