rucio-mcp: Instructions file for Claude Code

CLAUDE.md

rucio-mcp CLAUDE.md is an instructions file for Claude Code from kratsg/rucio-mcp. It costs 6,726 tokens per session, scanned A, original, Apache-2.0.

A contributor guide for an MCP server that lets AI agents work with ATLAS Rucio, a system used to manage and transfer scientific data.

In plain words
What is it for?
Use it when contributing to, configuring, or operating the rucio-mcp server in local command-line mode or hosted web mode.
Why use it?
It explains how the server connects to Rucio and how users authenticate, reducing confusion when running it locally or hosting it for multiple users.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions Claude Code.

This is kratsg/rucio-mcp's own configuration. It tells Claude Code how to work on rucio-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything rucio-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to kratsg/rucio-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/kratsg/rucio-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/kratsg/rucio-mcp

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for rucio-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/kratsg/rucio-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/kratsg/rucio-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/kratsg/rucio-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/kratsg/rucio-mcp/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for rucio-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/kratsg/rucio-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/kratsg/rucio-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 6,726 This file is loaded in full into every session.
When invoked 6,726 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.06726 $0.06726
Opus 5 $0.03363 $0.03363
Sonnet 5 $0.01345 $0.01345
Haiku 4.5 $0.00673 $0.00673

Measured 9d ago against content hash 5a8b327e92eb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

rucio-mcp CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 532 lines

How it starts

The opening of the file, as written. The whole thing — 532 lines — stays where its author put it; the contents beside it link to each section on GitHub.

rucio-mcp — Contributor Guide

MCP server that exposes ATLAS Rucio data management operations as tools for LLMs.

Architecture

Two transport modes:

# stdio (local, single-user)
LLM <--MCP/stdio--> rucio-mcp serve <--HTTPS (rucio.client)--> Rucio server
                              |
                              +--subprocess--> voms-proxy-info

# http (hosted, multi-user)
MCP client  <--auth-code+PKCE-->  rucio-mcp (OAuth AS proxy)  <--polling-->  Rucio auth server  <--IdP-->
                                         |                                          |
                                  BridgeProvider mints                   /auth/oidc + /auth/oidc_redirect
                                  auth codes; bearer = rucio token       (Rucio session token)

Stdio mode: one rucio.client.Client built at server startup from env vars; reused for all tool calls. All rucio auth types supported.

HTTP mode: rucio-mcp acts as an OAuth 2.1 Authorization Server proxy (RFC 8414 + CIMD + auth-code+PKCE). It bridges MCP client auth to Rucio's custom OIDC polling flow (/auth/oidc/auth/oidc_redirect). The resulting Rucio session token is returned verbatim as the MCP access_token. No IAM registration is required by operators or end-users.

Shared-secret HTTP mode: when serve is given --shared-secret (env RUCIO_MCP_SHARED_SECRET), HTTP transport switches to a distinct, mutually-exclusive model: it serves a single env-built Client (exactly like stdio, honoring --auth-type — e.g. a pre-authenticated x509 instance) gated by a server-wide static bearer. An MCPServer TokenVerifier (auth/shared_secret.py::SharedSecretVerifier, constant-time compare) enforces the secret; there is no OAuth bridge, OIDC poller, CIMD, /bridge, /authorize, /token, or /register. Single site only (one env config = one client). Built by _make_shared_secret_mcp / _make_shared_secret_app in server.py; reuses EnvBasedClientFactory.

Broker HTTP mode: when serve is given --broker-url (env RUCIO_MCP_BROKER_URL), HTTP transport runs behind af-mcp-platform's aggregator: bearers are broker-issued identity JWTs verified against the broker's JWKS (auth/broker.py::make_broker_token_verifier, backed by af-credentials), and BrokerProxyClientFactory redeems the caller's VOMS proxy from the broker per tool call, authenticates a fresh ProxyAuthClient (auth_type=x509_proxy, disk token cache disabled so one user's rucio token can never leak to another via the shared /tmp cache), and deletes the proxy file as soon as authentication completes. The rucio account is left unset — the Rucio server resolves it from the proxy DN's default-account mapping (AF unixnames do not match CERN/Rucio account names; an explicit account via the broker redeem response is tracked in af-mcp-platform#191). Single site only; mutually exclusive with --shared-secret; no OAuth bridge, CIMD, or /register. Built by _make_broker_mcp / _make_broker_app in server.py (the single-site app shell is shared with shared-secret mode via _wrap_single_site_app). Requires the broker extra (pip install rucio-mcp[broker]).

Read the full file on GitHub · 532 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 532 lines · 6,726 tokens per session scan A 5a8b327e92eb

Subscribe to this mod's changes

rucio-mcp CLAUDE.md is an instructions file published in the GitHub repository kratsg/rucio-mcp (5 stars, last pushed 2d ago), licensed Apache-2.0. It adds 6,726 tokens to every session, about $0.0336 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens