AI agents call take_screenshot to retrieve information from Pymdu without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Taking a screenshot captures existing visual information from the user's screen without causing side effects, modifications, or triggering external actions. This is a passive read operation that retrieves image data. While it has privacy implications in a broader security context, within the MCP tool classification framework it performs pure data retrieval.
From the tool's definition Tool name 'take_screenshot' and description 'Take a screenshot of the user's screen and return it as an image' indicate data retrieval with no modification or execution of external operations.
Attacks that exploit this kind of access
Take a screenshot of the user's screen and return it as an image. Use. It is categorised as a Read tool in the Pymdu MCP Server, which means it retrieves data without modifying state.
Register the Pymdu MCP server in PolicyLayer and add a rule for take_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 Pymdu. Nothing to install.
take_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 take_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 take_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.
take_screenshot is provided by the Pymdu MCP server (rupeelab17/mcp_pymdu). 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 →