bpftrace
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.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-02.
Scan details: Circle-IR · 2026-09-02 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- monitoring
- Source
- PulseMCP
- Repository
- github.com/eunomia-bpf/mcptrace
- Author type
- human
- Last scanned
- 2026-09-02
- Updated
- 2026-09-02
Use via MCP
Resolve bpftrace from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.