MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
Free, API-keyless MCP for resilient web search and safe, visible Chrome automation—with dynamic companion status, forms, uploads, and WebGL testing.
★ 2 -
NIA AI Web Evaluation Agent MCP Server - Autonomous browser testing and debugging
npm MIT -
@nguyenthdat/burpmcpgithub.com/nguyenthdat/burp-mcpupdated this year
Burp Suite MCP server with 80+ tools for authorized web security testing
npm MIT -
periscope-mcpgithub.com/segentic-lab/periscope-mcpupdated this year
Web-app QA, testing & analysis for AI agents — 74 Playwright tools: authenticated flows (2FA/SSO), 25-action E2E workflows, hard assertions, session reports, and accessibility / SEO / GEO / Core-Web-Vitals + Lighthouse audits across a page or a full crawled site. Battle-tested by an AI agent on real apps.
AGPL-3.0 ★ 10 -
siteglass-mcpgithub.com/siteglassio/siteglass-mcpupdated this year
MCP server for siteglass.io — agent-driven web QA: register a site, scan it, auto-generate and run E2E test flows, read results + replay. Pay-per-action in credits over Bitcoin Lightning.
npm MIT -
AI-powered App Test Automation MCP Server - iOS, Android, Flutter, React Native, Web
MIT -
getjoinableactive
Joinable's self-test and MCP server: check a web game's multiplayer integration with two headless players, and give coding agents the Joinable kit. https://getjoinable.com
npm UNLICENSED -
MCP tools that help coding agents test web apps systematically, find bugs, and deliver evidence-backed reports and regression tests for supported findings.
MIT ★ 7 -
telegram-bot-testing-mcpgithub.com/0x216/telegram-bot-testing-mcpupdated this year
Write test scenarios for your Telegram bot — Claude runs them like a human QA. MCP server driving the official Telegram Web client in a real browser: structured reads, button presses, files, screenshots, Mini Apps. No MTProto libraries.
MIT ★ 2 -
SpectreWeb-AIgithub.com/tuannguyen14/SpectreWeb-AIupdated this year
Self-Learning AI for Manual Web Penetration Testing
★ 14 -
Assertline's hosted MCP server: find your recorded web tests, run them and read step-by-step results. Instructions only.
MIT -
Open-source E2E testing an AI agent records for you. Plain-language tests, recorded once on your real app (web, desktop, SAP, Citrix, AI agents), replayed on every commit with zero LLM calls.
npm Apache-2.0 ★ 6 -
Generate realistic test data that follows your business rules. Offline, reproducible, independently verified, with safe manifest-based cleanup. CLI, terminal UI, web UI and MCP server. Java 21.
MIT ★ 1 -
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.
npm Apache-2.0 -
Human-like AI QA testing for any web app — Claude Code & Codex plugin, MCP server and CLI. Playwright drives a real browser like a person, finds UI, accessibility and permission bugs, and re-tests only what changed. Zero AI tokens per run.
MIT -
Open-source test automation for Android, iOS, web, smart TV (Android TV, Tizen, webOS) and Bluetooth (BLE) devices. Write tests as CSV/YAML, record them live, or let an AI agent build them over MCP. Self-healing locators: XPath, text, OCR, image.
pypi Apache-2.0 ★ 99 -
Local emulator for E2E testing: fake SMTP, Telegram, WhatsApp, SMS, push, Slack, Discord, Stripe & OAuth with a web timeline and MCP server for LLM agents.
MIT ★ 2 -
SceneScout — exploratory UI testing for AI coding agents. An MCP server that gives any agent (Claude Code, Cursor, VS Code Copilot, Codex, Gemini CLI and others) a structured view of a running web app, always-on oracles, a network-level write policy, memo
npm MIT -
AI-powered E2E testing for 10 platforms. 253 MCP tools. Zero config. Works with Claude, Cursor, Windsurf, Copilot. Test Flutter, React Native, iOS, Android, Web, Electron, Tauri, KMP, .NET MAUI — all from natural language.
MIT ★ 407 -
Let coding agents on different machines work together over an encrypted bridge: Claude Code, Codex, Cursor, Gemini. Backend ↔ mobile/web agents run test cycles: scenarios, test data, bug reports, fixes.
MIT ★ 2 -
Universal Test Automation MCP Server for web and desktop automation with self-healing capabilities
npm MIT -
KaDeep Studios CLI and releasegate: AI end-to-end testing from your terminal, CI/CD and coding agents (MCP). Run tests on web, mobile and desktop and get a go / no-go for every release.
