What is mcp-mcp CLAUDE.md?

A project instruction file for MCP-MCP, a service that discovers and provides MCP servers, which are tools that let an agent access external capabilities. It also defines note-taking, setup, testing, and architecture rules.

Use it when developing, testing, building, running, or documenting MCP-MCP with Python and the uv package manager.

It keeps development notes and project practices consistent and records the commands needed to work on the Python project.

How wojtyniak/mcp-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to wojtyniak/mcp-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/wojtyniak/mcp-mcp/master/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/wojtyniak/mcp-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/wojtyniak/mcp-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/wojtyniak/mcp-mcp/claude-md)

Your own site

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

Per session 2,185 This file is loaded in full into every session.

When invoked 2,185 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	$0.02185	$0.02185
Opus 5	$0.01092	$0.01092
Sonnet 5	$0.00437	$0.00437
Haiku 4.5	$0.00218	$0.00218

Measured 12d ago against content hash da9e8fe7e4c7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

mcp-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 12d 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 · 210 lines

How it starts

The opening of the file, as written. The whole thing — 210 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.

Journal

Keep development journal in @JOURNAL.md. Update it after each major change.

Note-Taking Guidelines

When asked to take notes: 1) Fill out @JOURNAL.md; 2) Add only the most important information to @CLAUDE.md

Development Setup

This project uses Python 3.13+ with uv as the package manager and direnv for environment management.

Essential Commands:

uv sync - Install/update dependencies (automatically triggered by direnv)
uv add <package> - Add a dependency
uv run pytest - Run unit tests
uv run main.py - Run the application
uv build - Build package for distribution
uvx mcp-mcp - Install and run via uvx (end-user command)
just update-readme - Update server count in README.md (test after README changes)

Environment Configuration: No special environment configuration required. Uses standard Python/uv project setup.

Project Architecture

See @PRD.md for the product requirements and architecture documentation.

MCP-MCP (Meta-MCP) Server - A tool discovery and provisioning service for MCP servers that helps AI assistants dynamically find, containerize, and use MCP servers on-demand.

Core Technology Stack:

Python 3.13+ with uv package manager
Key dependencies: httpx, mcp, sentence-transformers, rich, pydantic-settings
Planned: Docker for server containerization, GitHub API for discovery

Development Status:

MVP Complete: Multi-source discovery with semantic search and security hardening ✅
Future Work: Docker integration, MCP protocol proxy, advanced server management

Current Architecture Patterns:

Multi-Source Discovery: Aggregate servers from 3 curated sources with intelligent deduplication
Semantic Search: Use sentence-transformers for accurate capability matching
Security Middleware: Origin validation preventing DNS rebinding attacks
Production Distribution: Automated releases with precomputed data for fast startup

Read the full file on GitHub · 210 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.

12d ago First seen · 210 lines · 2,185 tokens per session scan A da9e8fe7e4c7

Subscribe to this mod's changes

mcp-mcp CLAUDE.md is an instructions file published in the GitHub repository wojtyniak/mcp-mcp (23 stars, last pushed 2mo ago), licensed MIT. It adds 2,185 tokens to every session, about $0.0109 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 2026-08-30.

Building agents

next.js AGENTS.md

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

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 · 5,153 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

mcp-mcp: Instructions file for Claude Code