AI agents call get_message_log 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 message log entries from QGIS without side effects. It is a read-only operation that returns diagnostic or informational data. The filtering capability ('Filter by level') does not change the underlying data, only the view of it. This poses minimal security risk as it only accesses already-logged information within the application.
From the tool's definition Tool name 'get_message_log' and description 'Get QGIS message log entries' indicate retrieval of existing log data with filtering capability. No modification, deletion, or execution of external operations is performed.
Attacks that exploit this kind of access
Get QGIS message log entries. Filter by level (. 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_message_log: 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_message_log 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_message_log 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_message_log. 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_message_log 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 →