browse_screenshot
Screenshot the current page; returns a base64 PNG ({screenshot_b64, bytes}).
This record as markdown: /tools/com-wingmanprotocol-agent-gateway/browse-screenshot.md
What browse_screenshot does on Gateway
AI agents call browse_screenshot 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 |
|---|---|---|---|
full_page | boolean | — | capture the full scrollable page |
browser_id | string | Yes | from browse_open |
Parameters from the server's own tool schema.
Why browse_screenshot is rated Low
Taking a screenshot is a passive read operation that queries the current state of a rendered page and returns image data. It has no capability to modify state, execute commands, delete data, or trigger external operations. The blast radius of misuse is minimal—an agent could see page contents it shouldn't, but cannot act on them through this tool alone.
From the tool's definition Tool name 'browse_screenshot' and description 'Screenshot the current page; returns a base64 PNG' indicate a retrieval operation with no side effects. The tool captures and returns visual data without modifying, deleting, or executing actions.
Attacks that exploit this kind of access
The rule that runs browse_screenshot 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_screenshot, this is the rule to start with:
browse_screenshot 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_screenshot call is checked against it from then on.
Questions about browse_screenshot
Screenshot the current page; returns a base64 PNG ({screenshot_b64, bytes}). It is categorised as a Read tool in the Gateway MCP Server, which means it retrieves data without modifying state.
browse_screenshot accepts 2 parameters: full_page, 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_screenshot: 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_screenshot 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_screenshot 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_screenshot. 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_screenshot 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