Return the most recent screen captures with a preview of the text.
AI agents call get_recent_captures to retrieve information from Screen Memory without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves historical screen capture data and text previews. It performs a query operation against stored screen memory without creating, modifying, deleting, or executing anything. The blast radius of misuse is limited to information disclosure of what was previously displayed on the user's screen, which the tool is explicitly designed to surface.
From the tool's definition Tool name is 'get_recent_captures' and description states it will 'Return the most recent screen captures' — a retrieval operation with no modification or side effects.
Attacks that exploit this kind of access
Return the most recent screen captures with a preview of the text. It is categorised as a Read tool in the Screen Memory MCP Server, which means it retrieves data without modifying state.
Register the Screen Memory MCP server in PolicyLayer and add a rule for get_recent_captures: 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 Memory. Nothing to install.
get_recent_captures 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_recent_captures 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_recent_captures. 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_recent_captures is provided by the Screen Memory MCP server (yonglim2392/screen-memory-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 →