AI agents use set_layer_labeling 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 modifies layer properties (labeling configuration) which changes how the map renders and stores state. This is a Write operation rather than Read (retrieves data) or Execute (arbitrary code execution). It's reversible—labeling can be re-enabled or reconfigured.
From the tool's definition Tool performs 'Configure labeling for a vector layer' and allows toggling enabled state, which modifies layer properties and rendering behavior. This is a reversible configuration change to layer metadata.
Attacks that exploit this kind of access
Configure labeling for a vector layer. Set enabled=false to disable labels. 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_layer_labeling: 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_layer_labeling 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_layer_labeling 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_layer_labeling. 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_layer_labeling 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 →