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.
-
real-browser-mcp-serveractive
MCP Server for Real Browser - Patchright Blocker.
npm ISC -
wraith-mcpgithub.com/Koreahwan/wraith-mcpupdated this year
AI-native stealth browser MCP server — Browser Use + Patchright
MIT -
AI Agent-first JS 逆向 MCP Server：有头 Chrome 调试、断点、网络/WebSocket 分析、Patchright 反检测，可选 CloakBrowser。
npm Apache-2.0 ★ 3,080 -
hermes-cloud-studiogithub.com/caiolea0/hermes-cloud-studioupdated this year
Autonomous B2B prospecting and LinkedIn 24/7 automation. Tauri desktop + FastAPI + Patchright stealth + 6 AI skills. PC orchestrates dashboard, VM (GCP) runs scrapers and LinkedIn campaigns with 14-day warm-up, anti-detection patches, residential SOCKS5 reverse tunnel, and compliance gates.
★ 1 -
web-scrapper-stdiogithub.com/JustAzul/web-scrapper-stdioupdated this year
MCP web scraper with persistent browser pool, Cloudflare bypass (Patchright + Turnstile solving), and dual transport (stdio + HTTP). Extracts Markdown/text/HTML from web pages for AI integration.
MIT -
Web research for AI agents. Fetch any page with anti-bot bypass plus web search. $0 forever. No scrapling dependency: hound uses primp + patchright directly. Graceful degradation when browser deps are unavailable (HTTP-only mode on Termux/Android). Token-optimized tool definitions, polished cross-platform CLI, brick-proof self-update with hound doctor + rollback.
pypi MIT License -
MCP server for searching and reading Kleinanzeigen listings
MIT ★ 1 -
Stealth browser automation for AI agents — real Chrome, N parallel persistent logged-in sessions.
pypi Apache-2.0 -
Async Python client and Model Context Protocol (MCP) server for Perplexity AI web interface with streaming and multi-model support
MIT -
Perplexity AI search, reasoning, research, and compute - MCP server, dashboard, and multi-IDE auto-config for VS Code.
npm MIT ★ 79 -
MCP & ETL for biggest czech web job servers - jobs.cz, prace.cz, bazos.cz, jenprace.cz, profesia.cz, volnamista.cz
-
Unofficial MCP server for Courses U (Super U / Hyper U grocery drive): search and compare products through your own browser session, in Docker. Cart, lists and orders to come.
MIT ★ 1 -
linkedin-mcp-pro-maxgithub.com/mdnaimul22/linkedin-mcp-pro-maxupdated this year
Personal LinkedIn MCP Agent Who Can Extract Update Profile, search apply jobs, writing CV or Cover Letter , and Optimize AI Recommendation profile.
MIT ★ 1 -
Stealth browser automation for AI agents — unattended, headless, N parallel persistent logged-in Chromes. One MCP server + CLI, credential vault with TOTP/IMAP 2FA, vision clicking, prompt-injection scanning. Self-hosted, real Chrome. 2,027 tests.
Apache-2.0 ★ 9 -
Self-hosted Google search scraper for Python. Scrape Google SERP results with a real Chrome browser and your own residential proxy. Self-hosted SERP API alternative with JSON output, an HTTP API and an MCP server for AI agents.
pypi MIT ★ 122