# browser_explore

A execute tool on the Looking Glass MCP server.

Agent View of the PolicyLayer registry record for `browser_explore`. HTML page: https://policylayer.com/tools/io-github-sahib-sawhney-wh-looking-glass-mcp/browser-explore

## Facts

- Tool: `browser_explore`
- Server: Looking Glass (`looking-glass-mcp`) — https://policylayer.com/tools/io-github-sahib-sawhney-wh-looking-glass-mcp.md
- Install: `npx -y looking-glass-mcp`
- Homepage: https://github.com/Sahib-Sawhney-WH/LookingGlass
- Risk category: Execute (High risk)
- Registry record: grade F, identity unverified
- Server rate-limited: no
- Parameters: 3
- Recommended policy verdict: Rate-limited

## Parameters

| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `maxDepth` | number | no | Maximum link depth to follow (default: 3) |
| `maxPages` | number | no | Maximum pages to crawl (default: 20) |
| `stayWithinPath` | boolean | no | Only crawl within the current URL path (default: false) |

Parameters from the server's own tool schema.

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

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

## Why browser_explore is rated High

The description is empty, so classification is based on context. The server is an AI-native browser automation platform. A tool named 'browser_explore' likely navigates or interacts with web pages, constituting browser execution actions. Given sibling tools like browser_click, browser_close, and browser_analyze_page, this tool likely performs active browser navigation/exploration.

From the tool's own definition: "Tool name 'browser_explore' on a server described as 'AI-native browser for agents' with 72 tools including browser actions like click, close, and console interaction."

## Use case

AI agents invoke browser_explore to trigger actions in Looking Glass. 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 Looking Glass:

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

## Other tools on Looking Glass (70)

- `browser_clean_slate` — Destructive — https://policylayer.com/tools/io-github-sahib-sawhney-wh-looking-glass-mcp/browser-clean-slate.md
- `browser_clear_history` — Destructive — https://policylayer.com/tools/io-github-sahib-sawhney-wh-looking-glass-mcp/browser-clear-history.md
- `browser_clear_mocks` — Destructive — https://policylayer.com/tools/io-github-sahib-sawhney-wh-looking-glass-mcp/browser-clear-mocks.md
- `browser_clear_storage` — Destructive — https://policylayer.com/tools/io-github-sahib-sawhney-wh-looking-glass-mcp/browser-clear-storage.md
- `browser_close` — Destructive — https://policylayer.com/tools/io-github-sahib-sawhney-wh-looking-glass-mcp/browser-close.md
- `session_end` — Destructive — https://policylayer.com/tools/io-github-sahib-sawhney-wh-looking-glass-mcp/session-end.md
- `test_chaos_clear` — Destructive — https://policylayer.com/tools/io-github-sahib-sawhney-wh-looking-glass-mcp/test-chaos-clear.md
- `vault_delete` — Destructive — https://policylayer.com/tools/io-github-sahib-sawhney-wh-looking-glass-mcp/vault-delete.md
- `browser_click` — Execute — https://policylayer.com/tools/io-github-sahib-sawhney-wh-looking-glass-mcp/browser-click.md
- `browser_drag` — Execute — https://policylayer.com/tools/io-github-sahib-sawhney-wh-looking-glass-mcp/browser-drag.md
- `browser_evaluate` — Execute — https://policylayer.com/tools/io-github-sahib-sawhney-wh-looking-glass-mcp/browser-evaluate.md
- `browser_fill_and_submit` — Execute — https://policylayer.com/tools/io-github-sahib-sawhney-wh-looking-glass-mcp/browser-fill-and-submit.md
- `browser_go` — Execute — https://policylayer.com/tools/io-github-sahib-sawhney-wh-looking-glass-mcp/browser-go.md
- `browser_go_back` — Execute — https://policylayer.com/tools/io-github-sahib-sawhney-wh-looking-glass-mcp/browser-go-back.md
- `browser_go_forward` — Execute — https://policylayer.com/tools/io-github-sahib-sawhney-wh-looking-glass-mcp/browser-go-forward.md
- `browser_hover` — Execute — https://policylayer.com/tools/io-github-sahib-sawhney-wh-looking-glass-mcp/browser-hover.md
- `browser_login` — Execute — https://policylayer.com/tools/io-github-sahib-sawhney-wh-looking-glass-mcp/browser-login.md
- `browser_mock_route` — Execute — https://policylayer.com/tools/io-github-sahib-sawhney-wh-looking-glass-mcp/browser-mock-route.md
- `browser_navigate` — Execute — https://policylayer.com/tools/io-github-sahib-sawhney-wh-looking-glass-mcp/browser-navigate.md
- `browser_performance_audit` — Execute — https://policylayer.com/tools/io-github-sahib-sawhney-wh-looking-glass-mcp/browser-performance-audit.md
- `browser_press_key` — Execute — https://policylayer.com/tools/io-github-sahib-sawhney-wh-looking-glass-mcp/browser-press-key.md
- `browser_recover` — Execute — https://policylayer.com/tools/io-github-sahib-sawhney-wh-looking-glass-mcp/browser-recover.md
- `browser_resolve_element` — Execute — https://policylayer.com/tools/io-github-sahib-sawhney-wh-looking-glass-mcp/browser-resolve-element.md
- `browser_scroll` — Execute — https://policylayer.com/tools/io-github-sahib-sawhney-wh-looking-glass-mcp/browser-scroll.md
- `browser_select_option` — Execute — https://policylayer.com/tools/io-github-sahib-sawhney-wh-looking-glass-mcp/browser-select-option.md
- `browser_smart_click` — Execute — https://policylayer.com/tools/io-github-sahib-sawhney-wh-looking-glass-mcp/browser-smart-click.md
- `browser_tab_new` — Execute — https://policylayer.com/tools/io-github-sahib-sawhney-wh-looking-glass-mcp/browser-tab-new.md
- `browser_tab_select` — Execute — https://policylayer.com/tools/io-github-sahib-sawhney-wh-looking-glass-mcp/browser-tab-select.md
- `browser_type` — Execute — https://policylayer.com/tools/io-github-sahib-sawhney-wh-looking-glass-mcp/browser-type.md
- `browser_wait_for` — Execute — https://policylayer.com/tools/io-github-sahib-sawhney-wh-looking-glass-mcp/browser-wait-for.md
- …and 40 more: https://policylayer.com/tools/io-github-sahib-sawhney-wh-looking-glass-mcp.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=io-github-sahib-sawhney-wh-looking-glass-mcp · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/io-github-sahib-sawhney-wh-looking-glass-mcp