MCP CheckMCP servers for testing
Every testing server in the official MCP Registry, 85 in all, ranked by how closely it fits. 72 work without an API key. Each row shows the security checks, the secrets asked for and an install command.
testing MCP servers 85
Now showing are unlisted. These entries didn't pass our listing filter: no source repo, a very short or duplicated description, or a publisher with 100+ servers. Same automated checks, shown as-is. How we check
| Type | Secrets | Version | Actions | ||||
|---|---|---|---|---|---|---|---|
★ 17 io.github.AishwaryShrivastav/vibe-testing Code-aware browser testing agent — 14 Playwright tools for AI code editors via MCP | 7/7All passed | 66health of 100 | npmRuns locally | Noneno keys asked | 0.4.6 | ||
★ 13 io.github.cocaxcode/api-testing-mcp MCP server for API testing. 35 tools: HTTP, assertions, flows, OpenAPI, collections. | 7/7All passed | 45health of 100 | npmRuns locally | Noneno keys asked | 0.11.12 | ||
★ 4 io.github.chriswu727/argus Testing MCP for coding agents: exercise real user journeys, find bugs, verify them with evidence. | 7/7All passed | 66health of 100 | PyPIRuns locally | Noneno keys asked | 0.11.0 | ||
 ★ 1 com.glockapps/mcp Inbox placement tests across Gmail, Outlook, Yahoo and 30+ providers. | 3/3All passed | 50health of 100 | RemoteHosted | Noneno keys asked | 1.0.0 | ||
io.github.Schoasch/backtesting-arena Crypto backtesting & Bitcoin cycle analytics. Point-in-time, DSR-corrected, look-ahead-aware. | 4/4All passed | 43health of 100 | RemoteHosted | Noneno keys asked | 1.13.0 | ||
 ★ 19k io.github.keploy/mcp End-to-end API testing — generate and run tests from OpenAPI, curl, Postman, or real user traffic. | 3/3All passed | 87health of 100 | RemoteHosted | Noneno keys asked | 1.0.0 | ||
★ 13k io.github.seleniumbase/seleniumbase Stealthy browser automation, testing, and web-scraping via CDP Mode. | 6/71 warning | 85health of 100 | PyPIRuns locally | Noneno keys asked | 4.56.4 | ||
★ 10k io.github.mobile-next/mobile-mcp MCP server for iOS and Android Mobile Development, Automation and Testing | 7/7All passed | 93health of 100 | npmRuns locally | Noneno keys asked | 1.0.14 | ||
★ 420 io.github.koreal6803/finlab-ai Quantitative trading toolkit with 900+ data columns, backtesting, and 60+ strategy examples. | 4/4All passed | 70health of 100 | RemoteHosted | Noneno keys asked | 1.1.0 | ||
★ 398 io.github.ai-dashboad/flutter-skill AI-powered E2E testing for 10 platforms. 253 MCP tools. Zero test code needed. | 6/71 warning | 69health of 100 | npmRuns locally | Noneno keys asked | 0.9.36 | ||
★ 398 io.github.telsav/flutter-skill AI E2E testing bridge — give AI eyes and hands inside any app. 8 platforms, 40+ tools. | 6/71 warning | 69health of 100 | npmRuns locally | Noneno keys asked | 0.7.6 | ||
★ 244 io.github.PramodDutta/qaskills Search, inspect, and install 400+ QA testing skills from qaskills.sh into any MCP client. | 7/7All passed | 69health of 100 | npmRuns locally | Noneno keys asked | 0.1.2 | ||
★ 182 io.github.satelliteoflove/godot-mcp Agent-driven Godot playtesting: editor control, input injection, game-time stepping, live state. | 7/7All passed | 78health of 100 | npmRuns locally | Noneno keys asked | 4.1.11 | ||
★ 156 io.github.WaterTian/wechat-devtools-mcp MCP Server for WeChat DevTools CLI - Automate development & testing with 7 aggregated APIs. | 7/7All passed | 71health of 100 | PyPIRuns locally | Noneno keys asked | 0.9.20 | ||
★ 140 io.github.hidai25/evalview-mcp Regression testing for AI agents. Golden baselines, CI/CD, LangGraph, CrewAI, OpenAI, Claude. | 6/71 warning | 74health of 100 | PyPIRuns locally | 1secret asked | 0.6.0 | ||
★ 135 io.github.KryptosAI/mcp-observatory MCP security scanner. CI-native testing, attack simulation, health scoring, and SARIF. | 5/72 warnings | 73health of 100 | npmRuns locally | Noneno keys asked | 1.36.1 | ||
★ 107 io.github.sathergate/flagpost Feature flags for Next.js. One file, full control with A/B testing. | 7/7All passed | 55health of 100 | npmRuns locally | Noneno keys asked | 0.1.1 | ||
★ 52 io.github.rafsilva85/credit-optimizer Optimizes Manus AI credit usage by 30-75% via intelligent model routing and smart testing. | 7/7All passed | 50health of 100 | PyPIRuns locally | Noneno keys asked | 5.2.0 | ||
