"Information about Unreal Engine 5 (UE5)" matching MCP connectors:
GET /v1/connectors – MCP directory API referenceMatching Connector Tools:
Risk-scan a diff, flag AI-generated-code tells, find secrets. 5 of 7 tools need no account.
Prove real MCP clients can connect: 5-client x 3-IdP OAuth matrix with shim fixes.
Free platform to test MCP clients without installing anything. Create mock tools with dynamic templates, configurable delays, conditions (if/then), and response sequences. Supports JSON-RPC 2.0 over Streamable HTTP. Built-in text_echo and json_echo tools. Rate-limited tiers: anonymous (5 calls/min, 1 mock tool), registered (10 calls/min, 4 mock tools), premium (60 calls/min, unlimited). Zero setup — no install, no registration required. More info: https://www.testmcp.dev
Website audits for AI agents: 69 checks with exact fixes, plus verify. 5 free a day, then x402.
Prompt evals over MCP: run a prompt on your dataset, score each output 1-5 with an LLM judge.
X-Z-CS AI validation with auditable reasoning. 8 active tools; 5 in maintenance. v0.5.66
Adversarial behavioural-bias engine — audits your decisions for cognitive biases via your own AI.
A deterministic verification engine for agents. Proves a fix: fails on the old code, passes on new.
Independent AI model test scores on 5 tasks: inbox, scheduling, receipts, finance, support replies.
Seven tools over the tabnas parsing engine: parse, validate, diagnose, fixtures, compare.
Check whether AI assistants can reach, read and cite a public website. No account for 4 of 5 tools.
Free MCP, API auth, webhook and schema diagnostics with bounded checks and safe quote routing.
Compare two versions of a JSON row list: what was added, removed or changed, field by field.
Verify artifacts, hand off public state, and record, check and find evidence about capabilities.
PQS scores any prompt before the model runs. 8 dimensions. 5 frameworks. Pre-flight, not post-hoc.
Scores any MCP server before you trust it: free quick check, full paid report, 2-5 way compare.
Deterministic recipe verification engine — validates AI-generated recipes against master SOPs.
SEO site audit MCP: up to 5 supplied URLs for on-page issues, plus Lighthouse page-speed scores.
Pay-per-call AI evaluation MCP server. Score LLM outputs against benchmark rubrics via Workers AI.
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.
Google PageSpeed Insights (Lighthouse) scores, Core Web Vitals and top speed fixes for every URL...
Evidence-governed screening of material decisions about physical assets and operational systems.
Compare two JSON files deeply without worrying about key or array order. Detect missing, extra, an…
