"npm" matching MCP servers:

A local-first MCP server for web search and documentation fetching, providing free DuckDuckGo search, URL-to-markdown conversion, and library docs from npm, PyPI, crates.io, Go, and GitHub with caching.

Desktop automation MCP server for any AI agent: control the screen, windows, mouse/keyboard, and Chrome (CDP) on your machine. Installable via npm @nuphus/nuphus-mcp.

Enables AI agents to perform Playwright-compatible browser automation with persistent profiles, Chrome extension support, proxy matching, humanized input, and npm/Docker deployment over stdio or Streamable HTTP.

Enables AI agents to perform browser automation through Playwright-compatible tools, CloakBrowser Chromium, persistent profiles, Docker or npm deployment, and stdio or Streamable HTTP transport.

It enables AI agents to control real Chromium browsers through Playwright-compatible tools for web research, automation, and testing, with stdio or Streamable HTTP transport and npm or Docker deployment.

Enables AI agents and compatible clients to automate real Chromium browsing through Playwright-compatible tools over stdio or Streamable HTTP, with persistent profiles, extensions, proxy matching, and Docker/npm deployment.

Enables AI agents to perform Playwright-powered Chromium browser automation, including web research, testing, persistent profiles, and humanized interactions, over stdio or Streamable HTTP with npm or Docker deployment.

Enables AI agents to automate web browsing through Playwright-compatible tools, with npm or Docker installation, stdio or Streamable HTTP transport, persistent profiles, proxy matching, extension loading, and humanized interactions.

Enables AI agents to automate Chromium browsing with Playwright-compatible tools for web research, testing, and routine tasks, including persistent profiles, extensions, proxy-aware regional QA, and humanized input over npm or Docker.

Enables AI agents to drive real browser automation through an unchanged Playwright MCP tool surface backed by CloakBrowser Chromium, with persistent profiles, proxy matching, humanized input, and npm, Docker, or Streamable HTTP deployment.

Enables AI agents to automate real Chromium browsing through Playwright-compatible tools, including humanized interactions, persistent profiles, proxy matching, and npm/Docker or stdio/Streamable HTTP deployment.

Enables AI agents to perform Playwright-compatible browser automation with persistent profiles, proxy routing, extension loading, and humanized mouse, keyboard, and scroll interactions over stdio, Streamable HTTP, npm, or Docker.

Enables AI agents to perform browser automation through Playwright-compatible tools on a specialized Chromium runtime, with npm/Docker deployment, persistent profiles, proxy matching, and stdio or Streamable HTTP transport.

Enables AI agents to run local multi-engine web searches, fetch pages through anti-bot fallback chains, and query site-specific sources such as GitHub, npm, PyPI, Docker Hub, and Twitter/X for structured results.

Enables AI agents to run Playwright-compatible browser automation against Chromium with persistent profiles, proxy matching, humanized interactions, and npm, Docker, stdio, or Streamable HTTP deployment.

A universal MCP aggregator toolkit that connects AI agents to multiple MCP servers through a single unified configuration. Features ready-made templates, cross-repo prompt workflows, and an npm package for zero-config installation.

Adds fdl-mcp-server — published on npm at https://www.npmjs.com/package/fdl-mcp-server Five tools any MCP client can call to analyze small business websites: * audit_website — deterministic 5-pillar scorecard (Performance, SEO, Mobile, Security, AEO) with a 0–100 score and specific findings * compare_websites — side-by-side scorecard of two sites with a winner * ai_visibility_check —

An MCP server that enables Claude to interact with Google NotebookLM via browser automation, allowing management of notebooks, adding sources, and querying information.

Enables stealth web browsing and search with Cloudflare Turnstile bypass, dynamic residential proxy rotation, and token-optimized markdown extraction.

Enables measuring DOM elements and capturing screenshots in a real local Chrome browser over the DevTools Protocol, with in-page login so httpOnly cookies apply and overlay-masking before capture. It removes common Chrome automation traps such as sandbox kills, WebSocket origin rejection, and Retina pixel scaling, with no npm or Python dependencies beyond the MCP SDK.