★ 37 io.github.jongalloway/dotnet-mcp AI assistant access to .NET SDK for projects, packages, building, testing, and development tools. | 4/4All passed | 62health of 100 | NuGetRuns locally | Noneno keys asked | 1.1.2 | ||
★ 33 io.github.NeuZhou/stratevo Quantitative trading: quotes, backtesting, screening, and genetic algorithm strategy evolution. | 7/7All passed | 45health of 100 | PyPIRuns locally | Noneno keys asked | 6.0.3 | ||
★ 32 com.mcparmory/browserbase Create and control browser sessions for web automation, testing, and AI agent tasks | 7/7All passed | 51health of 100 | PyPIRuns locally | Noneno keys asked | 1.0.4 | ||
 ★ 29 io.github.localstack/localstack-mcp-server A LocalStack MCP Server providing essential tools for local cloud development & testing | 7/81 warning | 63health of 100 | npmRuns locally | 7secrets asked | 0.5.0 | ||
★ 28 io.github.nirholas/solidity-compiler Browser Solidity compiler IDE - smart contract development testing deploy | 2/2All passed | 55health of 100 | RemoteRuns locally | Noneno keys asked | 1.0.0 | ||
★ 26 io.github.operantlabs/operant-mcp Security testing MCP server for penetration testing, forensics, and vulnerability assessment | 6/71 failed | 26health of 100 | npmRuns locally | Noneno keys asked | 1.0.1 | ||
 ★ 25 io.github.igrlk/uiverify Visual testing for coding agents: your agent sees every UI change it makes and triages each diff. | 3/3All passed | 58health of 100 | RemoteHosted | Noneno keys asked | 1.2.0 | ||
★ 22 io.github.sapiom/mcp Local Sapiom developer MCP for authoring, testing, deploying, and inspecting agents. | 7/7All passed | 63health of 100 | npmRuns locally | Noneno keys asked | 0.20.0 | ||
★ 19 ai.orangepro/mcp Find test gaps, generate grounded tests, and dynamically prove behavior with mutation testing. | 7/7All passed | 69health of 100 | npmRuns locally | 2secrets asked | 0.2.59 | ||
★ 19 io.github.OrangeproAI/orangepro Find test gaps, generate grounded tests, and dynamically prove behavior with mutation testing. | 7/7All passed | 69health of 100 | npmRuns locally | 2secrets asked | 0.2.12 | ||
★ 16 io.github.demwick/polymarket-agent-mcp Polymarket trading, market discovery, copy trading and backtesting — 48 MCP tools. | 7/81 warning | 55health of 100 | npmRuns locally | 4secrets asked | 1.7.0 | ||
★ 15 io.github.monkeywave/frida-mobile-mcp Mobile Frida MCP Server - AI-powered mobile app exploration and testing via Frida instrumentation | 7/7All passed | 67health of 100 | npmRuns locally | 1secret asked | 0.6.0 | ||
★ 12 io.github.electron-stagewright/core Agentic UX testing for real Electron apps: launch, inspect, interact, and assert through MCP. | 6/71 warning | 65health of 100 | npmRuns locally | Noneno keys asked | 0.7.0 | ||
★ 11 io.github.smbcloudXYZ/xcrs MCP tools for testing mobile and TV apps on iOS simulators, Android phones, and Apple/Android TV. | 3/41 warning | 55health of 100 | CargoRuns locally | Noneno keys asked | 0.7.5 | ||
★ 11 io.github.enessubass/mobiloop-mcp Guarded AI mobile Appium testing, security scanning, verification, and fix-retest MCP tools. | 4/4All passed | 58health of 100 | DockerRuns locally | Noneno keys asked | 0.1.0-alpha.15 | ||
★ 11 io.github.Xplo8E/hacktricks-mcp-server Search and query HackTricks pentesting documentation with quick lookup and section extraction | 6/71 warning | 40health of 100 | npmRuns locally | Noneno keys asked | 1.3.4 | ||
★ 10 io.github.austin-starks/nexustrade-mcp Quant research, backtesting, marketplace subscriptions, editable forks, copy trading, and execution. | 3/3All passed | 62health of 100 | RemoteHosted | Noneno keys asked | 1.0.1 | ||
★ 9 io.github.zomma-dev/quantcontext Deterministic stock screening, backtesting, and factor analysis for AI trading agents | 7/7All passed | 54health of 100 | PyPIRuns locally | Noneno keys asked | 0.1.2 | ||
★ 9 ai.com.mcp/petstore Swagger Petstore API (v1.0.27) as MCP for testing and prototyping powered by the HAPI MCP server | 4/4All passed | 49health of 100 | RemoteHosted | Noneno keys asked | 0.6.0 | ||
★ 7 io.github.fastslack/e2e-runner JSON-driven E2E test runner with parallel Chrome pool execution and 16 MCP tools. | 7/7All passed | 47health of 100 | npmRuns locally | Noneno keys asked | 1.3.0 | ||
