AI agents use duplicate_layer to create or update resources in QGIS MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your QGIS MCP environment.
This operation creates a new layer reversibly—the duplicate can be deleted, and the original remains unaffected. It does not execute arbitrary code, delete data irreversibly, or cause financial impact. The action is a standard Write operation within the GIS project context with minimal blast radius.
From the tool's definition Tool name 'duplicate_layer' and description 'Duplicate a layer (including its style) under a new name' indicate creation of a new layer resource through copying an existing one.
Attacks that exploit this kind of access
Duplicate a layer (including its style) under a new name. It is categorised as a Write tool in the QGIS MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the QGIS MCP server in PolicyLayer and add a rule for duplicate_layer: 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.
duplicate_layer is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the duplicate_layer 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 duplicate_layer. 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.
duplicate_layer 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 →