Oxenstierna

🚀 Oxenstierna 🦬⭐ (WIP)

Oxenstierna is a project that enables access to the Swedish National Archives (Riksarkivet) through multiple APIs, facilitating operations such as searching for records, downloading images, and more.

🚀 Quick Start

Many MCPs (Machine-Controlled Processes) can be built with the help of the following resources:

• Riksarkivet OAIPMH API Integration
• Riksarkivet IIIF API Integration
• Riksarkivet Search API Integration
• AI-Riksarkviet HTRflow pypi

✨ Features

Current Implementation

This server provides access to the Swedish National Archives (Riksarkivet) through multiple APIs.
    SEARCH-BASED WORKFLOW (start here):
    - search_records: Search for content by keywords (e.g., "coffee", "medical records")
    - get_collection_info: Explore what's available in a collection
    - get_all_manifests_from_pid: Get all image batches from a collection
    - get_manifest_info: Get details about a specific image batch
    - get_manifest_image: Download specific images from a batch
    - get_all_images_from_pid: Download all images from a collection
    URL BUILDING TOOLS:
    - build_image_url: Build IIIF Image URLs with custom parameters
    - get_image_urls_from_manifest: Get all URLs from an image batch
    - get_image_urls_from_pid: Get all URLs from a collection
    TYPICAL WORKFLOW:
    1. search_records("your keywords") → find PIDs
    2. get_collection_info(pid) → see what's available
    3. get_manifest_info(manifest_id) → explore specific image batch
    4. get_manifest_image(manifest_id, image_index) → download specific image
    Example PID: LmOmKigRrH6xqG3GjpvwY3

Tools

• Riksarkivet OAIPMH Metadata API Integration
• Riksarkivet IIIF Image API Integration
• Riksarkivet IIIF Presentation API Integration

Search API

The Search API allows you to search across transcribed text. For example:

• Search UI
• API Request

Note that IIIF content search is not a viable option!

HTRflow

Explore the possibility of performing HTR (Handwritten Text Recognition) on the flow:

• HTRflow MCP on Hugging Face

Schema: https://gabriel-htrflow-mcp.hf.space/gradio_api/mcp/schema

TODO:

• Implement MCP from https://github.com/knaw-huc/pagexml
• Separate content from output file
• Develop a visualizer

Resource

We aim to have resources similar to the following concept:

• https://gradio-docs-mcp.hf.space/

Part of Riksarkivet OAIPMH API Integration can serve as a resource. Also, refer to the IIIF presentation and image API.

📚 Documentation

FastMCP 2.0

Get started with FastMCP 2.0: https://gofastmcp.com/getting-started/welcome

MCP Inspector Integration

Use the inspector for interactive testing and debugging.

Client

Claude Desktop Integration

Document the process of adding the server to Claude Desktop.

Aider

...