What is mcp-python-exec-sandbox CLAUDE.md?

A project-instructions file for a Python package that runs Python scripts in isolated environments. It records the project's tools, folders, dependencies, and test commands.

Use it when modifying or testing the MCP server, its sandbox back ends, script execution, dependency setup, or end-to-end tests.

It gives a coding agent the project context needed to work within its existing structure and run the appropriate checks.

How lu-zhengda/mcp-python-exec-sandbox configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to lu-zhengda/mcp-python-exec-sandbox. 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/lu-zhengda/mcp-python-exec-sandbox/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/lu-zhengda/mcp-python-exec-sandbox

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/lu-zhengda/mcp-python-exec-sandbox/claude-md/github.svg)](https://agentmods.dev/instructions/lu-zhengda/mcp-python-exec-sandbox/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/lu-zhengda/mcp-python-exec-sandbox/claude-md"><img src="https://agentmods.dev/badge/instructions/lu-zhengda/mcp-python-exec-sandbox/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/lu-zhengda/mcp-python-exec-sandbox/claude-md"><img src="https://agentmods.dev/badge/instructions/lu-zhengda/mcp-python-exec-sandbox/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 588 This file is loaded in full into every session.

When invoked 588 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.

Model	Per session	Once invoked
Fable 5.1	$0.00588	$0.00588
Opus 5.5	$0.00235	$0.00235
Sonnet 5.5	$0.00118	$0.00118
Haiku 4.5	$0.00059	$0.00059

Measured 2mo ago against content hash 7c2c223559e4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp-python-exec-sandbox 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 2mo 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 · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Project

MCP server for sandboxed Python execution. Scripts run in ephemeral, isolated environments with inline dependencies (PEP 723) via uv. Zero host pollution.

Stack

Python 3.13+, no runtime deps beyond fastmcp and tomli-w
uv for script execution, dependency resolution, and Python version management
hatchling build backend, src/ layout

Structure

src/mcp_python_exec_sandbox/   # Package source
  server.py               # FastMCP server + tool definitions
  executor.py             # uv subprocess orchestration
  script.py               # PEP 723 metadata parsing/merging
  sandbox.py              # Sandbox ABC + factory
  sandbox_linux.py        # bubblewrap sandbox (Linux)
  sandbox_docker.py       # Docker sandbox (macOS/any)
  config.py, cache.py, output.py, errors.py
tests/                    # Unit + integration tests (mocked or local uv)
e2e_tests/                # End-to-end tests (require uv + network)
profiles/                 # Dockerfile, warmup packages

Commands

uv sync --dev             # Install deps
uv run pytest tests/ -v   # Unit + integration tests
uv run pytest e2e_tests/ -v  # E2E tests (slow, needs network)

Rules

Run uv run pytest tests/ -v before committing. All tests must pass.
Keep dependencies minimal. Do not add runtime deps without strong justification.
Lint with uv run ruff check . and format with uv run ruff format --check . before committing. Fix issues with --fix / ruff format ..
Tool docstrings in server.py are user-facing — they become the MCP tool descriptions that agents see. Write them for an LLM audience: include examples, avoid unexplained jargon, link PEPs.
Always pin versions in examples (e.g. "pandas>=2.2" not "pandas").
Sandbox backends must degrade gracefully: if the tool (bwrap, docker) is missing, fall back to NoopSandbox with a warning. Native sandbox is Linux-only (bwrap); macOS defaults to Docker.

Contribution format

Read the full file on GitHub · 53 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.

2mo ago First seen · 53 lines · 588 tokens per session scan A 7c2c223559e4

Subscribe to this mod's changes

mcp-python-exec-sandbox CLAUDE.md is an instructions file published in the GitHub repository lu-zhengda/mcp-python-exec-sandbox (1 stars, last pushed 9mo ago), licensed MIT. It adds 588 tokens to every session, about $0.0024 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.

ai-agents bubblewrap docker mcp mcp-server model-context-protocol

mcp-python-exec-sandbox CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
mcp-python-exec-sandbox CLAUDE.mdlu-zhengda/mcp-python-exec-sandbox	Instructions file	1	9mo ago	MIT	A	588	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

mcp-python-exec-sandbox: Instructions file for Claude Code