browse_snapshot
Agent-native ACT view of the current page: interactive elements with stable @eN refs (for click/type) + a heading outline + challenge state. Token-efficient (no raw DOM). Re-snapshot after each navigation — refs are regenerated per page.
This record as markdown: /tools/com-wingmanprotocol-agent-gateway/browse-snapshot.md
What browse_snapshot does on Gateway
AI agents call browse_snapshot 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 |
|---|---|---|---|
browser_id | string | Yes | from browse_open |
Parameters from the server's own tool schema.
Why browse_snapshot is rated Low
This tool retrieves and presents information about the current page state (interactive elements, headings, challenge state) without modifying data, executing code, or triggering side effects. It is fundamentally a read/query operation that enables an agent to understand page context before taking action. The stable references (@eN refs) are for subsequent operations (click/type), not the tool's own purpose.
From the tool's definition Tool provides a view/snapshot of the current page state with interactive element references and heading outlines. The description emphasizes it is 'Agent-native ACT view' and 'token-efficient' read-only representation.
Attacks that exploit this kind of access
The rule that runs browse_snapshot 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_snapshot, this is the rule to start with:
browse_snapshot 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_snapshot call is checked against it from then on.
Questions about browse_snapshot
Agent-native ACT view of the current page: interactive elements with stable @eN refs (for click/type) + a heading outline + challenge state. Token-efficient (no raw DOM). Re-snapshot after each navigation — refs are regenerated per page. It is categorised as a Read tool in the Gateway MCP Server, which means it retrieves data without modifying state.
browse_snapshot accepts 1 parameter: 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_snapshot: 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_snapshot 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_snapshot 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_snapshot. 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_snapshot 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