"A software or tool called Desktop Commander" matching MCP connectors:

Drive real Android & iOS devices and web browsers from natural language for mobile + web QA. 145+ tools across device control, app management, automation sessions, browser automation, and flow recording / replay. Bearer-auth — get a token at robotactions.com → Profile → API Tokens.

Prompt evals over MCP: run a prompt on your dataset, score each output 1-5 with an LLM judge.

Evidence-gated task verification for AI agents. Decompose goals into acceptance criteria, attach proof (screenshot, curl, file), independent LLM judge accepts or rejects. 24 tools. Hosted remote MCP (streamable-http, OAuth 2.1 + DCR).

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

Check that your AI is being logical. Free tool that mathematically catches contradictions in agent reasoning. No account needed. Also offers paid guardrails that converts natural language to formal verification proofs, that anyone can check succinctly.

Score any URL against a real design contract — 40 checks, A-F grade, token + motion validation.

MCP tool observatory: do registry servers answer, and are their answers true? No key.

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

A webhook inbox for agents: one call returns a live URL. Mock, verify, inspect and replay.

Accessibility pre-checks (WCAG/BFSG) in a real browser + statement drafts. Pay per call.

Grade MCP servers A to F with the open behavioral litmus. npm: full toolset; hosted: lookups only.

Hire a real human for real-world verification, product testing, AI output review, and errands.

Check if your MCP server is ready to publish on the MCP Registry, Smithery, or npm.

Runs your code against a contract; returns HELD or BROKE at the exact input. Deterministic.

MCP server for the Fail Modes taxonomy — a knowledge base of AI system failure modes

A flock of AI users tests your deployed app and reports where real people get stuck, with fixes.

Benchmark-first release surface with a read-only MCP endpoint and operator CLI.

End-to-end API testing — generate and run tests from OpenAPI, curl, Postman, or real user traffic.

Estimated game fps for any GPU or Apple Silicon chip, with the limiter and tweaks.

Disposable test mailboxes on a real domain: send, receive and assert on real email.