Return screenshot session metadata and an ASCII preview.
AI agents call get_screenshot_manifest to retrieve information from Screen MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays information about screenshot sessions without modifying, executing, or destructively operating on any data. While it enables screen capture viewing (which has privacy/surveillance implications), the tool itself performs only read operations. Severity is medium due to potential privacy risks from screenshot access rather than technical risk from the operation itself.
From the tool's definition Tool returns metadata and ASCII preview of captured screenshots - purely retrieval operations with no modification, execution, or deletion. Description uses 'Return' indicating read-only access.
Attacks that exploit this kind of access
Return screenshot session metadata and an ASCII preview. It is categorised as a Read tool in the Screen MCP MCP Server, which means it retrieves data without modifying state.
Register the Screen MCP server in PolicyLayer and add a rule for get_screenshot_manifest: 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 Screen MCP. Nothing to install.
get_screenshot_manifest 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_screenshot_manifest 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_screenshot_manifest. 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_screenshot_manifest is provided by the Screen MCP server (jeandelest/screen-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 →