"Creating or working on a website" matching MCP connectors:
GET /v1/connectors – MCP directory API referenceMatching Connector Tools:
Benchmark SQL queries, rewrites and indexes on real Postgres, MySQL and SQL Server at scale.
Test healthcare AI agents' medication claims against cited FDA label text. Not for clinical use.
Check if your website or Android app tracks visitors before cookie consent; catch broken analytics.
MCP-native AI browser testing for coding agents. Submit a URL + goal, get back action trail, bugs, screenshots, and WebM video your agent patches from directly. 43 tools, 12 AI evaluation personalities, combo tiers with auto-pause-on-bugs, throwaway email + SMS inboxes.
Check an A2A agent before you delegate, or an MCP server's measured conduct. Free, no key.
Design quality gate for AI-generated UI: score any URL on 45 deterministic checks, A–F grade.
Build, check and report on MIDAS CIVIL NX bridge models and design tendons, with MIDAS IT plugins.
Live website CMP banner auditor, Cookie dark pattern detector, and EU AI Act Article 50 transparency disclosure compliance checker for generative chatbots.
Lint a SKILL.md for frontmatter, structure, secrets and size. All 6 tools free.
Checks a public web page for accessibility problems and explains each one in plain English.
Risk-scan a diff, flag AI-generated-code tells, find secrets. 5 of 7 tools need no account.
Verification for AI coding agents: runs the tests and checks a change affects, with a receipt.
Test inboxes for your app's sign-up and login emails: get the code or link, or why none came.
Check JSON against a JSON Schema with exact paths, and schemas for OpenAI, Claude and Gemini strict.
Turn messy exports into clean, consistent data agents can trust, with every change logged.
Run regexes on real engines (JavaScript, RE2/Go) against test strings, and prove ReDoS safety.
Next run times of a cron expression in any time zone, to catch UTC vs local-time mistakes.
Free website tracking audit, no account needed: GTM, GA4, Meta Pixel, Consent Mode v2, server-side
Designed test case pack audit, delivered per API call as an atom service on Conduit Atoms.
Behind Second Look (preview): a shop's product page as clean data, source checks, price history.
AI support desk: tickets with acceptance criteria, estimates, time tracking, tests and mockups.
Check a link's share card on X, Facebook, LinkedIn: real image size, tag problems, fixed tags.
Neutral acceptance and signed agent-delivery verification over MCP + x402 USDC on Base.
Website audits for AI agents: one-call AI visibility report, schema, WCAG, PageSpeed, AI crawlers.
Test MCP server run by InterfaceDelta. Its harmless tools change on purpose to test change tracking.
Let your coding agent QA what it builds: plain-English tests run in real Chrome or on iPhone, iPad and Android, with a verdict, replay and evidence for every check, and a fix prompt when something fails. Get your first 10 tests free, no card needed: https://testsy.dev
Applied ML validation, delivered per API call as an atom service on Conduit Atoms.
Database design review audit, delivered per API call as an atom service on Conduit Atoms.
Defined-flow auditor, delivered per API call as an atom service on Conduit Atoms.
Read the verification code (OTP) and test emails your app sends to a catch-all test hostname. Four read-only tools: list_domains, get_latest_otp, list_messages, get_message. Needs a MailBots API key from the 14-day free trial (no card, no DNS) or a paid plan. Setup: https://mailbots.top/docs/mcp
Run Google Lighthouse audits on any URL — performance, SEO, accessibility scores.
QA platform for agents: coverage signals, in-repo test plans, verified tests and release governance.
Lighthouse scores, Core Web Vitals and what to fix on any page
Frontend implementation audit: a deliverable delivered per API call as an independent atom.
Assumption audit, delivered per API call as an atom service on Conduit Atoms.
C engineering review, delivered per API call as an atom service on Conduit Atoms.
Rag retrieval evaluation tuning, delivered per API call as an atom service on Conduit Atoms.
Direction, award-tier motion blocks and a local check for coding agents that build websites.
Adversarial testing for AI agents that move money: engine battery, Ed25519-sealed verdict reports.
Free SEO, AI visibility (AI crawlers, llms.txt, JSON-LD) and security-header checks for any URL.
Agent evaluation scorecard, delivered per API call as an atom service on Conduit Atoms.
Your agent says “done”. CheckMyApp uses your live app as a real user and tells it what broke.
Cloud Android phones for AI agents: give phones a task in plain words and get the answer
Load testing and synthetic monitoring platform: test with Playwright, Browser Bot, or Protocol Bots.
Check links live: broken, soft 404, redirects, missing anchors. Check a quote is really on a page.
Local-first sync design audit: a deliverable delivered per API call as an independent atom service.
Verify AI-generated code before you commit: independent reviewers check it. PR review too.
Agentic coding practice verdict, delivered per API call as an atom service on Conduit Atoms.
Agent safety guardrail audit, delivered per API call as an atom service on Conduit Atoms.
Correctness verification certificate, delivered per API call as an atom service on Conduit Atoms.
Release-readiness verdict, delivered per API call as an atom service on Conduit Atoms.
Zero knowledge claim audit, delivered per API call as an atom service on Conduit Atoms.
Stateless validation and PDF/A-3b envelope auto-repair for Factur-X 1.09.2, EN 16931 and French 2026 e-invoicing reform (BR-FR-CTC / Chorus Pro). Zero invoice retention.
Agentic AI quality engineering: run, debug and triage tests on real browsers and devices
Screwtape.ai decides whether an AI agent is allowed to spend money, and keeps the proof. Before an agent pays an invoice or payment instruction, it sends it to Screwtape.ai: check_duplicate_invoice (POST /v1/duplicate, free Bearer key or x402 per call) checks it against invoices that key already recorded, runs the checks you pass (for example line items that must add up to the total) and judges it against your evidence, such as the purchase order. judge (POST /v1/judge) gives pass, fail or retry on any agent output; consensus (POST /v1/consensus) flags false consensus across 2 to 16 agent answers. Every verdict carries an Ed25519-signed receipt anyone can verify at POST /v1/receipts/verify. judge and consensus can be paid per call with x402 ($0.005 USDC on Base or Solana, no account); a free key gives 10 calls per UTC day.
Open a React Native app in a simulated phone: read the screen, tap, type, set device state.
Efficient web build standard audit: a deliverable delivered per API call as an atom service.
Free AI visibility check: can AI crawlers read a site, and do ChatGPT, Gemini, Perplexity cite it?
Free compare_page_observations for two held JSON pages. No fetch, wallet, or payment.
Full-stack build audit: a deliverable delivered per API call as an independent atom service.