Apache-2.0 ★ 1 -
MCP server for the Web UI Component Specification — behavioral specs, tests, and principles for web UI component libraries
MIT -
hal-web-mcpgithub.com/Halfax/hal-web-mcpupdated this year
Web search/fetch MCP server behind a real SSRF wall — DNS-rebinding defense, private-range blocking, 31 tests.
-
Wopee.io MCP server: connect Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf or any MCP client to Wopee.io, the AI testing agent for web apps. Crawl your app, generate test cases, run them in a real browser, fetch results and file GitHub issues from chat.
npm MIT ★ 4 -
MCP server for the Web UI Component Specification — behavioral specs, tests, and principles for web UI component libraries
pypi MIT License -
Free MCP server and agent skill that runs, diagnoses and fixes failing Playwright tests (TypeScript and pytest), and proves each fix by re-running it. Flaky verdicts, finds the commit that broke a test, blocks fixes that check less, posts CI fixes as PR suggestions, accessibility and Web Vitals audits. MIT, no account.
npm MIT ★ 5 -
Open-source self-improving QA agent for software teams. A test harness with memory. Write tests in natural language for web and mobile. agent-qa learns from every run, adapts to UI changes, and catches regressions before you ship.
npm NOASSERTION ★ 857 -
🔭 Your coding agent, turned into a QA tester for any web app. Finds what is broken and shows you the proof: pictures, replays, journey videos and test reports. Over MCP, with Claude Code, Cursor, VS Code, Codex, Gemini CLI and more.
npm MIT ★ 2 -
Deterministic, zero-hallucination agentic QA engine. Equips AI agents with cognitive heuristics and boundary fuzzing to autonomously test Web, Mobile, Desktop, and APIs.
npm MIT ★ 1 -
A power tool for web security testing — scanner, repeater, intruder, and AI agent in one Rust binary. No accounts, no telemetry, no cloud.
NOASSERTION ★ 1 -
Wissensgetriebener, lokaler Pentest-Workspace (CLI) für CTF, Bug Bounty & autorisierte Tests – geführte Recon, Findings/Loot/Reports, Web-Dashboard, lokale KI-Unterstützung & MCP-Server. KI analysiert, führt nie selbst aus.
MIT ★ 1 -
Authorization-gated penetration testing MCP server for AI agents - 80 tools (recon, vuln scanning, web app, exploit, CTF, reporting) with engagement-file scope enforcement. pipx install pentester-mcp
MIT ★ 2 -
Test web pages on emulated real phones, foldables, tablets and desktops: real browser engines, device frames, notches, safe areas, Telegram Mini Apps, layout audits. Claude Code drives it over MCP.
MIT -
Hosted MCP server and 12 marketing skills for Claude and Codex. Give your agent live web analytics, A/B tests, funnels, heatmaps and paid-ads attribution resolved to Stripe revenue.
MIT ★ 85 -
Automated web application penetration testing framework: OWASP Top 10 + advanced attacks, an autonomous AI agent (Ollama/Claude/OpenAI), SAST source-code analysis, and an MCP server, with professional CVSS-scored reports.
NOASSERTION ★ 8 -
A comprehensive Model Context Protocol (MCP) server that provides web performance auditing, accessibility testing, SEO analysis, security assessment, and Core Web Vitals monitoring using Google Lighthouse. Enables LLMs and AI agents to perform detailed we
npm MIT -
小智 AI MCP 桥接 - 多接入点管理/消息互发/工具自检/文件搜索天气系统命令代码执行，含Web管理面板 | Xiaozhi AI MCP Bridge with multi-endpoint, messaging, self-test and Web dashboard
npm MIT -
crawlbase-mcpgithub.com/crawlbase/crawlbase-mcpupdated this year
Crawlbase MCP Server connects AI agents and LLMs with real-time web data. It powers Claude, Cursor, and Windsurf integrations with battle-tested web scraping, JavaScript rendering, and anti-bot protection enabling structured, live data inside your AI workflows.
★ 60 -
ZippyServe is a zero-dependency local web server. It lets you test single-page apps quickly. It serves directories, zips, HTML, and Markdown. [DOI: 10.5281/zenodo.21613944]
GPL-3.0 ★ 1 -
Make any game joinable. Agent kit, MCP server and self-test for adding multiplayer to web games with Joinable.
