Scroll MCP Server
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Scroll MCP Serversearch transcriptions for 'philosophy'"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Scroll MCP Server v0.2
π― Vesuvius Challenge submission β Automated quality audit & corpus navigation for the Herculaneum scrolls.
MCP Server for the Vesuvius Challenge papyrological corpus & open data.
Exposes scroll metadata, transcriptions, CT volumes, ML models, and documentation via the Model Context Protocol.
Quick Start
pip install scroll-mcp-server
scroll-mcp-serverOr with Claude Desktop β add to your claude_desktop_config.json:
{
"mcpServers": {
"scroll": {
"command": "scroll-mcp-server"
}
}
}Related MCP server: IIIF MCP Server
URI Scheme
scroll:// β Root
βββ catalog/scrolls β Scroll inventory
βββ catalog/vocabulary β Papyrological glossary
βββ scroll/{id}/metadata β Scroll metadata
βββ scroll/{id}/transcriptions β Deciphered text
βββ scroll/{id}/volumes β CT scan info
βββ model/ink-detection β ML models
βββ docs/tutorials β Tutorials
βββ docs/formats/tifxyz β Format specs
βββ docs/open-problems β Research challengesTools
Tool | Description |
| Search transcriptions & metadata |
| Filtered scroll inventory |
| Segment metadata + download links |
| Tutorial content |
| Technical format specification |
| ML model metadata |
| Filtered model list |
Prompts
Prompt | Purpose |
| Historical/philosophical context of a passage |
| Research recommendations from corpus state |
Architecture
Client β FastMCP β ScrollDataLayer β Catalog (JSON) + Vesuvius (streaming) + Cache (LRU)Catalogue JSON β Lightweight index (~50 KB) for instant metadata responses
Data Layer β Orchestrator with LRU cache, routes to the right source
Vesuvius Client β Streaming proxy for CT volumes (no local storage)
Development
git clone https://github.com/zengdard/scroll-mcp-server
cd scroll-mcp-server
pip install -e .
pytest tests/ -vReal Example β Scroll 1 Segment Audit
Un exemple complet avec donnΓ©es rΓ©elles du Scroll 1 (PHerc. Paris 4) est dans examples/ :
# Audit du mesh noisy (84k vertices) contre le volume CT
python examples/audit_demo.py --quickRΓ©sultat :
Quality score: 0.431 β mesh bruitΓ©, besoin de raffinement
Mean confidence: 0.942 β bonne qualitΓ© CT
Mean distance: 3.88 voxels
π΄ CRITIQUE β 55650 vertices en drift
π’ ANCRE β 6418 vertices stablesVoir le rapport complet : examples/AUDIT_REPORT.md
Submission
Ce projet est soumis au Scroll Prize. Voir SUBMISSION.md pour les dΓ©tails.
Team: Individual β zengdard
License
MIT
This server cannot be deployed
Maintenance
Related MCP Connectors
Auditable MCP server for PubMed, Europe PMC, ClinicalTrials.gov, and bioRxiv/medRxiv queries
MCP server for the GDEX (Geoscience Data Exchange) data portal: datasets, files, metrics, subsetting
MCP server for progressive tool usage at any scale (see https://klavis.ai)
MCP gateway federating 22 biomedical MCP servers behind one endpoint: gnomAD, ClinVar, HPO, VEP.
Related MCP Servers
- AlicenseAqualityBmaintenanceComprehensive MCP server for academic research workflows, enabling paper searching across multiple sources, manuscript processing with citation placeholders, search caching, and citation export.11MIT
- AlicenseAqualityDmaintenanceMCP server for IIIF integration, enabling image fetching, manifest exploration, annotation search, and authentication support for cultural heritage resources.112MIT
- AlicenseCqualityAmaintenanceMCP server for the Transkribus REST API. Manage collections, documents, HTR/OCR recognition, models, and more through the Model Context Protocol.30477 npm2Functional Source , Version 1.1, MIT Future
- AlicenseAqualityCmaintenanceHosted MCP server for antiquarian first-edition identification and New Mexico book-donation logistics. 12 tools over a CC-BY, DOI-cited dataset of 6,700+ titles and 870 publisher conventions.12MIT