MCPtrace: Instructions file for Claude Code

CLAUDE.md

MCPtrace CLAUDE.md is an instructions file for Claude Code from eunomia-bpf/MCPtrace. It costs 687 tokens per session, scanned D, original, MIT.

A CLAUDE.md instruction file for an MCP server that lets AI assistants observe and debug the Linux kernel with bpftrace. bpftrace is a tool for tracing what the operating system kernel is doing.

In plain words
What is it for?
Use it when developing or operating the server's probe listing, system information, asynchronous tracing, and result-retrieval tools.
Why use it?
It explains how to build, run, and test the Rust server and identifies its tracing operations.

Instructions file for Claude Code

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

This is eunomia-bpf/MCPtrace's own configuration. It tells Claude Code how to work on MCPtrace 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 MCPtrace configures →

Reuse

Borrowing it

Nothing to install: this file belongs to eunomia-bpf/MCPtrace. 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/eunomia-bpf/MCPtrace/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/eunomia-bpf/MCPtrace

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 MCPtrace CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/eunomia-bpf/mcptrace/claude-md/github.svg)](https://agentmods.dev/instructions/eunomia-bpf/mcptrace/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/eunomia-bpf/mcptrace/claude-md"><img src="https://agentmods.dev/badge/instructions/eunomia-bpf/mcptrace/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.

agentmods 80×15 button for MCPtrace CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/eunomia-bpf/mcptrace/claude-md"><img src="https://agentmods.dev/badge/instructions/eunomia-bpf/mcptrace/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 687 This file is loaded in full into every session.
When invoked 687 The same file — it is already loaded in full.
Security scan D 3 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 $0.00687 $0.00687
Opus 5 $0.00344 $0.00344
Sonnet 5 $0.00137 $0.00137
Haiku 4.5 $0.00069 $0.00069

Measured 9d ago against content hash 35793e6b0a37, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade D, and why

MCPtrace CLAUDE.md scanned grade D with 3 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 9d 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

- Requires sudo access for bpftrace execution

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh
CLAUDE.md · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 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 a bpftrace MCP (Model Context Protocol) server that provides AI assistants with access to Linux kernel tracing capabilities. The server acts as a bridge between AI models and the bpftrace tool, enabling kernel-level system observation and debugging.

The server is implemented in Rust using the rmcp crate from the rust-sdk.

Development Commands

Setup and Dependencies

# Install Rust (if not already installed)
curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh

# Build the server
cargo build --release

Running the Server

# Direct execution
./target/release/bpftrace-mcp-server

# Through cargo
cargo run --release

Testing

# Run unit tests
cargo test

# Run with verbose output
cargo test -- --nocapture

Architecture

The server is built with the rmcp crate and provides four main tools:

  1. list_probes - Lists available bpftrace probes with optional filtering
  2. bpf_info - Shows bpftrace system information and capabilities
  3. exec_program - Executes bpftrace programs asynchronously
  4. get_result - Retrieves execution results

Key Components

  • ExecutionBuffer (src/main.rs): Manages async output collection from bpftrace processes
  • DashMap execution_buffers: Thread-safe concurrent storage for active executions
  • Cleanup task: Background task that removes old buffers after 1 hour
  • BpftraceServer: Main server struct implementing the MCP ServerHandler trait

Security Considerations

  • Requires sudo access for bpftrace execution
  • Server reads sudo password from BPFTRACE_PASSWD environment variable (set in .env file)
  • Alternative: Configure passwordless sudo for bpftrace: sudo visudo then add username ALL=(ALL) NOPASSWD: /usr/bin/bpftrace
  • No script validation - relies on AI to generate safe bpftrace programs
  • Resource limits: 60s execution timeout, 10k line output buffer

Read the full file on GitHub · 86 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. 9d ago First seen · 86 lines · 687 tokens per session scan D 35793e6b0a37

Subscribe to this mod's changes

MCPtrace CLAUDE.md is an instructions file published in the GitHub repository eunomia-bpf/MCPtrace (72 stars, last pushed 6mo ago), licensed MIT. It adds 687 tokens to every session, about $0.0034 per session on Opus 5. A static security scan graded it D with 3 findings (asks for root, downloads and executes remote code, makes network calls). 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

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

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

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

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