Save a screenshot of the current desktop.
AI agents call pix4d_screenshot to retrieve information from PIX4Dmatic MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool captures visual state of the desktop without modifying, executing code, or causing irreversible changes. It is purely observational, analogous to a GET request that retrieves data. Severity is low because screenshots reveal only what is already visible on screen and do not expose sensitive operations.
From the tool's definition Tool name 'pix4d_screenshot' and description 'Save a screenshot of the current desktop' indicate a data retrieval operation with no side effects.
Attacks that exploit this kind of access
Save a screenshot of the current desktop. It is categorised as a Read tool in the PIX4Dmatic MCP MCP Server, which means it retrieves data without modifying state.
Register the PIX4Dmatic MCP server in PolicyLayer and add a rule for pix4d_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 PIX4Dmatic MCP. Nothing to install.
pix4d_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 pix4d_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 pix4d_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.
pix4d_screenshot is provided by the PIX4Dmatic MCP server (jangjo123/pix4d-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 →