Testing

Screenshot capture, AI analysis, OCR, visual regression testing, token compression — headless server + MCP tools for AI coding CLIs

KaDeep Studios CLI: AI end-to-end testing from your terminal, CI/CD and coding agents. Run test suites on web, mobile and desktop, read results, gate releases, and give Cursor or Claude Code KaDeep as MCP tools.

Command-line compliance test kit + security audit for A2A (Agent2Agent) protocol endpoints. Validates agent cards, JSON-RPC conformance, auth, and SSRF/TLS/CORS. Emits JSON, JUnit, SARIF, badge, snapshot diff.

Upload Android, iOS and HarmonyOS apps to PGYER and manage their apps and versions.

MCP server for browser inspection with Puppeteer - network monitoring and console error tracking

Local MCP server exposing captured bug reports and local server logs to an AI coding agent.

Let your AI coding agent test its own frontend work. Connects Claude Code, Cursor, and any MCP client to your real Chrome browser — real sessions, real cookies, no headless conflicts.

Quality checker for MCP servers — validates protocol handshake, discovery, tool-call dry-runs, and latency

MCP server for QA automation: test scenarios, Playwright codegen, execution, and GitHub bug creation

Inspect MCP servers and write a local readiness report.

MCP server for AI-driven API testing — HTTP, GraphQL, WebSocket, OAuth2, assertions, chained test suites, and SQLite-persisted history with JSON diff comparison.

Feedbug MCP server: read visual bug reports (screenshot, console, DOM context) and let your AI agent trace them to source and fix them.

Thiqah Playwright MCP server with org-standard guardrails and integrated instructions file.

AI QA Agent Platform — Skills-driven 8-stage test automation workflow CLI

MCP server that connects to your browser for real-time DOM, CSS, layout inspection, screenshot capture, and Figma design comparison — your IDE's AI agent sees exactly what users see

Run real MCP clients against your server and diff their rendered tool surface against tools/list. Deterministic — no LLM calls.

MCP server for the open marketing-mindset skill: test-size math, kill rules, AEO agent-readiness audit, a marketing-engineer JD generator and a playbook gate (is it time to write a playbook, or still search?) as callable tools for any MCP client (Claude C

MCP server for macOS desktop automation: give AI agents the ability to see and control macOS apps via the Accessibility API. Background GUI testing, sub-millisecond element access, self-healing locators. Works with Claude, Cursor, Windsurf, and any MCP cl

Behaviour specs with a coverage ratchet: one markdown file per behaviour, a committed manifest, CI-gated against drift, verified per wave. Ships a stdio MCP server and the docket/1 run protocol.

MCP server for iOS app testing — see inside your running app: network calls, WebSocket frames, logs, UserDefaults, screen layout, and API mocking. Works with Claude Code, Cursor, Codex, Windsurf.