browser_explore
A execute tool on the Looking Glass MCP server.
This record as markdown: /tools/io-github-sahib-sawhney-wh-looking-glass-mcp/browser-explore.md
What browser_explore does on Looking Glass
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.
| Parameter | Type | Required | Description |
|---|---|---|---|
maxDepth | number | — | Maximum link depth to follow (default: 3) |
maxPages | number | — | Maximum pages to crawl (default: 20) |
stayWithinPath | boolean | — | Only crawl within the current URL path (default: false) |
Parameters from the server's own tool schema.
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 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.
Attacks that exploit this kind of access
The rule that runs browser_explore safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Looking Glass, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For browser_explore, this is the rule to start with:
browser_explore stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Looking Glass, apply this rule, and every browser_explore call is checked against it from then on.
Questions about browser_explore
browser_explore is a execute tool on the Looking Glass MCP server. It is categorised as a Execute tool in the Looking Glass MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
browser_explore accepts 3 parameters: maxDepth, maxPages, stayWithinPath. The full parameter table on this page comes from the server's own tool schema.
Register the Looking Glass MCP server in PolicyLayer and add a rule for browser_explore: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Looking Glass. Nothing to install.
browser_explore is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the browser_explore rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for browser_explore. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
browser_explore is provided by the Looking Glass MCP server (looking-glass-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Looking Glass, and thousands of servers like it.
Across the catalogue