Get a screenshot of a Kasm session.
AI agents call get_session_screenshot to retrieve information from Kasm MCP Server v2 without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves session state (a screenshot) without side effects. However, severity is elevated to 'medium' rather than 'low' because screenshots can reveal sensitive information displayed on the desktop (passwords, private data, PII), creating risk if an agent captures sessions belonging to other users or containing confidential content.
From the tool's definition Tool name 'get_session_screenshot' and description 'Get a screenshot of a Kasm session' indicate retrieval of visual data from an active session without modification or deletion.
Attacks that exploit this kind of access
Get a screenshot of a Kasm session. It is categorised as a Read tool in the Kasm MCP Server v2 MCP Server, which means it retrieves data without modifying state.
Register the Kasm MCP Server v2 MCP server in PolicyLayer and add a rule for get_session_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 Kasm MCP Server v2. Nothing to install.
get_session_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 get_session_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 get_session_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.
get_session_screenshot is provided by the Kasm MCP Server v2 MCP server (roguedev-ai/kasm-mcp-server-v2). 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 →