MIT -
The definitive Spotify MCP server — full non-deprecated Web API coverage, paginated everything, podcast-first, tested end to end
npm MIT ★ 1 -
json-contracts-studiogithub.com/json-contracts/json-contracts-studioupdated this year
Local web Studio for testing natural-language-to-JSON workflows with JSON Contracts.
NOASSERTION ★ 1 -
Manage and simulate user interactions in modern web apps to improve testing accuracy and reliability with UserDispatch MCP.
MIT -
Local LLM does Claude's bulk work: reads logs and files, researches the web, writes test-gated code.
MIT ★ 2 -
@michelabboud/visual-forge-mcpgithub.com/michelabboud/visual-forge-mcpupdated this year
MCP server for AI image generation from markdown and HTML with multi-provider support, model testing, and automatic web optimization
npm SEE LICENSE IN LICENSE -
Local LLM does Claude's bulk work: reads logs and files, researches the web, writes test-gated code.
npm MIT -
debate-mcpgithub.com/grzesir/debate-mcpupdated this year
MCP server that stress-tests your decisions with adversarial AI debate. GPT vs Gemini, Skeptic vs Steelman, grounded in web search.
npm MIT -
Salesforce DevTools — CLI, VS Code extension, sf plugin, MCP server, and web dashboard for Salesforce DX deploy, test, org health, and release management. AI-optional, CI-ready.
Apache-2.0 ★ 1 -
Fable 5.1 Multi-Agent Architect & Invariant Verification Gate for Claude Code, Cursor & Web. Decouples task contracts from worker subagents with adversarial failure injection testing. BYOK (Claude 3.7, GPT-4o, DeepSeek, Ollama).
MIT ★ 1 -
debate-mcpgithub.com/grzesir/debate-mcpupdated this year
Stress-test your decisions with adversarial AI debate. MCP server for Claude Code. Skeptic vs Steelman, web-search grounded, confirmation bias attack.
MIT ★ 3 -
The agent-native web framework. Your coding agent builds on a live, running app, and every change is planned, tested and proven before it lands. Works with Claude Code, Codex, Cursor and any MCP client.
Apache-2.0 ★ 1 -
Disposable desktop MCP server for AI agents: private Linux GUI, Chromium, shell and read-only noVNC in Docker. Computer use and local web app testing without taking over your screen.
★ 2 -
agentic-research-engine-ossgithub.com/TheAiSingularity/agentic-research-engine-ossupdated this year
The best $0 research agent that runs on a laptop. Local Gemma 3 4B + SearXNG + trafilatura. CLI · TUI · Web GUI · MCP server · submittable Claude plugin. 264 tests, all mocked.
MIT ★ 2 -
repo-bridge-mcpgithub.com/zcrossoverz/repo-bridgeupdated this year
MCP server that turns ChatGPT Web into a real coding agent on your own repositories: read, search, edit, build, test, git, pull requests. OAuth 2.1. No OpenAI API key.
npm MIT -
- A Vibe Coded Project - Connect Claude Code to local LLMs through LM Studio APIs via MCP bridge. Multi-model support, hot reload, dynamic MCP discovery. Access filesystem, database, web, git, and more. Zero API costs, full privacy, test coverage. Inspired by infinitimeless/LMStudio-MCP.
MIT ★ 3 -
viewgraphgithub.com/sourjya/viewgraphupdated this year
ViewGraph is a developer super assistant that captures live web pages as structured, agent-ready UI context, combining layout, DOM-like structure, selectors, styles, spatial relationships, screenshots, and metadata to help coding agents generate tests, audit interfaces, compare changes, and build faster.
AGPL-3.0 ★ 7 -
repo-bridgegithub.com/zcrossoverz/repo-bridgeupdated this year
Turn ChatGPT Web into a real coding agent on your own repos - read, edit, build, test, git, PRs. MCP server with OAuth 2.1, driven by GPT-5.6 Sol on ChatGPT Plus/Pro. No OpenAI API key, no per-token API bill.
npm MIT ★ 4 -
RepoTunnel is a secure local AI workspace bridge that connects ChatGPT Web and MCP-compatible AI clients to approved local projects, files, terminals, Git, GitHub, browsers, editors, and desktop applications—so AI can inspect, edit, test, run, and manage real development work without constant copy-pasting.
MIT ★ 8 -
Claude-native, governed offensive-OSINT & external attack-surface platform for authorized red-team and bug-bounty. Multi-agent recon across web, identity, cloud, secrets & breach intel under deterministic scope/evidence/approval controls, with human-reviewed findings for hand-off to pen-testing. Not an exploitation framework.
NOASSERTION ★ 15