MCP Pointer vs web-eval-agent
A side-by-side comparison of two Browser Automation servers — tools, transport, auth, maintenance, and copy-paste config for each.
| MCP Pointer Point at browser DOM elements with Option+Click and feed them as context to agentic coding tools via MCP. 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 | 582 | 1.2k |
| Last commit | 7 months ago | 4 months ago |
| Verified | ||
| Actively maintained | ||
| Install | npx -y @mcp-pointer/server config claude | curl -LSf https://operative.sh/install.sh -o install.sh && bash install.sh && rm install.sh |
| Repo | Open | Open |
Verdict
Pick MCP Pointer if you want zero-setup with no API key.
Pick web-eval-agent if you want the official, vendor-maintained server, and you prefer the more popular, battle-tested option.
Add MCP Pointer
npx -y @mcp-pointer/server config claudePaste into ~/Library/Application Support/Claude/claude_desktop_config.json
{
"mcpServers": {
"mcp-pointer": {
"command": "npx",
"args": [
"-y",
"@mcp-pointer/server@latest",
"start"
],
"env": {
"MCP_POINTER_PORT": "7007"
}
}
}
}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.
FAQ
MCP Pointer or web-eval-agent — which is better?
Pick MCP Pointer if you want zero-setup with no API key. Pick web-eval-agent if you want the official, vendor-maintained server, and you prefer the more popular, battle-tested option.
Can I use both MCP Pointer 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 MCP Pointer and web-eval-agent work with Claude, Cursor and Windsurf?
Both do. Copy the per-client config below into Claude Desktop, Cursor, or Windsurf.