Launches any MCP server as a real client would, running the handshake, inspecting every tool's schema and description, and deliberately making a bad tool call to test error handling. Returns one deterministic, evidence-backed score with named issues so servers can be verified before users' agents hit them in production.
Open-source MCP server that audits websites for AI search readiness, providing deterministic scoring (0-100) and prioritized fix lists for metrics like JSON-LD, llms.txt, heading hierarchy, and AI crawler access.
Enables read-only security assessment of a public MCP endpoint by sending initialize and tools/list requests and returning a 0–100 score covering transport, auth, overly broad tools, injection phrasing, and rug-pull definition changes, plus a 12-probe prompt-injection suite against a bot you own that flags leaked system prompts, tool dumps, secrets, exfiltration channels, and canary obedience.
Local-first production-readiness MCP server for AI-built apps. It runs read-only checks, produces an evidence-based readiness score, and guides fixes before launch.