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.

Last push 4 hours ago

agent-security ai-agent-security ai-agents ai-firewall ai-security dlp egress-proxy github-action golang integrity-monitoring llm-firewall llm-security mcp mcp-security prompt-injection security security-scanning security-tools ssrf ssrf-protection

Created

Feb 2026

Total stars

1,008

7 days

+19

30 days

+72

12 months

+1,008

Star trends

README badge

Best of Go badge for pipelab-org/pipelock
[![Best of Go](https://bestofgo.dev/badge/pipelab-org/pipelock.svg)](https://bestofgo.dev/pipelab-org/pipelock)