The real catalog of tools for AI agents

Design review as MCP tools: critique, states, journeys, UI copy, PRD assumptions. BYOK or hosted.

Read-only MCP server over Verdict QA state: verdicts, findings, flaky quarantine, history.

Sandboxed test runs for coding agents: compact typed verdicts with failure fingerprints and history

Preserve a user-authorized judgment and append later answers. No model verdict or human score.

Attestation infrastructure for the agentic economy: signed, independently verifiable verdicts.

MCP for rules/skills/knowledge evaluation for Cursor, Claude, VS Code, and Antigravity.

Pre-purchase trust checks for AI agents: recalls, scam signals, proceed/caution/avoid verdict.

Send anything. Get the truth — REAL, SUSPICIOUS or LIKELY SCAM verdicts on messages and links.

Decision tracking with prediction validation and outcome gates for AI agents

Physics-based validation of simulation results: receipts with per-check verdicts, via MCP.

Polymarket preflight verdicts: OK/CAUTION/VETO on orders, COPY/WATCH/VETO on wallets. x402-paid.

Praxis: published trading strategies re-run and audited — verdicts, claimed vs measured stats.

GitHub repo maintainability verdicts—maintained, slowing, at-risk, abandoned—via MCP.

Verdict, the due-diligence house for DeFi: keyless ratings, methodology and a hack incident feed.

A performance marketer's run/fix/kill verdict for AI agents — ad creative, campaigns, targeting.

Building-permit verdicts by address, with cited records. SF, Seattle, Austin, NYC. Pay per call.

Remote MCP for A2A caller identity, scope policy, verdict receipts, and audit history.

Pay-per-call onchain reads (Base, Ethereum, Gnosis), token verdicts and LLM chat over x402 USDC

Unpaid-vs-ARC book verdicts, catalog facts, series order, and sample reviews.

Post-scrape data cleaner, no LLM: repairs mojibake, HTML, invisible chars. Plus a verdict.