Open-source AI agent firewall for MCP security and agent egress. Scans mediated HTTP, MCP, A2A, and WebSocket traffic for exfiltration, SSRF, and prompt injection, and emits mediator-signed action receipts: verifiable audit evidence from outside the agent.
Latest release v3.7.0 · 14 Oct 2026
2 files for Codex, OpenCode and Claude Code: pipelock AGENTS.md, pipelock CLAUDE.md — 3,184 tokens loaded in every session.
AGENTS.md A 3,179 tok CLAUDE.md A 5 tok These files are luckyPipewrench/pipelock's own configuration — they tell Codex, OpenCode and Claude Code how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.