★ 6 io.github.Xerolo44/rpgmaker-mv-mcp MCP server for reading, editing, and playtesting RPG Maker MV projects | 7/7All passed | 58health of 100 | npmRuns locally | Noneno keys asked | 0.5.1 | ||
★ 4 io.github.jrpool/kilotest Ensemble testing of web pages for accessibility, usability, and web standards | 4/4All passed | 54health of 100 | RemoteHosted | Noneno keys asked | 60.9.1 | ||
★ 4 io.github.Wopee-io/wopee-mcp AI testing agents for web apps — dispatch test runs, crawls, fetch artifacts and status. | 7/7All passed | 57health of 100 | npmRuns locally | 1secret asked | 1.32.0 | ||
 ★ 4 io.github.anilloutombam/mcp-failure-lab Deterministic fault-injection server for testing how MCP clients handle failures and recover. | 7/7All passed | 70health of 100 | npmRuns locally | Noneno keys asked | 0.13.1 | ||
 ★ 4 ai.getminds/minds Run AI market research: synthetic customer panels for concept testing, message testing, segments. | 3/3All passed | 58health of 100 | RemoteHosted | Noneno keys asked | 2.0.2 | ||
 ★ 3 io.github.skulitom/anode Background Windows desktop for AI agents: native GUI automation, screenshots and app testing. | 4/4All passed | 48health of 100 | MCPBRuns locally | Noneno keys asked | 0.11.3 | ||
★ 3 io.github.USHIKUNDESUYO/shiwake-mcp Journal entry testing (JET) for accounting audits. 15 screening rules, zero dependencies. | 7/7All passed | 53health of 100 | npmRuns locally | Noneno keys asked | 0.3.1 | ||
★ 3 io.github.MikhailHal/ariadne Returns only the unit tests affected by your current Kotlin/Android code changes. | 4/4All passed | 45health of 100 | DockerRuns locally | Noneno keys asked | 0.4.0 | ||
★ 2 io.github.jarbon/carbon AI testing harness with Jay: risk-based checks, bug investigation, and local evidence reports. | 7/7All passed | 52health of 100 | npmRuns locally | Noneno keys asked | 1.32.22-free.17 | ||
★ 2 io.github.tidynest/raven-nest-mcp AI-driven penetration testing - 22 security tools behind safety-hardened MCP endpoints | 4/4All passed | 51health of 100 | DockerRuns locally | Noneno keys asked | 0.4.1 | ||
★ 2 io.github.copyleftdev/kahea Deterministic HTTP/WebSocket testing and policy-gated API execution for AI agents. | 5/61 warning | 60health of 100 | MCPBRuns locally | Noneno keys asked | 0.3.1 | ||
★ 2 io.github.skuzadev/wpfpilot-mcp Automate Windows WPF apps from AI agents with semantic UIA selectors and FlaUI test generation. | 7/7All passed | 44health of 100 | npmRuns locally | Noneno keys asked | 0.1.1 |
Showing 1 to 50 of 85. These are the most recently updated; search or pick a category for the rest.
testing MCP servers: what to know before you pick one
Which testing MCP server should I use?
Among community builds, the most-starred on GitHub are Vibe Test — Browser Testing Agent (★ 17), api-testing-mcp (★ 13) and Argus — Testing for Coding Agents (★ 4). If you want one that passed every check, Vibe Test — Browser Testing Agent did.
Can I trust these testing MCP servers?
On registry checks, 72 of 85 come out clean. We also read the code or live tool list of 61 of them without running anything, and 9 raised a warning worth reading, such as an install script or text aimed at the AI. Treat a pass as "nothing found", and give any server the least access that works.
How do I add a testing MCP server to Claude?
To connect testing through Vibe Test — Browser Testing Agent, use this Claude Desktop (npm) entry: {
"mcpServers": {
"vibe-testing": {
"command": "npx",
"args": [
"-y",
"vibe-testing@0.4.6"
]
}
}
}. Pin the version shown before you rely on it.
Do I have to install a testing MCP server?
29 can run hosted, so you only paste a URL into Claude, Cursor or VS Code. The 59 that run locally ship as 39 npm, 11 PyPI, 3 Docker, 3 MCPB bundle, 1 NuGet and 1 Cargo packages.
Which testing MCP servers need no API key?
72 of the 85 list no secrets, including Vibe Test — Browser Testing Agent, api-testing-mcp and Argus — Testing for Coding Agents. Some still ask you to sign in once they run.
Who makes these testing MCP servers?
No company-verified one yet (checked 31 Oct 2026). All 85 testing servers are community builds from 84 different publishers, so check who is behind one before you hand it a testing key.
More topics: every “MCP server for…” page. Prefer a skill? Claude skills for this (1,373).