vscode-jupyter-mcp-server: Instructions file for Codex

AGENTS.md

vscode-jupyter-mcp-server AGENTS.md is an instructions file for Codex, OpenCode from Happypig375/vscode-jupyter-mcp-server. It costs 651 tokens per session, scanned C, original, MIT.

Repository instructions for a VS Code Jupyter MCP server, including its notebook tools, kernel handling, routing, and tests.

In plain words
What is it for?
They help maintain notebook opening and creation, notebook selection, kernel configuration, cell execution, and multi-window routing.
Why use it?
They document the server's supported interface and direct developers to the code and tests that define its behavior.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is Happypig375/vscode-jupyter-mcp-server's own configuration. It tells Codex and OpenCode how to work on vscode-jupyter-mcp-server 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 vscode-jupyter-mcp-server configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Happypig375/vscode-jupyter-mcp-server. 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/Happypig375/vscode-jupyter-mcp-server/master/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/Happypig375/vscode-jupyter-mcp-server

Made for: Codex, OpenCode.

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 vscode-jupyter-mcp-server AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/happypig375/vscode-jupyter-mcp-server/agents-md/github.svg)](https://agentmods.dev/instructions/happypig375/vscode-jupyter-mcp-server/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/happypig375/vscode-jupyter-mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/happypig375/vscode-jupyter-mcp-server/agents-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 vscode-jupyter-mcp-server AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/happypig375/vscode-jupyter-mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/happypig375/vscode-jupyter-mcp-server/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 651 This file is loaded in full into every session.
When invoked 651 The same file — it is already loaded in full.
Security scan C 1 finding. 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 $0.00651 $0.00651
Opus 5 $0.00326 $0.00326
Sonnet 5 $0.00130 $0.00130
Haiku 4.5 $0.00065 $0.00065

Measured 3d ago against content hash 839ff5604109, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade C, and why

vscode-jupyter-mcp-server AGENTS.md scanned grade C with 1 finding 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 3d 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.

Harvests environment variableshighData exfiltration

Enumerating or grepping the environment for keys collects credentials unrelated to what the mod says it does.

Run `npm run typecheck` and `npm run compile` for structural checks. `npm test` runs the MCP, Jupyter integration, and compiled broker suites; isolate the broker with `npm run compile:test; node .vscode-test/broker.test.
AGENTS.md · 26 lines

How it starts

The opening of the file, as written. The whole thing — 26 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent contract

Ownership

  • src/server.ts, src/schema.ts, src/localOperations.ts, src/extension.ts, and src/broker.ts define the MCP boundary and routing.
  • src/notebookOps.ts owns VS Code notebook operations.
  • src/test/mcp.test.js covers the public boundary, src/test/broker.test.ts covers multi-window routing, and src/test/mcp.jupyter.test.js covers Jupyter-backed integration behavior.

Authoritative 0.4.0 contract

Existing-notebook tools use notebookRef for one target and notebookRefs for multiple targets. A ref is a direct URI or a short opaque nb_ handle from list_notebooks; handles resolve only against currently open notebooks. list_notebooks returns grouped connected windows, including empty groups. open_notebooks accepts actual file URIs in uris and an optional windowId. create_notebook accepts title.

Tool schemas are strict. Unknown or obsolete keys fail validation. list_kernels is read-only; provider setup is explicit through configure_kernel; select_kernel accepts only an exact listed id. run_cells has no kernel hint. User supplied runtime selection takes precedence over defaults.

Source line bounds are 1-based and inclusive, and explicit source truncation is reported. Saved outputs can remain stale after edits; execution refreshes observed output state. File transfer uses only the public API of the current active idle Python kernel, is bounded and chunked, and never starts or selects a kernel.

The notebook.cell.execute command is invoked with an explicit target editor and selected cell ranges. Runtime selection supplied by the user takes precedence; missing or ambiguous targets fail closed rather than opening or transferring another notebook.

run_cells creates a tracked execution before dispatch and returns a JSON receipt containing an opaque executionId, status, and bounded per-cell state. waitMs only bounds the caller's wait and never cancels the sequential background runner; its default is 1000, while get_execution defaults to 0 and is read-only. Both accept non-negative safe-integer waits, including hour-scale workflows. A run is retained only for the current extension-window lifetime, with at most one active run per notebook, bounded global active work, and bounded terminal history/retention. Cell identity and source hashes are captured at request time; edits, moves, deletion, closure, MCP-issued kernel restart/interrupt, or unavailable observation stop later submission safely.

Read the full file on GitHub · 26 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. 3d ago First seen · 26 lines · 651 tokens per session scan C 839ff5604109

Subscribe to this mod's changes

vscode-jupyter-mcp-server AGENTS.md is an instructions file published in the GitHub repository Happypig375/vscode-jupyter-mcp-server (1 stars, last pushed 3d ago), licensed MIT. It adds 651 tokens to every session, about $0.0033 per session on Opus 5. A static security scan graded it C with 1 finding (harvests environment variables). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-07.

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