Commands come from the project's own docs or registry entry. Check them against the source before you run them.
Loading poll...
Browser Use is an open-source Python library for AI browser agents, and our entry covers its MCP route. The GitHub description also mentions Browser Use Cloud, with stealth browsers and a hosted agent API. The entry lists stdio and streamable HTTP transports and an install line of uvx browser-use. The licence is MIT and the maintainer is browser-use. We would suggest it to developers who want an agent to drive a real browser from a client such as Claude Code or Cursor, and who are comfortable running a Python tool. The star count of 119.6 thousand belongs to the parent repository, not to the MCP wrapper, so read it as a sign of project reach. The main limit is that browser agents are slow and can click the wrong thing, so give them a sandboxed profile. We have not run it, and the repository was last pushed on 30 October 2026.
SeleniumBase describes itself as the best API for web automation, testing and scraping, with a CDP Mode that launches a stealth browser to get past bot detection, and this entry is its MCP server, installed with uvx seleniumbase over stdio.
Skyvern is described as automating browser-based workflows with AI, and this entry is its hosted MCP endpoint at api.skyvern.com over streamable HTTP, added with claude mcp add --transport http skyvern https://api.skyvern.com/mcp/.
This browser server comes from the ByteDance UI-TARS-desktop repository and is published as @agent-infra/mcp-server-browser, installed with npx -y @agent-infra/mcp-server-browser.
Scrapling is a Python web scraping framework from D4Vinci, described on GitHub as handling everything from a single request to a full-scale crawl, and this entry is its MCP server.
Claude Flow is published on npm as claude-flow, and its repository now sits at ruvnet/ruflo, which the GitHub description calls the original agent harness for deploying multi-agent swarms and coordinating autonomous workflows.
Context7 is an MCP server from Upstash that serves up-to-date library documentation to coding agents, so the model reads current docs instead of guessing from training data.
tldraw is an infinite-canvas SDK for React, and this entry is a hosted MCP endpoint run on a tldraw Workers address, reachable over streamable HTTP and SSE.