agentmods.dev

mcproxy CLAUDE.md

A project-guidance document for mcproxy, a tool that sits between Claude Code and external tool servers and controls which tools are available.

In plain words
What is it for?
Use it when building, testing, or changing mcproxy, especially its TypeScript source, configuration files, proxy behavior, or documentation.
Why use it?
It gives contributors the project’s commands, file layout, architecture, and naming rules in one place.

Instructions file

20 7mo ago A scan 384 tokens original MIT
View the source file team-attention/mcproxy
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/team-attention/mcproxy/claude-md
Clone the repo
git clone --depth 1 https://github.com/team-attention/mcproxy
Per session 384 This file is loaded in full into every session.
When invoked 384 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 $0.00384 $0.00384
Opus 5 $0.00192 $0.00192
Sonnet 5 $0.00077 $0.00077
Haiku 4.5 $0.00038 $0.00038

Measured 2d ago against content hash 7f09b45990d7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcproxy 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.

CLAUDE.md · 41 lines

What it actually says

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

MCP Proxy for Claude Code - intercepts MCP server requests and filters tools based on .mcproxy.json configuration. Allows users to enable/disable specific MCP tools to reduce token consumption.

Commands

npm run build      # Compile TypeScript to dist/
npm test           # Run tests in watch mode
npm test -- --run  # Run tests once
npm run dev        # Run with tsx (development)

Architecture

Message Flow:

Claude Code ←→ mcproxy (stdio) ←→ MCP Server (subprocess)
                  ↓
            .mcproxy.json (tool config)

Key Modules:

  • src/index.ts - CLI entry point using Commander
  • src/proxy/mcp-proxy.ts - Main proxy class, manages upstream subprocess and stdio streams
  • src/proxy/message-handler.ts - Intercepts tools/list (filters response) and tools/call (blocks disabled tools)
  • src/config/config-manager.ts - Manages .mcproxy.json file, auto-registers new tools with enabled: true
  • src/config/mcp-config-reader.ts - Reads .mcp.json to auto-detect server name for config keys
  • src/filter/tool-filter.ts - Simple filter logic using ConfigManager

Server Name Resolution: The proxy reads .mcp.json to find which server name (e.g., "linear", "github") matches the current upstream command, then uses that as the key in .mcproxy.json.

File Naming

Use kebab-case for all TypeScript files (e.g., mcp-proxy.ts, config-manager.ts).

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. 2d ago First seen · 41 lines · 384 tokens per session scan A 7f09b45990d7

Subscribe to this mod's changes

mcproxy CLAUDE.md is an instructions file published in the GitHub repository team-attention/mcproxy (20 stars, last pushed 7mo ago), licensed MIT. It adds 384 tokens to every session, about $0.0019 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.

Related

Other instructions, from other repositories

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

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

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