Testing and QA MCP servers

Top 100 by trust score Trust score 0–100

• io.github.SPerekrestova/interactive-leetcode-mcp

  Interactive LeetCode MCP server with authorization and solution submission capabilities

  npm 97

• io.github.srbsa/diffgate

  Deterministic guardrail your coding agent runs on itself: diff-scoped findings, zero LLM tokens.

  npm 97

• Devloop

  Browser + dev-server logs on one correlated timeline, for Claude Code and AI agents.

  npm 97

• tieline

  Static FE-BE contract-drift checker: finds frontend calls the backend does not expose. CLI + MCP.

  npm 96

• HIG Doctor

  Apple Human Interface Guidelines search, lookup, and project audits for AI coding agents.

  npm 96

• RuleDrift

  Test whether AI agents retain critical instructions as conversations grow.

  npm 96

• Evidrift

  Catch TypeScript API and OpenAPI contract drift in AI-generated code, then revalidate it in CI.

  npm 95

• humanizer-ru

  Следы нейросети в русском тексте: балл чистоты 0-100, запреты и маркеры с позициями, факт-замок.

  pypi 95

• A11Y Toolkit

  The accessibility layer for AI coding agents: audit, fix, document and watch - WCAG 2.2.

  pypi 95

• Web Validator by DigestSEO

  Audit public webpages and supplied markup for HTML, CSS, SEO, JSON-LD, and link issues.

  remote · npm 94

• T1/T2 Protocol

  Caller-side T1/T2 heterogeneous validation MCP server. Stdlib-only Python.

  pypi 94

• io.github.hubertgajewski/playwright-report-mcp

  Run Playwright tests and surface structured results for AI agents doing test failure analysis.

  npm 94

• DocGuard

  Deterministic doc-drift detection: guard, score, explain, verify-claims and diagnose MCP tools.

  npm 94

• Perfonext Render MCP

  MCP server for analyzing React Profiler exports: rerenders, commit spikes, slow components.

  npm 94

• Metro MCP

  MCP server for React Native/Expo runtime debugging, inspection, and automation via Metro/CDP

  npm 94

• ResiliReplay

  Run bounded, deterministic MCP reliability tests and generate executable regressions.

  npm 93

• Orbilo

  Check whether a website is ready for AI agents (UCP, WebMCP, Access) and monitor your own sites.

  remote 93

• nittim

  Production-safety audits for AI-generated code, with a fix for every finding.

  remote 93

• io.github.Dave-London/pare-test

  Pare Test ג€” Auto-detects test framework (pytest, jest, vitest, mocha), returns typed JSON.

  npm 93

• io.github.Dave-London/python

  Structured Python tool output (ruff, mypy, pip-audit, pip-install) as typed JSON.

  npm 93

• io.github.Dave-London/test

  Auto-detects test framework (pytest, jest, vitest) and returns structured results.

  npm 93

• io.github.egulatee/codecov

  MCP server for querying Codecov coverage data with configurable URL support

  npm 93

• Jarroba Tools · Test audit

  Audits tests instead of writing them: what each one really asserts. 4 tools, local.

  npm 93

• Iris

  Stop shipping agents on vibes. Score every agent output for quality, safety, and cost.

  mcpb · npm 93

• SeedBase Test Data

  Generate realistic, FK-consistent synthetic test data for your databases from your AI assistant.

  remote · npm 93

• io.github.nickjlamb/opengate-mcp

  Check whether an AI answer is grounded in its context — deterministic, no LLM judge.

  npm 93

• io.github.PierreJanineh/tech-debt-mcp

  MCP Server for analyzing technical debt across multiple programming languages

  npm 93

• isitdone

  Make a coding agent prove it: run the repo's real tests, typecheck and lint before it says done.

  npm 93

• rendercheck

  Check generated audio, video and stills for defects. Returns a verdict, not more media.

  pypi 93

• Chart Color Audit

  CI-friendly accessibility audit for chart color palettes: WCAG contrast, CVD simulation, OKLab ΔE.

  npm 93

• io.github.bch1212/modelwatch

  Continuous behavioral drift monitoring for LLM apps — catches silent provider model updates.

  npm 92

• Godot Agent Loop

  MCP automation loop with 167 tested tools for Godot 4

  npm 92

• A11y Check

  Web accessibility scanning (WCAG 2.2 AA + KWCAG 2.2) with Korean remediation guides

  npm 92

• io.github.decantr-ai/mcp-server

  Stable eight-tool MCP server for changed-UI assurance, authority-aware UI task context, and repair.

