Skip to main content
Glama

Riksarkivet MCP Server

by AI-Riksarkivet
GitHub
Python
Apache 2.0
3
OverviewInspectNewEndpointsSchemaRelated ServersReviewsScore
Need Help?View Source CodeReport Issue

ra-mcp (WIP)

MCPs for Riksarkivet

A MCP server and command-line tools for searching and browsing transcribed historical documents from the Swedish National Archives (Riksarkivet).

Features

  • Full-text search across millions of transcribed historical documents

  • Complete page transcriptions with accurate text extraction from historical manuscripts

  • Reference-based document browsing using official archive reference codes

  • Contextual search highlighting to identify relevant content quickly

  • High-resolution image access to original document scans via IIIF

Getting Started

Quick Setup

# Search for anything uv run ra search "Stockholm"

How to Use

1. Search for Keywords

Find documents containing specific words or phrases:

# Basic search uv run ra search "Stockholm" # Search with full page transcriptions uv run ra search "trolldom" --context --max-pages 5 # Search with surrounding pages for context uv run ra search "trolldom" --context --context-padding 1 --max-pages 3 # Search without document grouping uv run ra search "vasa" --context --no-grouping --max-pages 3

Options:

  • --max N - Maximum search results (default: 50)

  • --max-display N - Maximum results to display (default: 20)

  • --context - Show full page transcriptions

  • --max-pages N - Maximum pages to load context for (default: 10)

  • --context-padding N - Include N pages before/after each hit for context (default: 0)

  • --no-grouping - Show pages individually instead of grouped by document

2. Browse Specific Documents

When you find interesting documents, browse them directly:

# View single page uv run ra browse "SE/RA/123" --page 5 # View page range uv run ra browse "SE/RA/123" --pages "1-10" # View specific pages with search highlighting uv run ra browse "SE/RA/123" --page "5,7,9" --search-term "Stockholm"

Options:

  • --page or --pages - Page numbers (e.g., "5", "1-10", "5,7,9")

  • --search-term - Highlight this term in the text

  • --max-display N - Maximum pages to display (default: 20)

3. Search with Full Context

The --context flag shows complete page transcriptions instead of just snippets:

# Search with full page transcriptions uv run ra search "Stockholm" --context --max-pages 5 # Include surrounding pages for additional context uv run ra search "trolldom" --context --context-padding 2 # Show pages individually instead of grouped by document uv run ra search "vasa" --context --no-grouping

Output Features

🔍 Search Results

When you run a search, results are presented with:

  • Document grouping - Related pages grouped together for context

  • Institution & dates - Archive location and document dates

  • Page numbers - Specific pages containing your search terms

  • Highlighted snippets - Preview text with keywords emphasized

  • Browse commands - Ready-to-run commands for deeper exploration

Example output:

Document: SE/RA/310187/1 - Kommissorialrätt i Stockholm ang. trolldom Institution: Riksarkivet i Stockholm/Täby | Date: 1676 - 1677 ├─ Page 2: "...Kommissorialrätt i Stockholm ang. **trolldom** 1676..." ├─ Page 7: "...som sig medh någon klagomåhl öfwer detta **Trolldoms** wäsende..." ├─ Page 8: "...till hemmande af denne **Trolldoms** Sundh på åthskillige orter..." ├─ Page 52: "...hustru Anna förklarades skyldig till **trolldom** och förde..." └─ Page 72: "...bekände han sig hafwa brukat **trolldom** emot sina fiender..." Browse commands: uv run ra browse "SE/RA/310187/1" --page 7 --search-term "trolldom" uv run ra browse "SE/RA/310187/1" --pages "2,7,8,52,72" --search-term "trolldom"

📄 Full Page Display

With the --context flag, you get complete page transcriptions featuring:

  • Full text transcriptions - Complete page content from ALTO XML

  • Keyword highlighting - Your search terms highlighted in yellow

  • Rich metadata - Document titles, dates, and archive hierarchy

  • Direct access links - Quick links to images, XML, and interactive viewer

  • Context indicators - Clear marking of surrounding pages when using --context-padding

