browser_extract
A read tool on the Looking Glass MCP server.
This record as markdown: /tools/io-github-sahib-sawhney-wh-looking-glass-mcp/browser-extract.md
What browser_extract does on Looking Glass
AI agents call browser_extract to retrieve information from Looking Glass without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
hint | string | — | Hint to narrow extraction region (e.g. "product listings") |
limit | number | — | Max items to extract (default: 50) |
fields | object | Yes | Schema: field name → type |
Parameters from the server's own tool schema.
Why browser_extract is rated Low
Given the server's purpose as an 'AI-native browser for agents' and the name 'browser_extract' alongside semantic extraction capabilities mentioned in the server description, this tool likely extracts or retrieves data from the current page state. Without an explicit description, it appears to be a read-only operation similar to page analysis.
From the tool's definition Tool name 'browser_extract' combined with server description mentioning 'semantic extraction' and sibling tools like 'browser_analyze_page' suggests data retrieval.
Attacks that exploit this kind of access
The rule that runs browser_extract 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_extract, this is the rule to start with:
browser_extract is read-only, so it stays allowed. 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_extract call is checked against it from then on.
Questions about browser_extract
browser_extract is a read tool on the Looking Glass MCP server. It is categorised as a Read tool in the Looking Glass MCP Server, which means it retrieves data without modifying state.
browser_extract accepts 3 parameters: hint, limit, fields. Required: fields. 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_extract: 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_extract is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the browser_extract 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_extract. 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_extract 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.
This server
Across the catalogue