Get the full OCR text of a specific capture by its ID.
AI agents call get_capture 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 previously captured screen text by ID. It performs a lookup and returns data without modifying, creating, deleting, or executing any operations. It is a straightforward read operation. Severity is low because access to screen capture history poses a privacy/confidentiality risk but does not enable further actions, financial harm, or data destruction.
From the tool's definition Tool description: 'Get the full OCR text of a specific capture by its ID.' The verb 'get' and the passive operation of retrieving stored OCR text indicates a read-only query with no side effects.
Attacks that exploit this kind of access
Get the full OCR text of a specific capture by its ID. 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_capture: 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_capture 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_capture 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_capture. 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_capture 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 →