Example output:

═══ SE/RA/310187/1 - Page 7 ═══ Title: Kommissorialrätt i Stockholm ang. trolldom Date: 1676-1677 | Institution: Riksarkivet i Stockholm/Täby skäligt sin emillan förafskeda, och det eftter Kongl. Senarens förordning, att alla dhe, som sig medh någon klagomåhl öfwer detta **Trolldoms** wäsende angifwa wela, ther medh skola inställa sigh för höga öfwerheten, huilket alt Högwälborne Herr General Leutnanten och Gouverneuren medh dhe brefwen han oss tillsändt hafwer, jämwäl och i muntel samptahl medh oss sigh förklarat, som wij och nu wid thetta tillfället Commissionen till hemmande af denne **Trolldoms** Sundh på åthskillige orter... Links: 📄 ALTO XML: https://sok.riksarkivet.se/dokument/alto/SE_RA_310187_1_007.xml 🖼️ Image: https://lbiiif.riksarkivet.se/arkiv/SE_RA_310187_1_007.jpg 🔍 Bildvisning: https://sok.riksarkivet.se/bildvisning/SE_RA_310187_1#007

🔗 Available Resources

Each result provides direct access to:

Resource

Description

Use Case

ALTO XML

Structured transcription data with precise positioning

Text analysis, data extraction

IIIF Images

High-resolution document scans with zoom/crop support

Visual inspection, citations

Bildvisning

Interactive web viewer with search highlighting

Online browsing, sharing

Collections

IIIF metadata for document series

Understanding document context

Examples

Basic Workflow

  1. Search for a keyword:

    uv run ra search "Stockholm"

  2. Get full context for interesting hits:

    uv run ra search "Stockholm" --context --max-pages 3

  3. Include surrounding pages for additional context:

    uv run ra search "Stockholm" --context --context-padding 1 --max-pages 3

  4. Browse specific documents:

    uv run ra browse "SE/RA/123456" --page "10-15" --search-term "Stockholm"

Advanced Usage

# Comprehensive search with context and surrounding pages uv run ra search "trolldom" --context --context-padding 2 --max-pages 8 # Targeted document browsing uv run ra browse "SE/RA/760264" --pages "1,5,10-12" --search-term "trolldom" # Large search with selective display uv run ra search "trolldom" --max 100 --max-display 30

Technical Details

Riksarkivet APIs & Data Sources

This tool integrates with multiple Riksarkivet APIs to provide comprehensive access to historical documents:

Current Integrations

Additional Resources

The Riksarkivet Data Platform Wiki provides comprehensive documentation for building additional MCP integrations.

Experimental Features

Troubleshooting

Common Issues

  1. No results found: Try broader search terms or check spelling

  2. Page not loading: Some pages may not have transcriptions available

  3. Network timeouts: Tool includes retry logic, but very slow connections may time out

Getting Help

uv run ra --help uv run ra search --help uv run ra browse --help uv run ra serve --help

MCP Server Development

Running the MCP Server

# Install dependencies uv sync && uv pip install -e . # Run the main MCP server (stdio) cd src/ra_mcp && python server.py # Run with SSE/HTTP transport on port 8000 cd src/ra_mcp && python server.py --http

Testing with MCP Inspector

Use the MCP Inspector to test and debug the MCP server:

# Test the server interactively npx @modelcontextprotocol/inspector uv run python src/ra_mcp/server.py

The MCP Inspector provides a web interface to test server tools, resources, and prompts during development.

Building and Publishing with Dagger

The project uses Dagger for containerized builds and publishing to Docker registries. Pre-built images are available on Docker Hub.

Prerequisites

  • Dagger CLI installed

  • Docker registry credentials (for publishing)

Available Commands

Build locally:

dagger call build

Run tests:

dagger call test

Build and publish to Docker registry:

# Set environment variables export DOCKER_USERNAME="your-username" export DOCKER_PASSWORD="your-password" # Build and publish dagger call publish \ --docker-username=env:DOCKER_USERNAME \ --docker-password=env:DOCKER_PASSWORD \ --image-repository="riksarkivet/ra-mcp" \ --tag="latest" \ --source=.

