AI agents use apply_style_qml 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 tool modifies layer properties (styling) but does not delete data or execute arbitrary code. Style application is reversible—another style can be applied over it. While it affects the map's appearance, the underlying data and features remain intact. This is a Write operation because it updates/modifies layer metadata and rendering configuration.
From the tool's definition The tool applies a QML style file to a layer, which modifies the layer's appearance and styling properties. The description states it 'Apply[s] a QGIS QML style file to a layer,' indicating it changes the layer's visual representation.
Attacks that exploit this kind of access
Apply a QGIS QML style file to a layer. 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 apply_style_qml: 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.
apply_style_qml 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 apply_style_qml 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 apply_style_qml. 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.
apply_style_qml 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 →