What is mcp-code-editor CLAUDE.md?

Project instructions for developing and testing the MCP Code Editor, a Python package that provides code-editing tools through the Model Context Protocol.

Use them when working on this repository, including installing dependencies, running tests, building the package, checking distributions and uploading releases.

They give a coding agent the project background and the commands used to build, test, validate and publish the package.

mcp-code-editor CLAUDE.md — Instructions file by alejoair

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/alejoair/mcp-code-editor/claude-md

Clone the repo

git clone --depth 1 https://github.com/alejoair/mcp-code-editor

Per session 951 This file is loaded in full into every session.

When invoked 951 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.

Model	Per session	Once invoked
Fable 5	$0.00951	$0.00951
Opus 5	$0.00476	$0.00476
Sonnet 5	$0.00190	$0.00190
Haiku 4.5	$0.00095	$0.00095

Measured 2d ago against content hash 98db67cb1a07, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp-code-editor 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 · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 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

MCP Code Editor is a FastMCP server providing advanced code editing tools with AST analysis, project management, and interactive console integration. The project is structured as a Python package that exposes code editing capabilities through the Model Context Protocol (MCP).

Development Commands

Build and Development

Development build: ./dev-build.sh (Linux/macOS) or dev-build.bat (Windows)
- Creates virtual environment, installs dependencies, builds package, and validates distribution
Package build: python -m build
Install dependencies: pip install -r requirements.txt
Install development dependencies: pip install -e .[dev]

Testing

Integration test: python integration_test.py
Run tests: pytest (when pytest is available in dev dependencies)
Package validation: twine check dist/*

Package Management

Version bump: Update version in both pyproject.toml and mcp_code_editor/__init__.py
Upload to PyPI: twine upload dist/*
Upload to Test PyPI: twine upload --repository testpypi dist/*

Architecture

Core Structure

mcp_code_editor/server.py: Main FastMCP server with tool definitions and MCP protocol handling
mcp_code_editor/core/: Core models and data structures (DiffBlock, validation models)
mcp_code_editor/tools/: All tool implementations organized by functionality

Tool Categories

Project Management (project_tools.py): Setup, file listing, project state management
File Operations (file_operations.py): Create, read, delete files with line number support
Diff Tools (diff_tools.py): Precise file modifications with search/replace blocks
AST Analysis (ast_analyzer.py, ast_integration.py): Python code structure analysis
Dependency Analysis (dependency_analyzer.py): Breaking change detection and impact analysis
Library Integration (library_indexer.py): External library indexing and search
Console Tools (console_tools.py): Interactive process management (Python, Node.js, shell)

Read the full file on GitHub · 86 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.

2d ago First seen · 86 lines · 951 tokens per session scan A 98db67cb1a07

Subscribe to this mod's changes

mcp-code-editor CLAUDE.md is an instructions file published in the GitHub repository alejoair/mcp-code-editor (0 stars, last pushed 1y ago), licensed MIT. It adds 951 tokens to every session, about $0.0048 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 2026-09-01.

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

mcp-code-editor CLAUDE.md