  npm 92

• pixelpact

  Extract a visual contract from a reference page and measure an implementation against it

  npm 92

• nomue Record Verifier

  Local verification of nomue Protocol Records; current release supports the Release 1 Welch bundle.

  npm 92

• io.github.mshegolev/allure-testops-mcp

  Allure TestOps MCP — projects, launches, test cases, test results via REST API.

  pypi 92

• io.github.specshield-io/specshield-mcp-server

  The API-change deploy gate for AI coding agents. Read-only breaking-change detection.

  npm 92

• ai.canaryusers/canaryusers

  A flock of AI users tests your deployed app and reports where real people get stuck, with fixes.

  remote 91

• Circuitarium MCP

  MCP tools for CRUMB artifacts and Logisim-evolution analysis and non-interactive simulation.

  npm 91

• io.github.lvlrSajjad/sidecrew

  Code changes and unit tests by local MLX models, behind a gate a machine can run.

  npm 91

• io.github.mobile-next/mobile-mcp

  MCP server for iOS and Android Mobile Development, Automation and Testing

  npm 91

• DataContractGate

  Infer, dry-run, deploy, and inspect DataContractGate semantic data contracts.

  npm 91

• io.github.nugehs/gate

  One ship/no-ship verdict from aiglare, bouncer, tieline & repoctx — the unified merge gate.

  npm 91

• MusicXML Comparer

  Music-aware, multi-level comparison of two MusicXML files

  pypi 91

• io.github.snayyar00/webability

  Free WCAG 2.2/ADA/508 accessibility MCP: scan, AI fixes, verify, vision audit, localhost tunnel

  remote · npm 91

• RepoRipple

  Deterministic repository change-impact analysis for engineers and coding agents.

  pypi 90

• Sounio Compiler

  Check, compile, run, and test Sounio programs locally.

  pypi 90

• Phyll

  UX review for apps built with AI, run by your own agent. The fixes keep your design.

  npm 90

• Agent Reliability

  Testing, benchmarking and auditing autonomous AI agents — methods, harnesses, evidence

  remote 90

• io.github.HeroSizy/cucumberstudio

  MCP server for Cucumber Studio - test scenarios, action words, and execution data

  npm 90

• io.github.JustinBeckwith/linkinator-mcp

  MCP server for link checking using linkinator

  npm 90

• Godot MCP

  Agent-driven Godot playtesting: editor control, input injection, game-time stepping, live state.

  npm 90

• Signalint

  Local stdio MCP server for cached, loop-aware JS/TS diagnostics (Oxlint, tsc, Biome, ESLint).

  npm 90

• Readiness scorer — can an agent sign up to your SaaS?

  Probe a signup URL you own and score whether an AI agent can sign up unaided.

  remote 89

• agent-device

  MCP server for mobile app automation: verify, control, and debug iOS, Android, TV, and desktop apps

  npm 89

• Snapshot Site

  Capture screenshots, detect visual regressions between page versions, and analyze with AI.

  remote · npm 89

• squirrelscan

  Website QA for your coding agent: audit SEO, performance, security, accessibility over MCP.

  remote 89

• Qase Test Management

  Official MCP server for Qase — manage test cases, runs, suites, defects via AI tools.

  remote · npm 89

• WSG Check

  Check websites against the W3C Web Sustainability Guidelines and look up the guidelines

  npm 89

• Bruno MCP Studio

  Author, edit and run Bruno collections as files: HTTP, WebSocket, gRPC, per-request pass/fail.

  npm 89

• io.github.abhinavteja123/codemore

  The static analyzer your AI agent reads — fix-ready, machine-readable scan reports over MCP.

  npm 88

• ChargerDojo

  OCPI versions, what changed between them, and which modules and journeys ChargerDojo tests.

  remote 88

• Human For AI

  Hire a real human for real-world verification, product testing, AI output review, and errands.

  remote · npm 88

• MCP Endpoint Lint - handshake, tool schemas, JSON-RPC errors

  {"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"whoami","arguments":{}}} free no key

  remote 88

• io.github.Eason0in/testlink-mcp

  AI-friendly, safety-first TestLink MCP server

  npm 88

• io.github.saiffmirza/kiyas

  AI design fidelity — compare Figma designs or screenshots against rendered UI. No API keys.

  npm 88

• Multisim MCP

  Generate Multisim circuits, run simulations, export data, and create experiment reports.

