mcp-trace: Instructions file for Claude Code

CLAUDE.md

mcp-trace CLAUDE.md is an instructions file for Claude Code from zabirauf/mcp-trace. It costs 2,900 tokens per session, scanned A, original, MIT.

A project-specific instruction file for mcp-trace, a Rust terminal interface that proxies and monitors communication between Model Context Protocol (MCP) clients and servers.

In plain words
What is it for?
Use it when working on MCP traffic interception, JSON-RPC forwarding, real-time terminal logs, proxy status, or the Rust workspace.
Why use it?
It explains the project’s separate proxy, monitor, and shared-library components so changes fit the existing architecture.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is zabirauf/mcp-trace's own configuration. It tells Claude Code how to work on mcp-trace itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mcp-trace configures →

Reuse

Borrowing it

Nothing to install: this file belongs to zabirauf/mcp-trace. 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/zabirauf/mcp-trace/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/zabirauf/mcp-trace

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.

agentmods badge for mcp-trace CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/zabirauf/mcp-trace/claude-md.svg)](https://agentmods.dev/instructions/zabirauf/mcp-trace/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/zabirauf/mcp-trace/claude-md"><img src="https://agentmods.dev/badge/instructions/zabirauf/mcp-trace/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,900 This file is loaded in full into every session.
When invoked 2,900 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.02900 $0.02900
Opus 5 $0.01450 $0.01450
Sonnet 5 $0.00580 $0.00580
Haiku 4.5 $0.00290 $0.00290

Measured 7d ago against content hash 1274b6ffa01c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

mcp-trace 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 7d 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 · 418 lines

How it starts

The opening of the file, as written. The whole thing — 418 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 when working with the MCP Proxy TUI project.

Project Overview

This is a Terminal User Interface (TUI) application built with Rust and Ratatui that acts as a proxy and monitor for Model Context Protocol (MCP) server traffic. It consists of two separate binaries that work together to intercept, log, and display all communication between MCP clients and servers in real-time.

Architecture

The project is structured as a Cargo workspace with two main components:

1. MCP Proxy (mcp-proxy)

  • Purpose: STDIO-based proxy for MCP servers
  • Language: Rust with tokio for async operations
  • Functionality: Intercepts and forwards JSON-RPC communication, sends logs to monitor
  • Binary location: target/release/mcp-proxy

2. MCP Monitor (mcp-monitor)

  • Purpose: TUI for monitoring multiple MCP proxies
  • Language: Rust with Ratatui for terminal UI
  • Functionality: Real-time display of logs, statistics, and proxy status
  • Binary location: target/release/mcp-monitor

3. Shared Library (mcp-common)

  • Purpose: Common types, IPC communication, and message protocols
  • Components: Types, IPC (Unix sockets), JSON-RPC handling
MCP Client → [mcp-proxy] → MCP Server (STDIO)
                 ↓ (IPC)
           [mcp-monitor TUI]
                 ↓
           [Log Storage]

Repository Information

GitHub Repository: zabirauf/mcp-trace

Binary Distribution

When setting up binary distribution, only the mcp-trace binary should be distributed. The other binaries (mcp-monitor and mcp-proxy) are for internal use only and should not be included in public distributions.

Commit Message Style

Keep git commit messages concise and direct. Avoid verbose explanations.

Branch Management

For new tasks unrelated to the current work, always create a new branch from main:

git checkout main
git pull origin main
git checkout -b feature/new-task-name

Read the full file on GitHub · 418 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.

  1. 7d ago First seen · 418 lines · 2,900 tokens per session scan A 1274b6ffa01c

Subscribe to this mod's changes

mcp-trace CLAUDE.md is an instructions file published in the GitHub repository zabirauf/mcp-trace (12 stars, last pushed yesterday), licensed MIT. It adds 2,900 tokens to every session, about $0.0145 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

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

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

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

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 · 4,469 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

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