code-analysis-context-python-mcp CLAUDE.md

Project instructions for an MCP server that analyzes Python codebases, especially projects using tools such as pandas, NumPy, scikit-learn, FastAPI, and Django. MCP is a standard way for AI tools to use external tools.

In plain words
What is it for?
For developing and validating the Python code-analysis server and testing its six analysis tools.
Why use it?
They tell an AI coding agent how the project works and how to install, run, test, format, lint, and type-check it.

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/andreahaku/code-analysis-context-python-mcp/claude-md
Clone the repo
git clone --depth 1 https://github.com/andreahaku/code-analysis-context-python-mcp
Per session 1,830 This file is loaded in full into every session.
When invoked 1,830 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 $0.01830 $0.01830
Opus 5 $0.00915 $0.00915
Sonnet 5 $0.00366 $0.00366
Haiku 4.5 $0.00183 $0.00183

Measured yesterday against content hash 1a3c831b3725, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-analysis-context-python-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 yesterday.

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 · 212 lines

How it starts

The opening of the file, as written. The whole thing — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

This is an MCP (Model Context Protocol) server that provides deep codebase analysis for Python projects, specifically designed for data analysis engineers working with pandas, numpy, sklearn, fastapi, django, and other Python frameworks.

The server exposes 6 analysis tools via the MCP protocol. It's a complete, production-ready implementation with 3,787 lines of code across 18 modules.

Development Commands

Setup & Installation

# Development installation with all dependencies
pip install -e ".[dev]"

# Install only runtime dependencies
pip install -e .

Running & Testing

# Test the MCP server by analyzing itself
python3 test_tools.py

# Run the MCP server (for use with Claude Desktop or other MCP clients)
python3 -m src.server

# Or use the installed script
code-analysis-python-mcp

Code Quality

# Format code (100 char line length)
black src tests
isort src tests

# Linting
flake8 src tests

# Type checking (strict mode enabled in pyproject.toml)
mypy src

# Run tests with coverage
pytest --cov=src --cov-report=html --cov-report=term

Architecture Overview

High-Level Design

MCP Server Pattern: The architecture follows a clear separation between the MCP protocol layer and analysis logic:

  1. src/server.py - MCP protocol handler (338 lines)

    • Defines 6 Tool schemas with short parameter names (e.g., path, inc, exc)
    • Maps short params to long params via map_params() function
    • Routes tool calls to appropriate analyzers
    • All tools are async functions returning Sequence[TextContent]
  2. src/tools/ - 6 independent analysis tools (each ~300-500 LOC)

    • Each tool is a standalone async function accepting a dict of long-form params
    • Tools return JSON results wrapped in TextContent
    • No shared state between tools
    • Tools: architecture_analyzer.py, pattern_detector.py, dependency_mapper.py, coverage_analyzer.py, convention_validator.py, context_pack_generator.py

Read the full file on GitHub · 212 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. yesterday First seen · 212 lines · 1,830 tokens per session scan A 1a3c831b3725

Subscribe to this mod's changes

code-analysis-context-python-mcp CLAUDE.md is an instructions file published in the GitHub repository andreahaku/code-analysis-context-python-mcp (1 stars, last pushed 10mo ago), licensed MIT. It adds 1,830 tokens to every session, about $0.0092 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.

Related

Other instructions, from other repositories

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 · 5,182 tokens

buildNext

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

next.js 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

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

spec-kit AGENTS.md

Instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,040 tokens

langchain 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 · 4,345 tokens