"Information about medical law" matching MCP connectors:

Declare what your app does and where it operates; get cited, jurisdiction-specific findings.

Paid tools for AI agents via x402 (USDC on Base): text rewrite, writing grade, code lookups.

Exact text tools for AI agents: unified diff, patch apply, regex testing, grapheme counting.

Permission-aware onboarding MCP server: answers about a codebase, filtered by the caller's role.

Tell your assistant you're about to launch. It checks the app your builder synced to GitHub, tells you what would break for real users, hands you the fix, and re-checks after the sync. Point it at any public repo first (nothing to install, nothing to grant) and see exactly what comes back before you connect the one that matters.

Audit GitHub Actions workflows for script injection, unpinned actions and missing permissions.

Audit Dockerfiles for root users, baked-in secrets, curl-pipe-shell and unpinned base images.

Scan text and git diffs for committed credentials using real vendor key formats plus entropy.

Scan AI agent skills and configs for hidden Unicode, prompt injection and exfiltration.

Static analysis for Pine Script v6 strategies — catches backtest-vs-live divergence traps.

Detects catastrophic-backtracking (ReDoS) regex risk via AST parsing, with JS-safe rewrites.

Audits MCP tool definitions for patterns that make models call tools wrong or mis-fill args.

Compare two JSON files deeply without worrying about key or array order. Detect missing, extra, an…