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/delexw/mcpware/claude-mdgit clone --depth 1 https://github.com/delexw/mcpwareWrote 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.
[](https://agentmods.dev/instructions/delexw/mcpware/claude-md)<a href="https://agentmods.dev/instructions/delexw/mcpware/claude-md"><img src="https://agentmods.dev/badge/instructions/delexw/mcpware/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.01106 | $0.01106 |
| Opus 5 | $0.00553 | $0.00553 |
| Sonnet 5 | $0.00221 | $0.00221 |
| Haiku 4.5 | $0.00111 | $0.00111 |
Grade A, and why
mcpware 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 3d 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 — 166 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
This is mcpware - a Python-based MCP (Model Context Protocol) Gateway Server that routes requests to multiple backend MCP servers. The primary purpose is to bypass tool limits in MCP clients by providing a single entry point to access multiple backend services.
Key Architecture
Core Components
gateway_server.py- Main entry point with async stdio handling and signal managementsrc/mcp_protocol_handler.py- Handles MCP protocol operations and message routingsrc/backend_forwarder.py- Manages request forwarding to backend serverssrc/config.py- Configuration management with environment variable substitutionsrc/jsonrpc_handler.py- JSON-RPC request/response handling
Request Flow
- MCP client sends request via stdio → gateway_server.py
- JSONRPCHandler parses request → routes to MCPProtocolHandler
- MCPProtocolHandler determines backend → BackendForwarder executes
- Backend response flows back through the same chain
Backend Management
- Backends are configured in
config.jsonwith command/args/env - Each backend runs as a separate process (Docker containers, npm packages, etc.)
- Gateway manages backend lifecycle and handles process communication via stdio
Common Development Commands
Setup and Installation
# Install dependencies
make install
# or
pip install -r requirements.txt
# Create virtual environment (recommended)
python -m venv venv
source venv/bin/activate # On Windows: venv\Scripts\activate
Testing
# Run all tests
make test
# or
pytest
# Run tests with coverage
pytest --cov=src --cov=gateway_server --cov-report=html
# Run specific test file
pytest tests/test_config.py
# Run in watch mode (requires pytest-watch)
pytest-watch
Development
# Run locally (requires config.json)
python gateway_server.py --config config.json
# Run with debug logging
python gateway_server.py --config config.json --log-level DEBUG
# Clean build artifacts
make clean
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.
- 3d ago First seen · 166 lines · 1,106 tokens per session scan A da1198507d54
mcpware CLAUDE.md is an instructions file published in the GitHub repository delexw/mcpware (3 stars, last pushed 1y ago), licensed MIT. It adds 1,106 tokens to every session, about $0.0055 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
plano CLAUDE.md
Instructions for katanemo/plano, covering claude.md, build & test commands, rust — wasm plugins (must target wasm32-wasip1), rust — brightstaff binary (native target) and rust — tests, format, lint.
telepresence AGENTS.md
Instructions for telepresenceio/telepresence, covering agents.md, project overview, git workflow, design plans and build artifacts.
zentinel AGENTS.md
Instructions for zentinelproxy/zentinel, covering zentinel, philosophy (north star), architecture, crates and core crates.
Morpheus-Lumerin-Node AGENTS.md
Instructions for MorpheusAIs/Morpheus-Lumerin-Node, covering agents.md — guidance for ai agents and coding assistants, how to load documentation (follow this order), priority reading (find these sections in llms-full.txt), concept references (cite from these) and how-tos by role.
prodex AGENTS.md
Instructions for christiandoxa/prodex, covering agents.md, scope and source of truth, project summary and ownership, before changing code and mojo-first development.
mcp-all-in-one AGENTS.md
Instructions for vtxf/mcp-all-in-one: These instructions are for AI assistants working in this project.