AI agents call get_project_variables to retrieve information from QGIS MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries project configuration data without side effects. It falls squarely into the Read category. Severity is low because project variables in GIS contexts are typically non-sensitive configuration metadata (CRS definitions, layer paths, etc.) rather than secrets or critical data. An AI agent misusing this would have minimal blast radius.
From the tool's definition Tool name is 'get_project_variables' and description states it 'Get[s] all project-level variables (key-value pairs set in Project Properties)' — a pure retrieval operation with no modification, deletion, or execution of code.
Attacks that exploit this kind of access
Get all project-level variables (key-value pairs set in Project Properties). It is categorised as a Read tool in the QGIS MCP MCP Server, which means it retrieves data without modifying state.
Register the QGIS MCP server in PolicyLayer and add a rule for get_project_variables: 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.
get_project_variables is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_project_variables 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 get_project_variables. 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.
get_project_variables 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 →