MCP Servers
4 open source tools compared. Sorted by stars. Scroll down for our analysis.
| Tool | Stars | Velocity | Score |
|---|---|---|---|
 mcp-chrome Chrome MCP server that lets AI assistants control and read your browser | 11.2k | — | 67 |
 docusaurus This website is built using [Docusaurus](https://docusaurus.io/), a modern static website generator. | 8.8k | — | 53 |
 firecrawl-mcp-server Official Firecrawl MCP server for web scraping, search, and browser automation | 6.1k | — | 69 |
 mcp-playwright MCP server for browser automation and testing via Playwright | 5.4k | — | 63 |
Stay ahead of the category
New tools and momentum shifts, every Wednesday.
Our Analysis
Connects your Chrome browser to AI assistants via MCP. Claude can take screenshots, fill forms, manage bookmarks, and search across your open tabs using a local vector database. Twenty-plus tools, all running locally. No data leaves your machine. Install the Chrome extension and the bridge package, configure your MCP client, and your AI can see what you see. Setup takes about 10 minutes. Maintained by hangwin (community). Free, MIT licensed, no API keys or subscriptions. If you want your AI assistant to actually interact with your browser, this is the one to install.
This is the documentation site for the AWS Labs MCP project, built with Docusaurus. It is not a connector to anything. It is a reference site for the other MCP servers in the suite. Completely free. No underlying service costs. AWS Labs maintains it alongside the rest of their MCP servers. Not something you install as an MCP server. It is documentation. The catch: this gets indexed as a "tool" because it lives in the monorepo, but it is just a docs site. No AI integration here.
Gives your AI assistant web scraping superpowers via Firecrawl's API. Scrape pages to clean markdown, run searches, automate browser interactions, and map entire sites. All through MCP tool calls. One npx command to install, but you need a Firecrawl API key. The service uses credit-based pricing, so costs scale with usage. Built-in credit warnings help prevent surprise bills. You can also point it at a self-hosted Firecrawl instance to avoid API costs entirely. Official Firecrawl team maintains this. Worth installing if web research is part of your AI workflow.