browse_discover
Tier-0 front door for the current session page (or pass url): does the site offer an agent-native interface (llms.txt / OpenAPI / ai-plugin)? Prefer it over scraping.
This record as markdown: /tools/com-wingmanprotocol-agent-gateway/browse-discover.md
What browse_discover does on Gateway
AI agents call browse_discover 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 |
|---|---|---|---|
url | string | — | optional: probe this url instead of the current page |
browser_id | string | Yes | from browse_open |
Parameters from the server's own tool schema.
Why browse_discover is rated Low
browse_discover performs information retrieval only: it checks whether a given URL or current session page exposes agent-native interface metadata (llms.txt, OpenAPI, ai-plugin). This is a read operation with no side effects, no command execution, and no data modification. The low severity reflects that misuse would only result in querying public interface metadata, with minimal blast radius.
From the tool's definition Tool description states it 'does the site offer an agent-native interface' — purely a discovery/detection function that queries and retrieves information about a website's available interfaces. No data is modified, deleted, or executed.
Risk signalsAccepts URL/endpoint input (url)
Attacks that exploit this kind of access
The rule that runs browse_discover 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_discover, this is the rule to start with:
browse_discover 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_discover call is checked against it from then on.
Questions about browse_discover
Tier-0 front door for the current session page (or pass url): does the site offer an agent-native interface (llms.txt / OpenAPI / ai-plugin)? Prefer it over scraping. It is categorised as a Read tool in the Gateway MCP Server, which means it retrieves data without modifying state.
browse_discover accepts 2 parameters: url, browser_id. Required: 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_discover: 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_discover 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_discover 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_discover. 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_discover 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