Borrowing it
Nothing to install: this file belongs to maniaclab/af-jupyterlab-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.
curl -O https://raw.githubusercontent.com/maniaclab/af-jupyterlab-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/maniaclab/af-jupyterlab-mcpWrote 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.
[](https://agentmods.dev/instructions/maniaclab/af-jupyterlab-mcp/claude-md)<a href="https://agentmods.dev/instructions/maniaclab/af-jupyterlab-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/maniaclab/af-jupyterlab-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.
<a href="https://agentmods.dev/instructions/maniaclab/af-jupyterlab-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/maniaclab/af-jupyterlab-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.03875 | $0.03875 |
| Opus 5.5 | $0.01550 | $0.01550 |
| Sonnet 5.5 | $0.00775 | $0.00775 |
| Haiku 4.5 | $0.00387 | $0.00387 |
Grade A, and why
af-jupyterlab-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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 289 lines — stays where its author put it; the contents beside it link to each section on GitHub.
af-jupyterlab-mcp — Contributor Guide
MCP server that lets AF users create, inspect, and delete their own per-user JupyterLab servers on the UChicago ATLAS Analysis Facility Kubernetes cluster — the same notebooks af-portal deploys today — exposed as tools for LLMs, behind the af-mcp-platform credential broker.
Architecture
LLM <--MCP/HTTP--> af-mcp-platform aggregator <--Bearer: broker JWT--> af-jupyterlab-mcp <--k8s API--> notebook namespace
Design philosophy: unlike ami-mcp (which exposes a query DSL and lets the LLM be expressive), this backend exposes fixed, typed tools over Kubernetes Pod/Service/Secret/Ingress objects and the notebook's own jupyter-mcp-server. There is no raw-k8s-manifest escape hatch: the value here is the AF-specific policy layered on top (guardrail validation, dual-writer safety, owner-scoping), not a thin pass-through to the Kubernetes API.
Six CRD-management tools create/inspect/delete the pod+service+secret+ingress
quadruple (tools/jupyterlab.py). Seventeen nb_* tools (tools/nb_proxy.py,
tracked in
maniaclab/af-mcp-platform#189)
proxy to the Datalayer jupyter-mcp-server running inside the notebook itself,
so a session can drive code execution inside the user's own notebook without the
notebook token ever entering LLM context. Fifty-two nb_ui_* tools
(tools/nb_ui.py) proxy JupyterLab frontend commands served by the
jupyter-mcp-tools extension; these run inside the user's open JupyterLab tab
and fail without one.
Project layout
src/af_jupyterlab_mcp/ splits into auth/ (broker JWT verification), k8s/
(all Kubernetes-facing logic: notebooks, guardrails, names, gpu, templates, and
the nb_* proxy transport), and tools/ (the @mcp.tool() registrations in
jupyterlab.py and nb_proxy.py, plus shared _helpers.py). tests/ mirrors
this layout one-to-one (tests/k8s/, tests/tools/, tests/auth/), plus
test_config.py, test_server.py, and test_cli.py at the top level. Run
tree src/af_jupyterlab_mcp tests for the current file-by-file breakdown --
deliberately not duplicated here, since a hand-maintained tree has already gone
stale twice (most recently: it didn't mention k8s/proxy.py,
tools/nb_proxy.py, or their tests after they shipped).
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.
- 1mo ago Changed · +30 lines · +484 tokens per session 6bd4bb6d1bd9
- 2mo ago Changed · +81 lines · +996 tokens per session 62b582ee5af7
- 2mo ago First seen · 178 lines · 2,395 tokens per session scan A fc7d1f72611e
af-jupyterlab-mcp CLAUDE.md is an instructions file published in the GitHub repository maniaclab/af-jupyterlab-mcp (0 stars, last pushed 12d ago), licensed Apache-2.0. It adds 3,875 tokens to every session, about $0.0155 per session on Opus 5.5. 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.
af-jupyterlab-mcp CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| af-jupyterlab-mcp CLAUDE.mdmaniaclab/af-jupyterlab-mcp | Instructions file | 0 | 12d ago | Apache-2.0 | A | 3,875 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 196k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 144k | today | MIT | A | 8,130 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 196k | today | MIT | A | 5,685 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 150k | today | MIT | A | 4,680 | Codex, OpenCode |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 283k | yesterday | MIT | A | 4,342 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 196k | today | MIT | A | 3,153 | GitHub Copilot |