AI agents call get_canvas_screenshot to retrieve information from QGIS MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool captures the current state of the map canvas for viewing/analysis purposes. It performs no side effects, creates no modifications, executes no external operations, and causes no data loss. It is a pure read operation that retrieves display output. The emphasis on 'no re-render' further confirms it is passive observation rather than active computation or change.
From the tool's definition Tool name 'get_canvas_screenshot' and description 'Grab a fast screenshot of the current map canvas widget (no re-render)' indicate retrieval of visual state data without modification or execution.
Attacks that exploit this kind of access
Grab a fast screenshot of the current map canvas widget (no re-render). It is categorised as a Read tool in the QGIS MCP MCP Server, which means it retrieves data without modifying state.
Register the QGIS 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 QGIS MCP. 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 QGIS MCP server (nkarasiak/qgis-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 →