Testing

Generates tests from acceptance criteria, then converges code with an agent that never sees them.

Sealed X11/Wayland sessions to see, drive and check real GUI programs: a11y, pictures, sound.

Turn an OpenAPI spec into WireMock stubs, contract tests and chaos scenarios, on local LLMs.

Ymigo MCP Server — Mathematical flow coverage analysis for Claude

End-to-end-encrypted, sovereign inbox for AI agents. The server only ever sees ciphertext.

Windows 11 desktop automation and vision-LLM QA via MCP

Enterprise-grade Windows automation MCP server for AI agents — 53 tools including click_text, wait_for_text, structured OCR, UI Automation, and batch operations

Capture HTTP, email, and DNS callbacks with webhook.site from MCP clients.

Find and fix first-person weapon bugs behind a gate: your game's probe measures, the Gate judges

FastMCP server for interactive Wayland window/desktop streaming, semantic UI inspection, boundary-clamped input injection, and desktop integration.

MCP server for autonomous multi-VM cluster orchestration on libvirt/QEMU

Read-only MCP server over Verdict QA state: verdicts, findings, flaky quarantine, history.

Sandboxed test runs for coding agents: compact typed verdicts with failure fingerprints and history

MCP server for UI Bridge - enables AI to inspect and interact with UI elements

UI Blackbox Tester MCP — natural-language UI testing for Claude Desktop via Playwright

Android mobile automation with uiautomator2. AI bot for taps, swipes, apps, XPath testing, RPA.

MCP server that tells flaky tests from genuinely broken ones using real CI run history, and generates synthetic test data / API contract diffs for QA automation.

MCP server exposing TestRail API endpoints as tools for LLMs

Generate load testing with k6 and Amazon Relay

Drive a running tModLoader (Terraria) instance from an agent: launch, query, screenshot, read state.