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.
npx agentmods add instructions/sperekrestova/github_mcp_server/claude-mdgit clone --depth 1 https://github.com/SPerekrestova/GitHub_MCP_ServerWhat 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 | $0.00676 | $0.00676 |
| Opus 5 | $0.00338 | $0.00338 |
| Sonnet 5 | $0.00135 | $0.00135 |
| Haiku 4.5 | $0.00068 | $0.00068 |
Grade A, and why
GitHub_MCP_Server 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.
How it starts
The opening of the file, as written. The whole thing — 72 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
GitHub MCP Server - A Model Context Protocol (MCP) server that provides GitHub API access for fetching and searching documentation in /doc folders across GitHub organizations. Built with Gradio for Hugging Face Spaces deployment.
Development Commands
# Setup
python3 -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt
cp .env.example .env # Add GITHUB_TOKEN
# Run locally (starts Gradio server with MCP support)
python main.py
# Server runs on http://localhost:7860
# MCP endpoint: http://localhost:7860/gradio_api/mcp/
Architecture
Single-file MCP server (main.py) using Gradio with MCP support:
-
MCP Tools (exposed via
gr.Interfacewithmcp_server=True):get_org_repos_tool- List repos with/docfolder detection (uses Search API first, falls back to listing all)get_repo_docs_tool- Get documentation files from repo's/docfolderget_file_content_tool- Fetch and decode file content (handles base64)search_documentation_tool- Search docs across org using GitHub Code Search API
-
Business Logic Functions (async, testable):
get_org_repos(),get_repo_docs(),get_file_content(),search_documentation()- Tool functions are async wrappers with error handling
-
Gradio Interface:
gr.TabbedInterfacecombining 4 tool interfaces- Each tool has its own
gr.Interfacefor web UI access - MCP tools auto-exposed at
/gradio_api/mcp/
Key Implementation Details
- GitHub API strategy: Search API first for efficiency, fallback to paginated list + check each repo
- Supported doc types:
.md,.mmd,.mermaid,.svg,.yml,.yaml,.json - Content decoding: Base64 content from GitHub API is automatically decoded
- Error handling: All tools return JSON with
{"error": "..."}on failure - MCP Schema: Available at
/gradio_api/mcp/schema
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 · 72 lines · 676 tokens per session scan A f97472b8eaec
GitHub_MCP_Server CLAUDE.md is an instructions file published in the GitHub repository SPerekrestova/GitHub_MCP_Server (0 stars, last pushed 4mo ago), licensed MIT. It adds 676 tokens to every session, about $0.0034 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.
Other instructions, from other repositories
arxiv-mcp-server CLAUDE.md
Instructions for blazickjp/arxiv-mcp-server, covering claude.md, project, setup and validation, architecture and tool groups.
mcp-server-excel llm-testing-philosophy.instructions.md
Instructions for sbroenne/mcp-server-excel, covering llm testing philosophy, what are llm tests?, the golden rule, what never belongs in a test and ❌ xfail or skip markers.
mcp-server-excel readme-management.instructions.md
Instructions for sbroenne/mcp-server-excel, covering readme management - quick reference, core entry documents, feature documentation, critical rules and tool & action counts must match.
mcp-server-excel development-workflow.instructions.md
Instructions for sbroenne/mcp-server-excel, covering development workflow, branch protection, development process, pr review comment workflow and retrieve inline code review comments using github cli.
mcp-server-excel extension-development.instructions.md
Instructions for sbroenne/mcp-server-excel, covering vs code extension development instructions, extension overview, changelog and changesets (critical), version management and automatic version management (unified release workflow).
mcp-server-excel copilot-instructions.md
Instructions for sbroenne/mcp-server-excel, covering github copilot instructions - excelmcp, repository map, environment, working rules and build and validation.