  pypi 88

• io.github.AdrianStauffer/copilot-studio-friction-index

  Evidence-based register of known Copilot Studio errors and limits, with dated, human-verified fixes.

  remote 87

• HefestoAI

  HefestoAI checks AI-generated code before you ship it.

  remote 87

• VibeFix

  Tests your live app like a first customer, free. One exact fix to paste in your builder, re-tested.

  remote 87

• com.webmcp-tool/agent-readiness

  Scores any public website on how usable it is by AI agents, with per-check evidence.

  remote 87

• io.github.DownAtTheBottomOfTheMoleHole/megalinter

  MCP server for running Ox Security MegaLinter via mega-linter-runner

  npm 87

• io.github.Hushlor/mcp-server-tauri

  A Model Context Protocol server for use with Tauri v2 applications

  npm 87

• Vynix

  Give AI coding agents access to your Vynix visual feedback, bug reports, and AI diagnosis.

  remote · npm 87

• IA-QA — 130+ QA & Dev Tools for AI Agents

  130+ QA & dev tools for AI agents: prompt injection, RAG testing, VLM eval, guardrails. Free.

  remote 87

• io.github.prashantsinghmangat/tracebug

  AI agents read TraceBug bug reports (console, network, replay, repro timeline) from local disk.

  npm 87

• QualityMax QA MCP

  Final release; the checks moved to 9lives (9l mcp). Local QA MCP: scan, inspect, repro, run tests.

  npm 87

• CodeCraft

  Checks whether generated Minecraft Bedrock content will actually load. Nine read-only tools.

  remote 87

• DiscreteRate

  Run DRS demos (Fast-Slow Drain, Hamburger Duo, Valdez Tanker) and explore the paradigm.

  remote 86

• Tailscale Compute

  Run builds, tests, and benchmarks on your own Tailscale compute node.

  npm 86

• io.github.oguzc/playwright-wizard-mcp

  MCP server providing Playwright test generation wizard with intelligent prompts and best practices

  npm 86

• io.github.pipehero/pipehero

  Debug webhooks from your AI agent: inspect and replay captured webhooks on localhost.

  remote 86

• io.github.salrad22/code-sentinel

  Code quality analysis MCP server - detects security issues, deceptive patterns, and placeholders

  npm 86

• Verificate MCP

  Agentic code review, no signup to try: reality gates + frontier-model review, with veto.

  remote 85

• RTBlint

  Validate OpenRTB bid requests and responses against IAB specs. ARTF, Rust core.

  remote 85

• com.shonanfarm/sukimalabo-tester

  みんなのテスター（スキマラボ）公開情報MCP。Google Playクローズドテストのテスター集めを支援する相互テストコミュニティの情報を提供する。

  remote 85

• Reality Graph Verification Tools

  Read-only AI coding tools for change verification, release readiness, capacity, and guidance.

  remote 85

• M00N Report

  Test management over MCP: author cases, run manual executions, cut releases, read health

  npm 85

• io.github.machinegrade/validate

  Deterministic validation for AI-generated artifacts: JSON Schema, OpenAPI response, SQL syntax.

  remote · npm 85

• io.github.vola-trebla/react-render-profile-mcp

  Decodes React DevTools Profiler exports into render summaries and memoization advice for AI agents.

  npm 85

• MCP Compliance

  CLI tool and MCP server that tests MCP servers for spec compliance

  npm 85

• io.github.arose26/zapier-dev-mcp

  For Zapier integration developers: inspect, lint, and validate zapier-platform-cli projects.

  npm 84

• io.github.Bishop81/accessibility-scanner-mcp

  Scan any URL for WCAG accessibility issues (axe-core) and get per-element fixes for an AI agent.

  npm 84

• QueueSim

  Run M/M/c queue simulations and four scenarios (call center, ER, coffee shop, single server).

  remote 84

• io.github.dingdawg/dingdawg-code-review

  AI code review — security, quality, performance. Learns your patterns. Receipted.

  npm 84

• io.github.electron-stagewright/core

  Agentic UX testing for real Electron apps: launch, inspect, interact, and assert through MCP.

  npm 84

• Godot Forge

  Godot 4 MCP server — test runner, API docs, script analysis, scene parsing, LSP.

  npm 84

• GridProof

  Gridproof your UI — automated spacing & grid QA in the agent loop (MCP server).

  npm 84

• io.github.hypothesi/mcp-server-tauri

  A Model Context Protocol server for use with Tauri v2 applications

  npm 84