mcp_python_toolbox CLAUDE.md

Development instructions for MCP Python Toolbox, a Python project that provides tools through MCP. They describe setup, testing, type checking, linting, formatting, and coding conventions.

In plain words
What is it for?
Use them when developing the project to install dependencies, run tests, check types, lint, format, and follow its Python naming and documentation rules.
Why use it?
They make the project’s required checks and style clear, reducing inconsistent code and avoidable build or review problems.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/gianlucamazza/mcp_python_toolbox/claude-md
Clone the repo
git clone --depth 1 https://github.com/gianlucamazza/mcp_python_toolbox
Per session 253 This file is loaded in full into every session.
When invoked 253 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00253 $0.00253
Opus 5 $0.00127 $0.00127
Sonnet 5 $0.00051 $0.00051
Haiku 4.5 $0.00025 $0.00025

Measured 2d ago against content hash bd157d487152, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp_python_toolbox 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 2d 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 · 22 lines

What it actually says

MCP Python Toolbox - Development Guidelines

Build/Test/Lint Commands

  • Install dev dependencies: pip install -e ".[dev]"
  • Run all tests: pytest
  • Run single test: pytest tests/path/to/test_file.py::test_function_name -v
  • Type checking: mypy src/mcp_python_toolbox
  • Linting: pylint src/mcp_python_toolbox
  • Format code: black src/mcp_python_toolbox

Code Style Guidelines

  • Line length: 100 characters (Black configuration)
  • Python version: 3.7+
  • Formatting: Use Black for automatic formatting
  • Imports: Standard library first, then third-party, then local modules
  • Types: All functions must have type annotations (disallow_untyped_defs=true)
  • Naming:
    • Classes: PascalCase
    • Functions/variables: snake_case
    • Constants: UPPER_CASE
  • Error handling: Use specific exceptions with descriptive error messages
  • Documentation: Docstrings for all modules, classes, and functions using """triple quotes"""
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. 2d ago First seen · 22 lines · 253 tokens per session scan A bd157d487152

Subscribe to this mod's changes

mcp_python_toolbox CLAUDE.md is an instructions file published in the GitHub repository gianlucamazza/mcp_python_toolbox (9 stars, last pushed 1mo ago), licensed MIT. It adds 253 tokens to every session, about $0.0013 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.