cursor

THE RISK

Low Risk

Why cursor needs a policy

This tool merely retrieves the current cursor position, which is informational data. It performs no writes, deletions, code execution, or external operations. The blast radius is negligible—knowing cursor position cannot be misused to cause harm.

From the tool's definition Tool name 'cursor' and description 'Get the current cursor position in the terminal' indicate a read-only query operation that retrieves state without modification or side effects.

Documented attack patterns abuse exactly the kind of access cursor gives an agent:

POLICY

How to control cursor

PolicyLayer is an MCP gateway — it sits between your AI agents and Tui, and nothing reaches the server without passing your rules. This is the rule we recommend for cursor:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "cursor": {}
  }
}

cursor is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

Create a free account and register Tui — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

CAP THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Tui tools

Destructive kill Terminate a TUI session and its underlying process. Execute launch Launch a TUI application in a managed pseudo-terminal. Returns a session ID for subsequent Execute wait_for_idle Wait until the terminal buffer stops changing. Useful after sending keys to wait for the a Execute wait_for_text Wait until a regex pattern appears in the terminal buffer. Useful for waiting for prompts, Execute resize Resize the terminal dimensions of a session. The TUI app will receive a SIGWINCH signal. Execute send_keys Send keystrokes to the TUI app. Use this for special keys and shortcuts, not for typing te Execute send_mouse Send a mouse event to the TUI app (if the app has mouse support enabled). Execute send_text Type a string of characters into the TUI app. The text is sent exactly as provided - MCP J

All 13 Tui tools →

Read tools on other servers

M-Team MCP Server get_torrent_detail YouTube MCP Server search_channel Android Forensics ADB MCP Server parse_browser_history 0xarchive web3_challenge

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Data exfiltration → How read access becomes an exfiltration channel when chained with untrusted content.
MCP token cost → What connecting this server costs in context-window tokens on every request.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about cursor

What does the cursor tool do? +

Get the current cursor position in the terminal. It is categorised as a Read tool in the Tui MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on cursor? +

Register the Tui MCP server in PolicyLayer and add a rule for cursor: 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 Tui. Nothing to install.

What risk level is cursor? +

cursor is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit cursor? +

Yes. Add a rate_limit block to the cursor 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 completely? +

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

cursor is provided by the Tui MCP server (nvms/tui-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Tui tool call.

Start from Tui, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →