rucio-mcp
A community-maintained MCP server for Rucio that provides secure OAuth-based access to Rucio data management, enabling multi-experiment deployments and interaction via natural language.
README
rucio-mcp — one MCP server for the Rucio community
Slides for the Rucio community discussion (Indico: "Rucio Meeting", 2026-07-09) by Giordon Stark (UC Santa Cruz / SCIPP): a 15-minute pitch (12 min talk + 3 min live demo) for converging on a single, community-maintained MCP server for Rucio instead of per-experiment implementations.
▶ View the deck: https://kratsg.github.io/2026-07-09-rucio-mcp/
The talk covers the parallel MCP efforts (Belle II's PoC by Cédric Serfon, the EIC/ePIC server used by EIC and DUNE, and rucio-mcp), what rucio-mcp provides today, the OAuth bridge and security posture, the hosted multi-experiment deployment at https://rucio-mcp.af.uchicago.edu, and an honest menu of maintenance/governance options for the community to pick from.
What's here
| Path | What it is |
|---|---|
presentation.html |
The deck (reveal.js 5.1, loaded from CDN — no build step) |
styles.css |
Dark "control-room" theme (CSS variables, pt font sizing) |
scripts/ |
Overflow checker + in-browser text editor (Node/Puppeteer) |
pixi.toml |
Environment + tasks (check, screenshots, pdf, serve) |
.github/workflows/deploy.yml |
Auto-publishes to GitHub Pages on push to main |
View it
- Online: the GitHub Pages link above (always reflects
main). - Locally: open
presentation.htmlin a browser (reveal.js comes from a CDN, so you need a network connection), orpixi run serve. - Speaker notes: press
Sin the browser for speaker view. Every slide has notes, including the demo plan and fallback prompts. - Backup slides: press the down arrow on the final slide (bridge sequence end-to-end, full tool inventory).
Edit it
pixi install && pixi run install # one-time: node env + puppeteer/decktape
# after editing presentation.html / styles.css:
pixi run check # flag any slide whose content exceeds 1280x720
pixi run screenshots # capture every slide for visual review
pixi run pdf # export slides.pdf
pixi run edit # click-to-edit text in the browser, saves back to HTML
Deploy
Pushing to main publishes presentation.html (as index.html) +
styles.css to GitHub Pages and stamps the build (<short-sha> · <date> in
the bottom-left corner; reads dev locally). One-time setup: repo Settings →
Pages → Source: GitHub Actions.
Credits
Slides AI-assisted by Claude (Anthropic). Built with reveal.js. The Belle II / EIC context comes from Cédric Serfon's Belle II report (Nov 2025) and eic/rucio-eic-mcp-server.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.