FRENES

Browser automation · MCP server

Hwatu: MCP server, setup and security

Hwatu is an open-source MCP server published on GitHub that lets an AI agent verify webpages using headless WebKit DOM evaluation screenshots and pixel comparisons. Its repository has 117 stars and its last commit is from October 17, 2026 and it is licensed under MIT.

Score
66/100
Adoption (stars) 21/40
Maintenance 30/30
Framework (licence, registry, official) 15/30
Actively maintainedSystem access

What Hwatu does

According to its repository: “Verification browser for coding agents: headless WebKit, DOM eval, screenshots, pixel-diff.”

The Model Context Protocol (MCP) is a standard plug between an AI agent and an outside service: once the server is connected, its tools show up in the agent, which decides when to call them. Hwatu is listed under Browser automation, a category of 109 servers in the directory, where it ranks #54 by stars.

Topics declared by the repository: browser, rust, tiling-window-manager, wayland, webkit, linux.

Installing and connecting Hwatu

Distribution modes declared in the official MCP registry:

  • MCPB bundle (one-click install in Claude Desktop)

It works with any MCP-compatible client (Claude Desktop, Claude Code, Cursor, VS Code, Codex and most recent agents). You add one entry to the client's MCP configuration: server name, start command or URL, environment variables. Project language: Rust.

Security: what to check

Connecting an MCP server means installing software that talks straight to your agent: it runs with your rights and the model trusts its tool descriptions. The risk therefore depends on what it can touch and how far its code can be trusted.

Points found for Hwatu:

  • System access: the Browser automation category gives the agent control over files, a terminal, code or a browser. A booby-trapped instruction in content the agent reads (prompt injection) can then turn into an action.

Good practice: grant only the rights needed (least privilege), require human approval for irreversible actions, and run the AI agent security check.

Project activity and maintenance

Created on July 18, 2026, the hongnoul/hwatu repository has 117 stars and 12 forks, with 1 open issues. It has more stars than 69% of the servers in the directory. It received changes this month. Version published in the registry: 0.6.0 (July 25, 2026).

Stars measure attention, not quality: a recent, heavily promoted project can collect them fast, while a useful but niche server will have few.

Browser useBrowser use : 119K119KScrapling MCP ServerScrapling MCP Server : 89.4K89.4KChrome DevTools MCPChrome DevTools MCP : 54.1K54.1KMCP server browserMCP server browser : 39.4K39.4KPlaywright MCPPlaywright MCP : 38.6K38.6KBrowserBrowser : 36.9K36.9KSkyvernSkyvern : 23.3K23.3KSeleniumBase MCPSeleniumBase MCP : 13.1K13.1KHwatuHwatu : 117117
GitHub stars of the most followed servers in the category (log scale); Hwatu in orange. Checked October 25, 2026.

Verdict

Hwatu is a reasonable choice; check the points below before connecting it.

Strengths

  • Active project: recent commit
  • Listed in the official MCP registry
  • Permissive licence (MIT)

Avoid if…

  • You cannot isolate the agent (sandbox, container)

Frequently asked questions

How do I install Hwatu?

Hwatu is distributed as MCPB bundle (one-click install in Claude Desktop). Add it to your client's MCP configuration (Claude Desktop, Cursor, VS Code…) following the README of hongnoul/hwatu.

Is Hwatu free?

The code is published under the MIT licence and can be used free of charge.

Is Hwatu safe?

Points to watch: system access. Give it minimum rights and approve sensitive actions.

Is it an official server?

Nothing says so: it is a project published by hongnoul on GitHub. Check who maintains it before giving it access.

What are the alternatives to Hwatu?

In the same category: Firecrawl MCP Server, Browser use, MCP server browser, and Playwright MCP. Firecrawl MCP Server and Browser use score higher on our grid.

Related articles

Neutrality. No affiliate links. No vendor pays to be reviewed, rated or ranked. Reviews are directed by François Chollet, neutral and factual, and every data point is dated and sourced. How we score