AI agents use save_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.
The tool creates or modifies a style file for a layer, which is a reversible write operation. It does not execute arbitrary code, delete data, move money, or trigger external operations beyond saving styling metadata. The blast radius is moderate because it could overwrite existing styles, but the operation is reversible by restoring from backups or resaving with different styles.
From the tool's definition Tool name 'save_style_qml' and description 'Save a layer' indicate the tool persists styling data to a QML (QGIS Markup Language) file. This modifies the project state by writing style information.
Attacks that exploit this kind of access
Save 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 save_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.
save_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 save_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 save_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.
save_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 →