- ShotAPI MCP Server @smallhandsome/shotapi-mcp-serverScreenshot and HTML render MCP server for AI agents16% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.1 GitHub stars.
- FetchSandbox @fetchsandbox/mcpA deterministic verification engine for agents. Proves a fix: fails on the old code, passes on new.4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.1 GitHub stars.
- MockHero @dinosaur24/mockheroGenerate realistic relational test data — 156 field types, 22 locales, JSON/CSV/SQL, free previews.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.1 GitHub stars.
- ProdPoke @prodpoke/prodpoke-mcpAI QA tester — real browsers scan sites for bugs, SEO, perf, and accessibility issues via chat.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.1 GitHub stars.
- Gridzen Verification @gridzen/verificationCountry verification research, integration planning and synthetic tests. No live identity checks.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- 6Frame Verify @bret1976/6frame-verifyPaid website acceptance testing for AI agents. Quick $3, Full $12, $100 credit pack. MCP + REST.10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Traffic Parrot @trafficparrot/publicTraffic Parrot simulates APIs and messaging. Request or withdraw a trial, read docs, send feedback.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Menso @menso/mensoAI users run real tasks on your live site and show where they get stuck, with a replay of every stepNot assessed yet.A remote server; no sign-in.
- mailsocket @mailsocket/mailsocket-mcpEmail inboxes for AI agents: create an inbox, then block until the OTP or magic link arrives.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
- Hooklistener @hooklistener/mcpWebhook, email, WebSocket and tunnel testing for AI agents: capture, wait, verify, replay.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- AnyHook @anyhook/anyhookA webhook inbox for agents: one call returns a live URL. Mock, verify, inspect and replay.4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- agentcheck @agentwares/agentcheckSynthetic checks, nightly regression replay and model-drift alerts for AI agents4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- DiffCI @adityankale190895/diffciChange-aware CI validation and affected-test guidance for coding agents.4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Whoogy @whoogy/whoogy-mcpCompare Figma designs against live websites and get visual + content QA reports, from inside Claude.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- ViewportWitness by Apex Labs @baffles78/viewport-witnessAgent website testing: browser QA, visual regression, Markdown extraction, and security checks.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- qarunbook @ifeanyiejindu/qarunbookShared app-testing runbook: read the plan, record results per platform, raise and fix issues.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- DiffCI @diffci/diffciFail-closed, change-aware verification for AI coding agents with affected-test guidance.3% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- PlaywrightGen @playwrightgen/playwrightgenApproved test intent, reviewed Playwright automation and run evidence, inside your editor.11% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
- Webhook Toolkit @the-kipdev/webhook-toolkitWebhook URLs for AI agents: receive, wait for, replay, sign and verify webhooks (Stripe, GitHub…).4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Edgehound @energixe/edgehound-mcpWrites adversarial test suites for AI-built code. Your agent's test engineer.11% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- OmniDebugLink @omnidebuglink/omnidebuglinkremote debug iOS/Android/Unity/Godot/Flutter/RN/Web on real-device.ui-tree/screenshots/taps,tests.11% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Loadster @loadster/loadster-mcpLoad testing and synthetic monitoring platform: test with Playwright, Browser Bot, or Protocol Bots.4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Retry Trace @carbaj03/retry-traceInspect external HTTPS 429/503 retries with server-recorded attempts, Retry-After and arrival times.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- FlurryPORT @flurryport/webhooks-and-roomsWebhook capture and replay, delivery pipes, and signed multi-agent rooms. No signup to start.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
