browser-use MCP
Browser Use is an open-source Python library for AI browser agents, and our entry covers its MCP route.
- MCP server
- Official
browser-use · 119,597 stars
MCP server
MCP server with a hosted endpoint. Transports: streamable-http. Maintained in Skyvern-AI/skyvern.
Checked 2026-10-31
claude mcp add --transport http skyvern https://api.skyvern.com/mcp/gemini mcp add --transport http skyvern https://api.skyvern.com/mcp/Hosted endpoint: https://api.skyvern.com/mcp/
Commands come from the project's own docs or registry entry. Check them against the source before you run them.
Loading poll...
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/. The licence is AGPL 3.0, a strong copyleft licence that matters if you self-host and modify it. The parent repository shows 23.3 thousand stars. We would suggest it to teams who want an agent to complete multi-step web tasks such as forms and portals that have no API, using a service that handles the browser. The main limits are that the hosted endpoint is a paid cloud service with an account, that automation of third-party sites can break their terms, and that we did not review its pricing or success rates. The repository was pushed on 31 October 2026. We have not used the service.
Browser Use is an open-source Python library for AI browser agents, and our entry covers its MCP route.
browser-use · 119,597 stars
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.
seleniumbase · 13,208 stars
The Apify MCP server, per its repository, lets agents extract data from social media, search engines, maps, e-commerce sites and other websites using thousands of ready-made tools called Actors.
apify · 13,969 stars
The Firecrawl MCP server is the official one from Firecrawl, which its repository calls the context API for AI agents: search, scrape and interact with the web, plus parse, crawl, map, an agent mode and monitoring.
firecrawl · 7,729 stars
Checked 2026-10-31
Checked 2026-10-31
Checked 2026-10-31
Checked 2026-10-31
Tried it with one of these? Vote below: works for me, or not.
Run this command: claude mcp add --transport http skyvern https://api.skyvern.com/mcp/. The install box on this page has the command for each agent it works with.
It is published under the AGPL 3.0 licence.
It is maintained by Skyvern-AI. The code is at github.com/Skyvern-AI/skyvern.
It runs over streamable-http.
Loading poll...
Loading reviews…
Only members can review this page. Sign in
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.
D4Vinci · 90,477 stars
Netdata is an observability platform, and this entry is its hosted MCP endpoint at app.netdata.cloud, reached over streamable HTTP.
netdata · 81,227 stars
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.
ruvnet · 80,298 stars
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.
upstash · 63,974 stars
MCP server published on npm as chrome-devtools-mcp. Transports: stdio. Maintained in ChromeDevTools/chrome-devtools-mcp.
ChromeDevTools · 54,503 stars
The all-in-one WordPress community stack
Also ours: wbcomdesigns.comvapvarun.combrndle.com