Help us improve
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
Transcribe handwritten historical Swedish documents using HTR tools with interactive viewers and JSON exports, search Riksarkivet archives via metadata and transcriptions, browse and zoom PDFs/IIIF images, annotate pages in Label Studio, map topics to record types, and upload files to Hugging Face Spaces for remote access.
npx claudepluginhub ai-riksarkivet/ra-mcp --plugin ra-mcp-toolsGuide for understanding Swedish archival record types and administrative history. Maps research topics to the correct Förvaltningshistorik chapters available as MCP resources. Use when: what records exist, which archive, document types, court records, church records, folkbokföring, bouppteckning, dombok, husförhörslängd, mantalslängd, military records, tax records, prison records, parish records, Swedish administrative history, where to find records, what archives contain, understand archival structure.
Essential research guide — load BEFORE browsing, reading, or presenting archival documents. Use whenever the user wants to browse, read, examine, analyze, translate, or interpret documents from the Swedish National Archives (Riksarkivet), or when presenting research findings from archival sources. Covers research integrity, citing archival sources with reference codes, translating old Swedish, cross-tool research workflow (search, browse, synthesize), browsing strategy, result presentation, and coverage awareness. Use when: browse document, read pages, examine records, translate old Swedish, interpret documents, cite sources, present findings, research methodology, archival research, historical research, document analysis, reference codes, court records, church records, dombok, bouppteckning, any archive browsing or research.
Essential pre-search guide — load BEFORE calling search_transcribed or search_metadata. Use whenever the user wants to search, find, look up, or discover documents, people, places, events, or any information in the Swedish National Archives (Riksarkivet). Covers tool selection (search_transcribed vs search_metadata), search strategy, Solr query syntax, wildcards, fuzzy matching for OCR/HTR errors, old Swedish spelling variants, proximity search, Boolean operators, and pagination workflows. Use when: search, find, look up, discover, query, search archives, search documents, find person, find place, search records, search court records, search church records, search transcriptions, historical research, archival research, Riksarkivet search, trolldom, häxprocesser, bouppteckning, dombok, any archive query.
Guide for sending document pages to Label Studio for human feedback on transcriptions. Use when: feedback, label studio, annotation, review transcription, quality check, send to label studio, import to label studio, human review, correct transcription, segmentation feedback, transcription feedback, ALTO to label studio, review pages, flag pages for review, quality assurance, QA, annotation task, annotate images, label images, send images for annotation.
Guide for using HTRflow MCP tools to transcribe handwritten documents. Use when: transcribe handwriting, HTR, handwritten document, OCR historical document, read old handwriting, digitize manuscript, transcribe old letters, recognize handwritten text.
Share bugs, ideas, or general feedback.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Search your local documents with natural language. Index folders of PDFs, Word docs, markdown, and more — then ask questions in English or German and get answers with source citations.
Open source document intelligence and review plugin for Claude Code: ingest, search, review, enrich, and export local document workspaces.
A research infrastructure for AI agents. Search, read, and analyze papers from your local knowledge base while coding. Includes arXiv discovery, layered reading, ingestion, topic modeling, citation graphs, insights analytics, Office document inspection, scientific tool docs, and academic writing workflows. Requires Python 3.10+ and pip install.
Academic paper search MCP for arXiv, PubMed, IEEE, Scopus, ACM, and more. Requires Docker.
MCP server for the Wayback Machine — save URLs, retrieve snapshots, search archives, check status, list screenshots, compare snapshots, and manage cache
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
A Model Context Protocol server and CLI for searching and browsing transcribed historical documents from the Swedish National Archives (Riksarkivet). Provides full-text search across millions of AI-transcribed pages, complete page transcriptions, handwritten text recognition, interactive document viewing, and archival research guides — all as MCP tools that any LLM client can use.
Streamable HTTP — works with ChatGPT, Claude, and any MCP-compatible client:
https://riksarkivet-ra-mcp.hf.space/mcp
Claude Code:
claude mcp add --transport http ra-mcp https://riksarkivet-ra-mcp.hf.space/mcp
IDE (mcp.json):
{
"mcpServers": {
"ra-mcp": {
"type": "streamable-http",
"url": "https://riksarkivet-ra-mcp.hf.space/mcp"
}
}
}
uv pip install ra-mcp
# Search transcribed documents
ra search "trolldom"
ra search "((Stockholm OR Göteborg) AND troll*)"
# Browse specific pages
ra browse "SE/RA/310187/1" --pages "7,8,52" --search-term "trolldom"
# Interactive terminal browser
ra tui "trolldom"
For architecture, development setup, deployment, tool reference, CLI reference, and more:
ai-riksarkivet.github.io/ra-mcp