Render the current canvas headlessly to an image and return it inline (png default, or svg). Frame and size it with bbox {x,y,w,h}, scale (0-4], and maxDim (100-8000, a longest-edge pixel cap). The renderer sidecar makes this work even with no browser tab open in the room.
AI agents call screenshot to retrieve information from Excalidraw MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The screenshot tool retrieves and renders visual data from the canvas without creating side effects, modifying state, or executing code. It is a pure read operation that returns image data. The low severity reflects minimal blast radius—an AI agent misusing this tool could only extract visual information about the canvas, with no ability to alter, delete, or execute operations.
From the tool's definition Tool description states it 'Render[s] the current canvas headlessly to an image and return[s] it inline', with parameters for framing and scaling. No modification, deletion, or execution of external operations occurs.
Attacks that exploit this kind of access
Render the current canvas headlessly to an image and return it inline (png default, or svg). Frame and size it with bbox {x,y,w,h}, scale (0-4], and maxDim (100-8000, a longest-edge pixel cap). The renderer sidecar makes this work even with no browser tab open in the room. It is categorised as a Read tool in the Excalidraw MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Excalidraw MCP Server MCP server in PolicyLayer and add a rule for 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 Excalidraw MCP Server. Nothing to install.
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 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 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.
screenshot is provided by the Excalidraw MCP Server MCP server (val4evr/excalidraw-zephy). 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 →