Jupyter MCP Server is a Model Context Protocol server that lets AI agents connect to and manage Jupyter notebooks in real time. It supports notebooks running locally or on hosted platforms, and its catalogue add-ons provide commands and skills for working with those notebooks.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/datalayer/jupyter-mcp-server/notebookgit clone --depth 1 https://github.com/datalayer/jupyter-mcp-serverWrote 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/commands/datalayer/jupyter-mcp-server/notebook)<a href="https://agentmods.dev/commands/datalayer/jupyter-mcp-server/notebook"><img src="https://agentmods.dev/badge/commands/datalayer/jupyter-mcp-server/notebook.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.00230 |
| Opus 5 | $0.00000 | $0.00115 |
| Sonnet 5 | $0.00000 | $0.00046 |
| Haiku 4.5 | $0.00000 | $0.00023 |
Grade A, and why
notebook 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 5d 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.
What it actually says
description: Open a Datalayer notebook and work in it argument-hint: [notebook name or path]
Connect to a Datalayer notebook and make it the one we work in.
Steps:
- Call
list_notebooksto see what this account can reach. - If
$ARGUMENTSis empty, show the list and ask which notebook to open. Otherwise pick the notebook whose name or path best matches$ARGUMENTS; if several match, list the candidates and ask rather than guessing. - Call
use_notebookwith a short, stable alias and the notebook's path. - Call
read_notebookwith the brief format and summarise what the notebook contains — how many cells, what it appears to be about, and where its last execution stopped.
Do not create a notebook unless you were asked to. If nothing matches, say so and list what is available.
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.
- 5d ago First seen · 28 lines · 0 tokens per session scan A edecaa4b3460
notebook is a command published in the GitHub repository datalayer/jupyter-mcp-server (1,271 stars, last pushed today), licensed BSD-3-Clause. It costs nothing until one of its globs matches a file; then it loads 230 tokens. 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 2026-08-30.
Other commands, from other repositories
review-epo-claims
Analyze patent claims for EPO Art. 84 EPC compliance - clarity, conciseness, support by description.
ingest-dev
Ingest a URL, directory, or file into your knowledge base. remember = a specific durable fact, ingest = a URL, learn = a distilled lesson that gets retrieval preference.
quarry
Manage your quarry knowledge base.
remember-dev
Remember inline text content in your knowledge base. remember = a specific durable fact, ingest = a URL, learn = a distilled lesson that gets retrieval preference.
scout
Scout vetted GitHub candidates for a thin shelf (or a stale entry's successor), deduped against the library, ending in /add-entry offers.
resume
Auto-detect and resume any interrupted Plan Cascade task. Detects mega-plan, hybrid-worktree, or hybrid-auto context and routes to the appropriate resume command.