# evaluate

A execute tool on the Playwright MCP Server MCP server.

Agent View of the PolicyLayer registry record for `evaluate`. HTML page: https://policylayer.com/tools/alexrwilliam-playwright-mcp-server/evaluate

## Facts

- Tool: `evaluate`
- Server: Playwright MCP Server (`alexrwilliam/playwright-mcp-server`) — https://policylayer.com/tools/alexrwilliam-playwright-mcp-server.md
- Homepage: https://github.com/alexrwilliam/playwright-mcp-server
- Risk category: Execute (High risk)
- Registry record: grade F, identity unverified
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Rate-limited

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "evaluate",
    "arguments": {}
  }
}
```

## Why evaluate is rated High

In Playwright, 'evaluate' is the primary method for running arbitrary JavaScript code within a browser page. This can execute any code, access DOM, exfiltrate data, or perform destructive actions. Even without a description, the server context (Playwright automation) and the well-known Playwright API make this classification highly reliable. Empty description lowers confidence slightly.

From the tool's own definition: "Tool name 'evaluate' on a Playwright browser automation server; description is empty but in Playwright context 'evaluate' refers to page.evaluate() which executes arbitrary JavaScript in the browser context."

## Use case

AI agents invoke evaluate to trigger actions in Playwright MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.

## Recommended policy (PolicyLayer)

Verdict: **Rate-limited**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Playwright MCP Server:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "evaluate": {
      "limits": [
        {
          "counter": "evaluate_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}
```

## Other tools on Playwright MCP Server (66)

- `clear_cookies` — Destructive — https://policylayer.com/tools/alexrwilliam-playwright-mcp-server/clear-cookies.md
- `clear_network_logs` — Destructive — https://policylayer.com/tools/alexrwilliam-playwright-mcp-server/clear-network-logs.md
- `clear_storage` — Destructive — https://policylayer.com/tools/alexrwilliam-playwright-mcp-server/clear-storage.md
- `apply_antidetect_preset` — Execute — https://policylayer.com/tools/alexrwilliam-playwright-mcp-server/apply-antidetect-preset.md
- `check_checkbox` — Execute — https://policylayer.com/tools/alexrwilliam-playwright-mcp-server/check-checkbox.md
- `clear_text` — Execute — https://policylayer.com/tools/alexrwilliam-playwright-mcp-server/clear-text.md
- `click` — Execute — https://policylayer.com/tools/alexrwilliam-playwright-mcp-server/click.md
- `fill` — Execute — https://policylayer.com/tools/alexrwilliam-playwright-mcp-server/fill.md
- `go_back` — Execute — https://policylayer.com/tools/alexrwilliam-playwright-mcp-server/go-back.md
- `go_forward` — Execute — https://policylayer.com/tools/alexrwilliam-playwright-mcp-server/go-forward.md
- `hover` — Execute — https://policylayer.com/tools/alexrwilliam-playwright-mcp-server/hover.md
- `intercept_route` — Execute — https://policylayer.com/tools/alexrwilliam-playwright-mcp-server/intercept-route.md
- `navigate` — Execute — https://policylayer.com/tools/alexrwilliam-playwright-mcp-server/navigate.md
- `press_key` — Execute — https://policylayer.com/tools/alexrwilliam-playwright-mcp-server/press-key.md
- `recreate_context` — Execute — https://policylayer.com/tools/alexrwilliam-playwright-mcp-server/recreate-context.md
- `reload` — Execute — https://policylayer.com/tools/alexrwilliam-playwright-mcp-server/reload.md
- `restart_browser` — Execute — https://policylayer.com/tools/alexrwilliam-playwright-mcp-server/restart-browser.md
- `scroll` — Execute — https://policylayer.com/tools/alexrwilliam-playwright-mcp-server/scroll.md
- `select_option` — Execute — https://policylayer.com/tools/alexrwilliam-playwright-mcp-server/select-option.md
- `set_extra_headers` — Execute — https://policylayer.com/tools/alexrwilliam-playwright-mcp-server/set-extra-headers.md
- `set_user_agent` — Execute — https://policylayer.com/tools/alexrwilliam-playwright-mcp-server/set-user-agent.md
- `set_viewport_size` — Execute — https://policylayer.com/tools/alexrwilliam-playwright-mcp-server/set-viewport-size.md
- `switch_page` — Execute — https://policylayer.com/tools/alexrwilliam-playwright-mcp-server/switch-page.md
- `switch_to_latest_page` — Execute — https://policylayer.com/tools/alexrwilliam-playwright-mcp-server/switch-to-latest-page.md
- `type_text` — Execute — https://policylayer.com/tools/alexrwilliam-playwright-mcp-server/type-text.md
- `uncheck_checkbox` — Execute — https://policylayer.com/tools/alexrwilliam-playwright-mcp-server/uncheck-checkbox.md
- `unroute_all` — Execute — https://policylayer.com/tools/alexrwilliam-playwright-mcp-server/unroute-all.md
- `upload_file` — Execute — https://policylayer.com/tools/alexrwilliam-playwright-mcp-server/upload-file.md
- `wait_for_element` — Execute — https://policylayer.com/tools/alexrwilliam-playwright-mcp-server/wait-for-element.md
- `wait_for_load_state` — Execute — https://policylayer.com/tools/alexrwilliam-playwright-mcp-server/wait-for-load-state.md
- …and 36 more: https://policylayer.com/tools/alexrwilliam-playwright-mcp-server.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=alexrwilliam-playwright-mcp-server · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/alexrwilliam-playwright-mcp-server