Available Dagger Functions

  • build: Creates a production-ready container image using the Dockerfile

  • test: Runs the test suite using pytest with coverage reporting

  • publish: Builds and publishes container image to registry with authentication

  • build-local: Build with custom environment variables and registry settings

The Dagger configuration is located in .dagger/main.go and provides a complete CI/CD pipeline for the project.

image

Current MCP Server Implementation

The MCP server provides access to transcribed historical documents from the Swedish National Archives (Riksarkivet) through three primary tools and two resources:

🔧 Available Tools

1. search_transcribed

Search for keywords in transcribed materials with pagination support.

search_transcribed( keyword="trolldom", # Search term offset=0, # Pagination offset (required) show_context=False, # Full page text (default: False for more results) max_results=10, # Maximum results to return max_hits_per_document=3 # Max hits per document )

2. browse_document

Browse specific pages of a document by reference code.

browse_document( reference_code="SE/RA/310187/1", # Document reference pages="7,8,52", # Page numbers or ranges highlight_term="trolldom", # Optional keyword highlighting max_pages=20 # Maximum pages to display )

3. get_document_structure

Get document structure and metadata without fetching content.

get_document_structure( reference_code="SE/RA/310187/1", # Document reference (or use pid) include_manifest_info=True # Include IIIF manifest details )

📚 Available Resources

  • riksarkivet://contents/table_of_contents - Complete guide index (Innehållsförteckning)

  • riksarkivet://guide/{filename} - Specific guide sections (e.g., '01_Domstolar.md', '02_Fangelse.md')

🔄 Typical Workflow

  1. Search → search_transcribed("trolldom", offset=0) to find relevant documents

  2. Paginate → Continue with offset=50, 100, 150... for comprehensive discovery

  3. Browse → Use browse_document() to view specific pages with full transcriptions

  4. Structure → Use get_document_structure() to understand document organization

💡 Search Strategy Tips

  • Start with show_context=False to maximize hit coverage

  • Use pagination (increasing offsets) to find all matches

  • Enable show_context=True only when you need full page text for specific hits

  • Browse specific pages for detailed examination with keyword highlighting

Deploy Server
-
security - not tested
A
license - permissive license
-
quality - not tested

How are these scores calculated?

remote-capable server

The server can be hosted and run remotely because it primarily relies on remote services or has no dependency on the local environment.

Tools

Enables users to search and access digital collections from the Swedish National Archives (Riksarkivet) through multiple APIs. Supports searching records by keywords, exploring collections, and downloading historical images and documents.

  1. MCPs for Riksarkivet
    1. Features
      1. Getting Started
        1. Quick Setup
      2. How to Use
        1. 1. Search for Keywords
        2. 2. Browse Specific Documents
        3. 3. Search with Full Context
      3. Output Features
        1. 🔍 Search Results
        2. 📄 Full Page Display
        3. 🔗 Available Resources
      4. Examples
        1. Basic Workflow
        2. Advanced Usage
      5. Technical Details
        1. Riksarkivet APIs & Data Sources
      6. Troubleshooting
        1. Common Issues
        2. Getting Help
      7. MCP Server Development
        1. Running the MCP Server
        2. Testing with MCP Inspector
        3. Building and Publishing with Dagger
      8. Current MCP Server Implementation
        1. 🔧 Available Tools
        2. 📚 Available Resources
        3. 🔄 Typical Workflow
        4. 💡 Search Strategy Tips

      New MCP Servers

      MCP directory API

      We provide all the information about MCP servers via our MCP API.

      curl -X GET 'https://glama.ai/api/mcp/v1/servers/AI-Riksarkivet/ra-mcp'

      If you have feedback or need assistance with the MCP directory API, please join our Discord server