send_mouse

THE RISK

High Risk

Why send_mouse needs a policy

This tool triggers external operations by sending mouse events to a running TUI application. The effects depend on what the target application does in response to mouse clicks/movements, making it an Execute-category action. Misuse could trigger arbitrary application-level actions depending on what's running in the terminal session.

From the tool's definition Send a mouse event to the TUI app (if the app has mouse support enabled)

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

POLICY

How to control send_mouse

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 send_mouse:

policy.json

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

send_mouse 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.

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.

RATE-LIMIT 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_text Type a string of characters into the TUI app. The text is sent exactly as provided - MCP J Read cursor Get the current cursor position in the terminal.

All 13 Tui tools →

Execute tools on other servers

Android Forensics ADB MCP Server adb_shell_command EMBA-MCP run_emba_scan Frida Game Hacking MCP remove_breakpoint Procmon request_elevation

Go deeper

High-risk tools in Tui → Every high-risk tool this server exposes, in one view.
All high-risk MCP tools → Every high-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Agent sandbox → Bounding what an agent can execute and where the boundary should sit.
Least privilege for MCP → Granting agents the minimum tool surface the task needs.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about send_mouse

What does the send_mouse tool do? +

Send a mouse event to the TUI app (if the app has mouse support enabled). It is categorised as a Execute tool in the Tui MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on send_mouse? +

Register the Tui MCP server in PolicyLayer and add a rule for send_mouse: 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 send_mouse? +

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

Can I rate-limit send_mouse? +

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

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

send_mouse 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 →