web-eval-agent vs Selenium MCP (mcp-selenium)
A side-by-side comparison of two Browser Automation servers — tools, transport, auth, maintenance, and copy-paste config for each.
| 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 | Selenium MCP (mcp-selenium) Selenium WebDriver MCP server — cross-browser automation for Chrome, Firefox, Edge, and Safari. Verified stdio (local) No auth JavaScript | |
|---|---|---|
| Category | Browser Automation | Browser Automation |
| Language | Python | JavaScript |
| Transport | stdio (local) | stdio (local) |
| Auth | API key | None |
| GitHub stars | 1.2k | 900 |
| Last commit | 4 months ago | 3 months ago |
| Verified | ||
| Actively maintained | ||
| Install | curl -LSf https://operative.sh/install.sh -o install.sh && bash install.sh && rm install.sh | npx -y @angiejones/mcp-selenium |
| Repo | Open | Open |
Verdict
Pick web-eval-agent if you want the official, vendor-maintained server, and you prefer the more popular, battle-tested option.
Pick Selenium MCP (mcp-selenium) if you want zero-setup with no API key, and you need the broadest set of tools.
Add web-eval-agent
curl -LSf https://operative.sh/install.sh -o install.sh && bash install.sh && rm install.shPaste 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.
Add Selenium MCP (mcp-selenium)
npx -y @angiejones/mcp-seleniumPaste into ~/Library/Application Support/Claude/claude_desktop_config.json
{
"mcpServers": {
"selenium-mcp-mcp-selenium": {
"command": "npx",
"args": [
"-y",
"@angiejones/mcp-selenium"
]
}
}
}FAQ
web-eval-agent or Selenium MCP (mcp-selenium) — which is better?
Pick web-eval-agent if you want the official, vendor-maintained server, and you prefer the more popular, battle-tested option. Pick Selenium MCP (mcp-selenium) if you want zero-setup with no API key, and you need the broadest set of tools.
Can I use both web-eval-agent and Selenium MCP (mcp-selenium)?
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 web-eval-agent and Selenium MCP (mcp-selenium) work with Claude, Cursor and Windsurf?
Both do. Copy the per-client config below into Claude Desktop, Cursor, or Windsurf.