What is claude-mcp CLAUDE.md?

A project instruction file for a tool that connects Claude Code, a command-line coding assistant, with stored framework and library documentation. It describes fetching, indexing, storing, and searching that documentation.

Fetching framework documentation, registering it, storing it by version, searching it, and making it available to Claude Code.

It helps the coding assistant use documentation collected for specific frameworks and versions instead of relying only on its built-in knowledge.

How RLabs-Inc/claude-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to RLabs-Inc/claude-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/RLabs-Inc/claude-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/RLabs-Inc/claude-mcp

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/rlabs-inc/claude-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/rlabs-inc/claude-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/rlabs-inc/claude-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/rlabs-inc/claude-mcp/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/rlabs-inc/claude-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/rlabs-inc/claude-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 668 This file is loaded in full into every session.

When invoked 668 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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 5.1	$0.00668	$0.00668
Opus 5.5	$0.00267	$0.00267
Sonnet 5.5	$0.00134	$0.00134
Haiku 4.5	$0.00067	$0.00067

Measured 2mo ago against content hash ed5bc5145262, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

claude-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 2mo 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 · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Helper File

Project Overview

This project is a Master Control Program (MCP) server that integrates with Claude Code CLI. The primary objective is to extend Claude's capabilities by providing tools that Claude can use directly when generating code.

Main Purpose

Provide Claude with access to up-to-date documentation for frameworks and libraries
Enable Claude to follow current best practices and use the latest APIs
Integrate seamlessly with Claude Code CLI through a plugin system

Core Features

Documentation fetcher tool that scrapes and indexes documentation
Interactive CLI (docadd) for managing framework documentation
Search functionality for finding information within documentation
Claude Code integration that allows Claude to use fetched documentation

Implementation Notes

Framework registration is persisted to disk in data/framework-registry.json
Documentation is stored in the docs/ directory, organized by framework and version
Scrapers automatically extract content from framework documentation sites
Users interact with the system primarily through claude fetch-docs <framework> command

Build & Test Commands

Install: bun install
Development server: bun dev
Start server: bun start
Build: bun build
Lint: bun lint
Format: bun format
Typecheck: bun typecheck
Test: bun test
Test single: bun test -t "test name"
Clean: bun clean

Current Progress

Framework Registry Persistence ✅: Framework configurations are now saved to disk
Interactive CLI ✅: Added comprehensive CLI tool for managing frameworks
Documentation Fetcher ✅: Core scraping and processing functionality works
Claude Code Integration ✅: Basic integration established
Rate Limiting & Robustness ✅: Added intelligent rate limiting and robust error handling
Site-Aware Scraping ✅: Enhanced scraper detects documentation site structure
Language Filtering ✅: Implemented filtering for non-English content
Search Improvements ✅: Implemented graceful fallback for search with improved error handling
Error Recovery ✅: System now recovers gracefully from various error conditions

Read the full file on GitHub · 63 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.

2mo ago First seen · 63 lines · 668 tokens per session scan A ed5bc5145262

Subscribe to this mod's changes

claude-mcp CLAUDE.md is an instructions file published in the GitHub repository RLabs-Inc/claude-mcp (5 stars, last pushed 1y ago), licensed MIT. It adds 668 tokens to every session, about $0.0027 per session on Opus 5.5. 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.

claude-mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
claude-mcp CLAUDE.mdRLabs-Inc/claude-mcp	Instructions file	5	1y ago	MIT	A	668	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,685	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,086	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	280k	2d ago	MIT	A	4,325	Codex, OpenCode

claude-mcp: Instructions file for Claude Code