lightweight-github-mcp CLAUDE.md

A project guide for Claude Code in a lightweight GitHub MCP repository. The repository is a small server that limits which tools from GitHub's official MCP server are exposed to an AI coding agent.

In plain words
What is it for?
Use it to install dependencies, build, run, develop, and inspect the lightweight GitHub MCP server.
Why use it?
It gives an agent the project background, required software, commands, and architecture needed to work on the codebase. MCP is a way for an AI agent to call external tools and services.

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/ham0215/lightweight-github-mcp/claude-md
Clone the repo
git clone --depth 1 https://github.com/ham0215/lightweight-github-mcp
Per session 800 This file is loaded in full into every session.
When invoked 800 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 $0.00800 $0.00800
Opus 5 $0.00400 $0.00400
Sonnet 5 $0.00160 $0.00160
Haiku 4.5 $0.00080 $0.00080

Measured yesterday against content hash 96043e85fc66, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

lightweight-github-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 · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 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

Lightweight GitHub MCP is a proxy server that wraps github/github-mcp-server (GitHub's official MCP server) and exposes only whitelisted tools via YAML configuration. This dramatically reduces context consumption (100+ tools → 10-20 tools).

Prerequisites: Docker must be installed and running.

Build and Run Commands

# Install dependencies
npm install

# Build
npm run build

# Development mode (watch)
npm run dev

# Run the server
npm start

# Test with MCP Inspector
npx @modelcontextprotocol/inspector node dist/index.js

Architecture

Claude Desktop/Code
        │ MCP Protocol (stdio)
        ▼
┌─────────────────────────────┐
│  lightweight-github-mcp     │
│  ┌─────────┐  ┌──────────┐  │
│  │MCP      │→ │Tool      │→ │ config.yaml (allowedTools)
│  │Server   │  │Filter    │  │
│  └─────────┘  └──────────┘  │
│         ↑          │        │
│         │    ┌─────▼─────┐  │
│         │    │MCP Client │  │
│         │    └─────┬─────┘  │
└─────────┼──────────┼────────┘
          │          │ spawn Docker container
          │          ▼
          │  github/github-mcp-server (Docker, ~100 tools)
          │
    Claude requests

Key Components

  • src/index.ts - Entry point, config loading, server initialization
  • src/server.ts - MCP server implementation, tool filtering, meta-tool handlers
  • src/upstream-client.ts - Child process management for upstream GitHub MCP
  • src/config.ts - YAML configuration loading and validation
  • config.yaml - Tool whitelist configuration

Meta-Tools (Always Available)

The proxy provides four built-in meta-tools that are always exposed:

  • list_all_upstream_tools - List all upstream tools (allowed + blocked)
  • list_blocked_tools - List blocked tools by category
  • search_upstream_tools - Search upstream tools by keyword
  • get_tool_info - Get details about a specific tool

Read the full file on GitHub · 118 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 · 118 lines · 800 tokens per session scan A 96043e85fc66

Subscribe to this mod's changes

lightweight-github-mcp CLAUDE.md is an instructions file published in the GitHub repository ham0215/lightweight-github-mcp (0 stars, last pushed 8mo ago), licensed MIT. It adds 800 tokens to every session, about $0.0040 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

spec-kit AGENTS.md

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 · 7,104 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

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

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 · 4,345 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

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