AI agents call cursor_list_commands 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 performs information retrieval only—it queries the IDE for a list of available commands. There are no side effects, no code execution, no data modification, and no destructive operations. It is purely introspective metadata access, making it a Read category tool with low severity.
From the tool's definition Tool name 'cursor_list_commands' and description 'List Cursor/VS Code commands available in the IDE' indicate a read-only operation that retrieves and enumerates available commands without executing them or modifying state.
Attacks that exploit this kind of access
List Cursor/VS Code commands available in the IDE. Use filter to narrow results. 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_list_commands: 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_list_commands 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_list_commands 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_list_commands. 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_list_commands 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 →