AI agents use set_project_crs 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 project-level settings (the CRS/coordinate reference system) which is a write operation. It is reversible (can be changed back), so it does not qualify as Destructive. The severity is medium because incorrect CRS settings could cause spatial analysis errors or data misalignment, affecting downstream GIS operations, but the change itself can be undone.
From the tool's definition Tool name 'set_project_crs' and description 'Set the project coordinate reference system' indicate modification of project metadata/settings. This is a reversible configuration change that alters how spatial data is interpreted.
Attacks that exploit this kind of access
Set the project coordinate reference system (e.g. 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_project_crs: 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_project_crs 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_project_crs 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_project_crs. 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_project_crs 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 →