AI agents use set_active_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.
The tool changes application state (which layer is active) rather than performing destructive operations or executing arbitrary code. It's a reversible modification of UI state—switching the active layer back is trivial. While it may enable downstream editing operations, the tool itself only sets focus/state, making it Write rather than Execute.
From the tool's definition Tool description states 'Set the active layer in the QGIS layer panel by layer ID.' This modifies the active state of a UI element, changing which layer is focused for editing or interaction, but does not modify or delete layer data itself.
Attacks that exploit this kind of access
Set the active layer in the QGIS layer panel by layer ID. 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 set_active_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.
set_active_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 set_active_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 set_active_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.
set_active_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 →