AI agents call get_canvas_screenshot to retrieve information from Arcmap without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Taking a screenshot of a canvas is a read-only operation that retrieves visual state without modifying data, executing code, or causing destructive changes. The impact is minimal—it only captures what is already displayed. Confidence is reduced slightly due to empty description, but the semantic meaning of the name is clear and unambiguous in the GIS context.
From the tool's definition Tool name 'get_canvas_screenshot' indicates retrieval of a visual representation of the ArcMap canvas. No description provided, but the name and server context (viewing the canvas) suggest image capture with no side effects.
Attacks that exploit this kind of access
get_canvas_screenshot. It is categorised as a Read tool in the Arcmap MCP Server, which means it retrieves data without modifying state.
Register the Arcmap MCP server in PolicyLayer and add a rule for get_canvas_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 Arcmap. Nothing to install.
get_canvas_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 get_canvas_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 get_canvas_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.
get_canvas_screenshot is provided by the Arcmap MCP server (pedralcg/arcmap-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 →