bpftrace

Provides Linux kernel tracing capabilities through bpftrace integration with probe discovery, helper function documentation, asynchronous program execution with timeout protection, and buffered output retrieval for system debugging and performance monitoring.

This MCP server provides AI assistants with Linux kernel tracing capabilities through bpftrace integration, built by eunomia-bpf using Python with FastMCP and asyncio for concurrent execution management. The implementation offers four core tools: probe discovery with filtering support, helper function documentation, asynchronous bpftrace program execution with configurable timeouts, and buffered output retrieval with pagination, all backed by subprocess management that handles sudo authentication and automatic cleanup of execution buffers. Built with in-memory output buffering, timeout protection, and background cleanup tasks, it serves system administrators needing kernel-level debugging through conversational interfaces, performance engineers requiring real-time system call tracing, and developers wanting to integrate eBPF-based monitoring into AI-assisted troubleshooting workflows with automatic result collection and management.