# performance_start_trace

Starts a performance trace recording on the selected page. This can be used to look for performance problems and insights to improve the performance of the page. It will also report Core Web Vital (CWV) scores for the page.

Agent View of the PolicyLayer registry record for `performance_start_trace`. HTML page: https://policylayer.com/tools/anirbandz-chrome-mcp-devtool/performance-start-trace

## Facts

- Tool: `performance_start_trace`
- Server: Chrome DevTools MCP (`anirbandz/chrome_mcp_devtool`) — https://policylayer.com/tools/anirbandz-chrome-mcp-devtool.md
- Homepage: https://github.com/Anirbandz/Chrome_MCP_DEVTOOL
- 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": "performance_start_trace",
    "arguments": {}
  }
}
```

## Why performance_start_trace is rated High

This tool triggers an active operation in the browser (starting a trace recording session) that affects the runtime state of the page. It initiates an ongoing process with side effects on the browser's profiling subsystem. It's not purely read-only (it starts a recording process) but doesn't write/modify user data, making Execute the most appropriate category.

From the tool's own definition: "Starts a performance trace recording on the selected page"

## Use case

AI agents invoke performance_start_trace to trigger actions in Chrome DevTools MCP. 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 Chrome DevTools MCP:

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

## Other tools on Chrome DevTools MCP (25)

- `click` — Execute — https://policylayer.com/tools/anirbandz-chrome-mcp-devtool/click.md
- `drag` — Execute — https://policylayer.com/tools/anirbandz-chrome-mcp-devtool/drag.md
- `emulate` — Execute — https://policylayer.com/tools/anirbandz-chrome-mcp-devtool/emulate.md
- `evaluate_script` — Execute — https://policylayer.com/tools/anirbandz-chrome-mcp-devtool/evaluate-script.md
- `handle_dialog` — Execute — https://policylayer.com/tools/anirbandz-chrome-mcp-devtool/handle-dialog.md
- `hover` — Execute — https://policylayer.com/tools/anirbandz-chrome-mcp-devtool/hover.md
- `navigate_page` — Execute — https://policylayer.com/tools/anirbandz-chrome-mcp-devtool/navigate-page.md
- `new_page` — Execute — https://policylayer.com/tools/anirbandz-chrome-mcp-devtool/new-page.md
- `performance_stop_trace` — Execute — https://policylayer.com/tools/anirbandz-chrome-mcp-devtool/performance-stop-trace.md
- `press_key` — Execute — https://policylayer.com/tools/anirbandz-chrome-mcp-devtool/press-key.md
- `resize_page` — Execute — https://policylayer.com/tools/anirbandz-chrome-mcp-devtool/resize-page.md
- `wait_for` — Execute — https://policylayer.com/tools/anirbandz-chrome-mcp-devtool/wait-for.md
- `get_console_message` — Read — https://policylayer.com/tools/anirbandz-chrome-mcp-devtool/get-console-message.md
- `get_network_request` — Read — https://policylayer.com/tools/anirbandz-chrome-mcp-devtool/get-network-request.md
- `list_console_messages` — Read — https://policylayer.com/tools/anirbandz-chrome-mcp-devtool/list-console-messages.md
- `list_network_requests` — Read — https://policylayer.com/tools/anirbandz-chrome-mcp-devtool/list-network-requests.md
- `list_pages` — Read — https://policylayer.com/tools/anirbandz-chrome-mcp-devtool/list-pages.md
- `performance_analyze_insight` — Read — https://policylayer.com/tools/anirbandz-chrome-mcp-devtool/performance-analyze-insight.md
- `take_screenshot` — Read — https://policylayer.com/tools/anirbandz-chrome-mcp-devtool/take-screenshot.md
- `take_snapshot` — Read — https://policylayer.com/tools/anirbandz-chrome-mcp-devtool/take-snapshot.md
- `close_page` — Write — https://policylayer.com/tools/anirbandz-chrome-mcp-devtool/close-page.md
- `fill` — Write — https://policylayer.com/tools/anirbandz-chrome-mcp-devtool/fill.md
- `fill_form` — Write — https://policylayer.com/tools/anirbandz-chrome-mcp-devtool/fill-form.md
- `select_page` — Write — https://policylayer.com/tools/anirbandz-chrome-mcp-devtool/select-page.md
- `upload_file` — Write — https://policylayer.com/tools/anirbandz-chrome-mcp-devtool/upload-file.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=anirbandz-chrome-mcp-devtool · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/anirbandz-chrome-mcp-devtool