AI agents use create_memory_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 tool creates a new in-memory vector layer, which is a reversible write operation. While it modifies the GIS project state by adding a new layer, the operation is not destructive (layers can be removed) and does not execute arbitrary code or delete data. The severity is medium because misuse could corrupt a GIS project's layer structure, but the effects are recoverable.
From the tool's definition Tool name is 'create_memory_layer' and description states 'Create a new in-memory vector layer' with geometry type options. The verb 'Create' indicates data creation.
Attacks that exploit this kind of access
Create a new in-memory vector layer. geometry_type: Point, LineString, Polygon,. 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 create_memory_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.
create_memory_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 create_memory_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 create_memory_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.
create_memory_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 →