- 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.
- Checktrail @stsepelin/checktrailLocal code validation with explicit execution trust and evidence of what actually ran.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- 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.
- Schema Sieve @mrfentmen/schema-sieve-mcpLocal JSON Schema structure inspection and privacy-safe fixture planning. Tools include inspect...4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Flaky History @mrfentmen/flaky-history-mcpLocal aggregate test-history stability analysis without test names or raw result contents. Tools...4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Sidecrew @lvlrsajjad/sidecrewCode changes and unit tests by local MLX models, behind a gate a machine can run.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- EmbeddedCI BenchPod @embeddedci-com/embeddedci-mcpDrive a BenchPod hardware-in-the-loop bench: power, flash, UART, I2C, CAN, analog and logic.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- JevSim @huaaudio/jevsimRun verified iOS and Android UI workflows in one agent tool call with Jev.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- 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.
- KeyboardExtAX @nikitosina/keyboard-ext-axAccessibility snapshots and tap coordinates for active third-party iOS keyboards in Simulator.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- 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.
- B2IGE Verify @b2ige2-a11y/b2ige-verifyIndependent deterministic verification for AI-written software. Local, evidence-backed checks.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.
- VibeView @vibeview/vibeviewDrive cloud iOS, Android, Apple TV, Android TV and Roku devices to verify app changes.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- DVERA CT verification tools @suresofttechnologies/dvera-mcpDVERA drives CT verification of mission-critical C/C++: setup, analysis, tests, coverage.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.
- Achlens @mscott9160-web/achlensLocal-first MCP server and CLI for validating and generating synthetic ACH files.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- IsolatedTester — TinkyVision system @agewellepm/isolated-testerIsolated macOS app tests, MCP images, OCR/ASCII frames, accessibility and evidence reports.12% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.
- Asdesigned @maher-reven/asdesignedDiff a rendered UI element against its Figma source and get every drifted property with its delta.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Glitch Toolkit @abstractglitch/glitch-toolkitRead-only checks that fail a guardrail which is present but has stopped refusing anything5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- 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.
- Snapsurf @zumerlab/snapsurfWeb navigation and verification for AI agents: page digest, typed diff per action, assertions.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Agenthub Monitor @nevelsk65/agenthub-monitorRenders a pipeline DAG and test-harness dashboard inline as an MCP App3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.
