bpftrace MCP Server: generate eBPF to trace linux kernel

A minimal MCP (Model Context Protocol) server that provides AI assistants with access to bpftrace kernel tracing capabilities.

Now implemented in Rust using the rmcp crate for better performance and type safety. The Python implementation is still available in the git history.

Features

• AI-Powered Kernel Debugging: Enable AI assistants to help you debug complex Linux kernel issues through natural language - no eBPF expertise required
• Discover System Trace Points: Browse and search through thousands of kernel probes to find exactly what you need to monitor - from system calls to network packets
• Rich Context and Examples: Access a curated collection of production-ready bpftrace scripts for common debugging scenarios like performance bottlenecks, security monitoring, and system troubleshooting
• Secure Execution Model: Run kernel traces safely without giving AI direct root access - MCPtrace acts as a secure gateway with proper authentication
• Asynchronous Operation: Start long-running traces and retrieve results later - perfect for monitoring production issues that occur intermittently
• System Capability Detection: Automatically discover what tracing features your kernel supports, including available helpers, map types, and probe types

Why MCPtrace?

Debugging kernel issues traditionally requires deep eBPF expertise. MCPtrace changes that.

By bridging AI assistants with bpftrace (the perfect eBPF tracing language), MCPtrace lets you debug complex system issues through natural conversation. Just describe what you want to observe - "show me which processes are opening files" or "trace slow disk operations" - and let AI generate the appropriate kernel traces.

AI never gets root access. MCPtrace acts as a secure gateway, and with its rich collection of example scripts and probe information, AI has everything needed to help you understand what's happening inside your kernel. No eBPF expertise required.

Installation

Prerequisites

1. Install Rust (if not already installed):

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

2. Ensure bpftrace is installed:

sudo apt-get install bpftrace  # Ubuntu/Debian
# or
sudo dnf install bpftrace      # Fedora

Install from crates.io (Recommended)

cargo install bpftrace-mcp-server

This will install the bpftrace-mcp-server binary to your Cargo bin directory (usually ~/.cargo/bin/).

Build from Source

Alternatively, you can build from source:

git clone https://github.com/yunwei37/MCPtrace
cd MCPtrace
cargo build --release

The binary will be available at ./target/release/bpftrace-mcp-server.

Quick Setup

Use our automated setup scripts:

• Claude Desktop: ./setup/setup_claude.sh
• Claude Code: ./setup/setup_claude_code.sh

For detailed setup instructions and manual configuration, see setup/SETUP.md.

Running the Server

If installed via cargo install

bpftrace-mcp-server

If built from source

./target/release/bpftrace-mcp-server

Development mode (from source)

cargo run --release

Manual Configuration

For manual setup instructions for Claude Desktop or Claude Code, see setup/SETUP.md.

Usage Examples

List System Call Probes

await list_probes(filter="syscalls:*read*")

Get BPF System Information

info = await bpf_info()
# Returns system info, kernel helpers, features, map types, and probe types

Execute a Simple Trace

result = await exec_program(
    'tracepoint:syscalls:sys_enter_open { printf("%s\\n", comm); }',
    timeout=10
)
exec_id = result["execution_id"]

Get Results

output = await get_result(exec_id)
print(output["output"])

Security Notes

• The server req

... View full README on GitHub