Oxenstierna MCP: Integrate Multiple APIs for Easy Access to Swedish National Archives & HTR Process Exploration

Oxenstierna

This project aims to provide access to the content of the Swedish National Archives (Riksarkivet) through multiple API interfaces (such as OAI - PMH, IIIF, and Search API), including functions such as searching for records, obtaining collection information, downloading images, etc., and exploring the real - time handwritten text recognition (HTR) process.

Research and data Art and culture #Archive Access #Image Processing #Text Recognition #API Integration .Python

rating : 2.5 points

downloads : 6.4K

update time : 2025-07-23

Open Site

What is the Oxenstierna MCP Server?

The Oxenstierna MCP server is a tool based on the Model Context Protocol (MCP) that allows users to access the digital resources of the Swedish National Archives (Riksarkivet) through various API interfaces, including search, image retrieval, text recognition, etc.

How to use the Oxenstierna MCP Server?

Users can operate through simple commands or API calls, such as searching for keywords, obtaining collection information, downloading pictures, etc. The server provides a complete toolchain to help users quickly find and process historical documentary materials.

Applicable scenarios

Suitable for researchers, historians, digital humanities workers, and other people who need to access the digital resources of the Swedish National Archives, and can be used for literature retrieval, image analysis, text recognition, and other work.

Main Features

Multi-API Integration

Supports the OAIPMH, IIIF, and Search APIs of Riksarkivet, providing a comprehensive way to access digital resources.

Batch Image Processing

Can obtain all image batches of a specified collection and support downloading single or all images.

Text Recognition and HTR

Integrates the HTRflow tool to automatically recognize and transcribe handwritten text in images.

URL Building Tool

Provides the function of building IIIF image URLs for customized image access.

Advantages

Supports multiple APIs, providing a rich way to access data.

Has powerful image processing capabilities, suitable for academic research and digital humanities projects.

Supports handwritten text recognition, improving the availability of documents.

Limitations

Some functions rely on external services and may be restricted by network or permissions.

For non-technical users, the command-line interface requires a certain learning cost.

How to Use

Search for Records

Use the search_records method to input keywords for searching and obtain the PIDs of relevant documents.

Get Collection Information

Obtain detailed information about the collection based on the PID to understand its content and structure.

Get Image Batches

Obtain information about all image batches from the collection for subsequent processing.

Download a Specific Image

Download a specific image file according to the image index.

Usage Examples

Find Historical Documents

A user wants to find documentary materials about "coffee" in 19th - century Sweden.

Download a Specific Image

A user needs to download the first image in a certain document.

Frequently Asked Questions

Do I need to install any software for this server?

How to obtain the PID of a document?

What is HTRflow?

Can I download all the images in a collection?

Related Resources

Riksarkivet OAIPMH API Documentation

Riksarkivet's OAIPMH API documentation for metadata retrieval.

IIIF Presentation API Specification

The standard documentation of the IIIF Presentation API for describing the structure of image sets.

HTRflow MCP Example Page

An interactive demonstration page of HTRflow MCP, showing the text recognition function.

Gradio MCP Example Page

An example page of Gradio MCP, showing how to build an MCP application.

🚀 Oxenstierna 🦬⭐ (WIP)

Oxenstierna is a project that provides access to the Swedish National Archives (Riksarkivet) through multiple APIs, enabling users to search and download related content.

🚀 Quick Start

A large number of MCPs (Metadata Control Points) can be built with the help of: Riksarkivet Data Platform Wiki

✨ 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