AI agents call get_bookmarks 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 queries and returns existing spatial bookmarks without modifying, creating, deleting, or executing any operations. It is purely a data retrieval function that returns bookmark metadata (name, group, and presumably spatial coordinates). This is a read-only operation with minimal risk, as it only accesses existing project data.
From the tool's definition Tool name is 'get_bookmarks' and description indicates it retrieves spatial bookmarks from the project ('Get spatial bookmarks from the project'). The verb 'Get' is a retrieval operation with no side effects.
Attacks that exploit this kind of access
Get spatial bookmarks from the project. Each bookmark has a name, group,. 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_bookmarks: 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_bookmarks 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_bookmarks 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_bookmarks. 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_bookmarks 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 →