Browser MCP vs web-eval-agent

A side-by-side comparison of two Browser Automation servers — tools, transport, auth, maintenance, and copy-paste config for each.

	Browser MCP Automate your existing browser with AI using your real profile, logged-in sessions, and stealth fingerprint. Unverified stdio (local) No auth Stale TypeScript	web-eval-agent Autonomous browser agent that evaluates and debugs your web app end-to-end from your IDE. Unverified stdio (local) API key Python
Category	Browser Automation	Browser Automation
Language	TypeScript	Python
Transport	stdio (local)	stdio (local)
Auth	None	API key
GitHub stars	6.7k	1.2k
Last commit	1 year ago	5 months ago
Verified
Actively maintained
Install	`npx @browsermcp/mcp@latest`	`curl -LSf https://operative.sh/install.sh -o install.sh && bash install.sh && rm install.sh`
Repo	Open	Open

Verdict

Pick Browser MCP if you prefer the more popular, battle-tested option, and you want zero-setup with no API key.

Pick web-eval-agent if you want the official, vendor-maintained server.

Add Browser MCP

Install / run

npx @browsermcp/mcp@latest

Paste into ~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "browser-mcp": {
      "command": "npx",
      "args": [
        "@browsermcp/mcp@latest"
      ]
    }
  }
}

Add web-eval-agent

Install / run

curl -LSf https://operative.sh/install.sh -o install.sh && bash install.sh && rm install.sh

Paste into ~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "web-eval-agent": {
      "command": "uvx",
      "args": [
        "--refresh-package",
        "webEvalAgent",
        "--from",
        "git+https://github.com/Operative-Sh/web-eval-agent.git",
        "webEvalAgent"
      ],
      "env": {
        "OPERATIVE_API_KEY": "<YOUR_KEY>"
      }
    }
  }
}

Requires `uv` (the Python package runner). Install it from https://docs.astral.sh/uv/ if `uvx` is not found.

FAQ

Browser MCP or web-eval-agent — which is better?

Pick Browser MCP if you prefer the more popular, battle-tested option, and you want zero-setup with no API key. Pick web-eval-agent if you want the official, vendor-maintained server.

Can I use both Browser MCP and web-eval-agent?

Yes — MCP clients let you enable multiple servers at once. Add both configs to your client's mcpServers and use whichever tool fits the task.

Do Browser MCP and web-eval-agent work with Claude, Cursor and Windsurf?

Both do. Copy the per-client config below into Claude Desktop, Cursor, or Windsurf.

View Browser MCP →View web-eval-agent →More comparisons →