Intake notes: listed with facts from the source repo; not yet vetted. A verdict waits on a real hands-on audit (install, run, audit what it injects). Health is checked automatically; the summary is the author’s own description.
browserbase-mcp
• Not yet vettedAllow LLMs to control a browser with Browserbase and Stagehand
In the intake queue. Listed with facts only; no verdict until a human runs it.
by browserbase MCP server Browser automation
Quiet for 3 months failing liveness · checked Oct 19, 2026
Commit activity · last 52 weeks
Stars3.4k
LanguageTypeScript
LicenseApache-2.0
Open issues52
Pricingfree
ListedJul 12, 2026
Facts pulled from the source repo and refreshed nightly. Stars are a data point, not our ranking. We don't order by popularity.
Runs in
| Harness | Support | Notes |
|---|---|---|
| Any MCP client | untested | — |
Support levels reflect what we actually ran, not what the README claims. untested means exactly that.
What a vet will check
- Whether it can act or write when told not to (read-only and scope enforcement)
- What it injects per session: token cost and the size of the tool surface
- Where your data goes: any call that leaves your machine, disclosed or not
No verdict is published until a human installs it, runs it, and audits what it injects. How vetting works →
More in Browser automation
playwright-mcp MCP server “The rare tool that's safe by default. Filesystem access is restricted to your workspace roots, and navigation to file:// URLs is blocked unless you explicitly pass --allow-unrestricted-file-access. That's the opposite of the usual "wide open until you lock it down." No telemetry, and the only dependencies are Microsoft's own playwright packages. Two honest caveats, both about what the tool is rather than a flaw. It drives a real browser, so the agent can reach any site it navigates to, and the --allowed-origins and --blocked-origins flags say plainly in their own help text that they are not a security boundary. And by default it persists a browser profile to a temp dir (cookies, logins); pass --isolated to keep the session in memory only. Treat it like handing your agent a real browser with access to your project files, because that's what it is.”
apify-mcp MCP server The Apify MCP server enables your AI agents to extract data from social media, search engines, maps, e-commerce sites, or any other website using thousands of ready-made scrapers…
fetch-mcp MCP server A flexible HTTP fetching Model Context Protocol server.
firecrawl-mcp MCP server Official Firecrawl MCP server. Adds web scraping and search to Claude, Cursor, and other LLM clients.