Aguara MCP runs on your own machine — the client starts it, so there is no endpoint to ping. Last commit 2 Jul 2026.
Scan skills, MCP configs, and agent content for injection and supply-chain risks. Offline, no LLM.
Today is the operative word: we check Aguara MCP every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
Audit MCP configs and skill files for over-broad scope and injection risk. 6 of 8 free.
Scan an MCP server or agent config for injection, exfiltration, and risky capabilities.
Security firewall for AI agents — scans MCP calls for injection, secrets, and risks.
Scans MCP servers for tool poisoning, prompt injection and supply chain risks.
Security scanner for AI agent skills and MCP servers
Pre-install security scanner for AI agent skills (local stdio MCP). Offline static scan; no upload.
Pre-injection context compression for coding agents. Zero LLM calls, zero telemetry, offline-safe.
Multi-layer security scanner for MCP servers and agent skills (injection, exfiltration)
Answers built from our own checks of this server.