No installation required — works with any MCP-compatible client that supports SSE transport.
No installation required — works with any MCP-compatible client that supports SSE transport.
Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.
Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.
| Tool | What it does |
|---|---|
| web-scrape | Scrape websites with CSS selectors (SSRF hardened) |
| search-web | Web search via Tavily/Serper/DuckDuckGo |
| web-search | AI-synthesized web search answers |
| extract-page | Clean text/markdown from any URL |
| extract-metadata | OG tags, headers, word count from URLs |
| extract-pdf | Text and tables from PDFs |
| screenshot-capture | Page screenshots with metadata |
| browser-task | Headless browser automation via Playwright |
| html-to-markdown | Convert HTML to clean Markdown |
| rss-parse | RSS/Atom feed parser |
| news-search | Latest news articles on any topic |
| ocr-extract | Text from images via AI vision |
{
"mcpServers": {
"arch-tools": {
"command": "npx",
"args": ["-y", "@deesmo/arch-tools-mcp"],
"env": {
"ARCH_API_KEY": "arch_your_key_here"
}
}
}
}Configuration as documented by the project. Restart the client after saving.
| Variable | Description | Required |
|---|---|---|
| ARCH_API_KEY | Credential the server authenticates with. | Yes |
Use Microsoft’s Playwright MCP server to navigate pages, inspect accessibility snapshots, fill forms and capture browser screenshots.
The original Chromium automation reference server — simple, screenshot-driven browser control.
Give your coding agent the full DevTools toolbox: traces, network, console, heap snapshots and Lighthouse.
Puppeteer-powered browser control that drives pages from the accessibility tree instead of pixels.
Enables AI-powered applications to monitor and interact with browser data via a Chrome extension and MCP.
Automates browsers and APIs, enabling Large Language Models (LLMs) to interact with web pages for tasks like screenshot capture and JavaScript