cursor_send_message · Vscode MCP: Risk & Policy

WHAT IT DOES

What cursor_send_message does on Vscode

AI agents invoke cursor_send_message 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_send_message needs a policy

Sending a message to Cursor chat triggers an AI agent that can execute arbitrary operations including file modifications, shell commands, and code execution. The blast radius is high because the downstream AI can perform destructive or high-impact actions based on the message content.

From the tool's definition 'send a message (starts a new conversation)' in Cursor chat, which is an AI coding assistant capable of executing code, running commands, and modifying files

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

cursor_send_message Rate-limited

cursor_send_message 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_send_message": {
      "limits": [
        {
          "counter": "cursor_send_message_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_send_message

What does the cursor_send_message tool do? +

Open the Cursor chat and send a message (starts a new conversation). 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_send_message? +

Register the Vscode MCP server in PolicyLayer and add a rule for cursor_send_message: 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_send_message? +

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

Can I rate-limit cursor_send_message? +

Yes. Add a rate_limit block to the cursor_send_message 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_send_message completely? +

Set action: deny in the PolicyLayer policy for cursor_send_message. 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_send_message? +

cursor_send_message 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.