cursor_run_command · Vscode MCP: Risk & Policy

WHAT IT DOES

What cursor_run_command does on Vscode

AI agents invoke cursor_run_command to trigger actions in Vscode. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why cursor_run_command needs a policy

This tool allows execution of arbitrary VS Code/Cursor commands by ID, which can trigger a wide range of effects depending on the command executed. While it is scoped to VS Code/Cursor commands rather than shell execution, it still represents the Execute category as it runs code or triggers external operations whose effects fundamentally depend on the arguments (command ID) provided.

From the tool's definition Tool name and description: 'Execute any VS Code / Cursor command by its ID' explicitly states the capability to execute arbitrary commands.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

cursor_run_command Rate-limited

cursor_run_command stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "cursor_run_command": {
      "limits": [
        {
          "counter": "cursor_run_command_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Vscode, so you can run agents against it safely.

FAQ

Questions about cursor_run_command

What does the cursor_run_command tool do? +

Execute any VS Code / Cursor command by its ID. Use cursor_list_commands to discover IDs. It is categorised as a Execute tool in the Vscode MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on cursor_run_command? +

Register the Vscode MCP server in PolicyLayer and add a rule for cursor_run_command: 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.

What risk level is cursor_run_command? +

cursor_run_command is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit cursor_run_command? +

Yes. Add a rate_limit block to the cursor_run_command 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.

How do I block cursor_run_command completely? +

Set action: deny in the PolicyLayer policy for cursor_run_command. 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.

What MCP server provides cursor_run_command? +

cursor_run_command 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.