browse_extract
Deterministic structured extraction from the current page: {name: css_selector} -> {name: text}. More robust + cheaper than re-snapshotting and parsing.
This record as markdown: /tools/com-wingmanprotocol-agent-gateway/browse-extract.md
What browse_extract does on Gateway
AI agents call browse_extract to retrieve information from Gateway 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 |
|---|---|---|---|
fields | object | Yes | {name: css_selector} |
browser_id | string | Yes | from browse_open |
Parameters from the server's own tool schema.
Why browse_extract is rated Low
This tool only queries and extracts data from a webpage using CSS selectors—a read-only operation with no side effects. It does not create, modify, delete, or execute code. The deterministic nature and comparison to parsing reinforces that this is purely data retrieval.
From the tool's definition Tool performs 'structured extraction from the current page' using CSS selectors to retrieve text. The description explicitly contrasts it as 'more robust + cheaper than re-snapshotting and parsing,' indicating it retrieves and transforms existing data without…
Attacks that exploit this kind of access
The rule that runs browse_extract safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Gateway, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For browse_extract, this is the rule to start with:
browse_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 Gateway, apply this rule, and every browse_extract call is checked against it from then on.
Questions about browse_extract
Deterministic structured extraction from the current page: {name: css_selector} -> {name: text}. More robust + cheaper than re-snapshotting and parsing. It is categorised as a Read tool in the Gateway MCP Server, which means it retrieves data without modifying state.
browse_extract accepts 2 parameters: fields, browser_id. Required: fields, browser_id. The full parameter table on this page comes from the server's own tool schema.
Register the Gateway MCP server in PolicyLayer and add a rule for browse_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 Gateway. Nothing to install.
browse_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 browse_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 browse_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.
browse_extract is provided by the Gateway MCP server (https://wingmanprotocol.com/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Gateway, and thousands of servers like it.
This server
Across the catalogue