AI agents call cursor_get_model to retrieve information from Vscode without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only reads/retrieves the currently selected AI model configuration in Cursor. It has no side effects, cannot modify state, execute commands, or delete data. It is a pure information retrieval operation, fitting the Read category with low severity since the information exposed (model name) poses minimal security risk if disclosed.
From the tool's definition Tool name and description indicate a query operation: 'Get the currently configured AI model' — retrieves state information about the current model setting without modifying, deleting, or executing anything.
Attacks that exploit this kind of access
Get the currently configured AI model in Cursor. It is categorised as a Read tool in the Vscode MCP Server, which means it retrieves data without modifying state.
Register the Vscode MCP server in PolicyLayer and add a rule for cursor_get_model: 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 Vscode. Nothing to install.
cursor_get_model 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 cursor_get_model 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 cursor_get_model. 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.
cursor_get_model is provided by the Vscode MCP server (kloutdevs/vscode-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 →