AI agents call browser_capture_profile_mobile to retrieve information from Mcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool reads/captures visual and diagnostic information from a profile page in a mobile browser session. It does not modify data, execute arbitrary code, or perform destructive actions. The 'close the session' part is a cleanup action inherent to the capture workflow, not a destructive operation on user data.
From the tool's definition capture screenshots/styles/diagnostics, and close the session
Attacks that exploit this kind of access
Open the profile page in a mobile browser profile, capture screenshots/styles/diagnostics, and close the session. It is categorised as a Read tool in the Mcp MCP Server, which means it retrieves data without modifying state.
Register the MCP server in PolicyLayer and add a rule for browser_capture_profile_mobile: 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 Mcp. Nothing to install.
browser_capture_profile_mobile 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_capture_profile_mobile 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_capture_profile_mobile. 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_capture_profile_mobile is provided by the MCP server (victormyschik/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →