AI agents use area_m2 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 existing geospatial features by adding or updating field values. While reversible (fields can be deleted/modified afterward), it constitutes a Write operation as it creates or alters data structures. Severity is medium because the changes are contained to a single layer/feature set and reversible, but could affect large datasets if applied broadly.
From the tool's definition Tool description states 'populate a field from a QGIS expression, per feature, in-place' — this directly modifies feature data by adding and populating fields. The phrase 'in-place' confirms data modification without creating new objects.
Attacks that exploit this kind of access
Add (if missing) + populate a field from a QGIS expression, per feature, in-place. 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 area_m2: 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.
area_m2 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 area_m2 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 area_m2. 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.
area_m2 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 →