// MCP TOOL REFERENCE

send_keys

ServerScenic MCP
CategoryExecute

WHAT IT DOES

What send_keys does on Scenic MCP

AI agents invoke send_keys to trigger actions in Scenic MCP. 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.

THE RISK

High Risk

Why send_keys needs a policy

This tool sends keyboard input including special keys and modifier combinations to an application. While it may appear to be just 'writing' input, sending keystrokes like ctrl+c, cmd+s, or arbitrary key combinations triggers application-level operations whose effects depend entirely on the arguments — potentially saving files, copying data, closing windows, or triggering other application behaviors.

From the tool's definition Send text input or special keystrokes to the Scenic application... Supports text, special keys (enter, escape, tab), and modifier combinations (ctrl+c, cmd+s)

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

POLICY

How to control send_keys

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

policy.json

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

send_keys 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 Scenic MCP — 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 Scenic MCP tools

Execute click_element SEMANTIC CLICK: Click an element by its semantic ID. This is the high-level equivalent of Execute connect_scenic CONNECTION SETUP: Establish the connection to the ScenicMCP GenServer running inside our S Execute hover_element SEMANTIC HOVER: Move the mouse to hover over an element by its semantic ID. Finds the elem Execute send_mouse_click MOUSE INTERACTION: Click at specific screen coordinates to interact with buttons, links, a Execute send_mouse_move CURSOR MOVEMENT: Move the mouse cursor to specific coordinates. Useful for hover effects, Read find_clickable_elements SEMANTIC DISCOVERY: Find all clickable elements in the viewport with their semantic IDs, t Read get_scenic_status CONNECTION STATUS: Check if we are connected to a Scenic app and fetch details. Read inspect_viewport UI ANALYSIS: Get a detailed text-based description of what\

All 10 Scenic MCP 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 Scenic MCP → 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_keys

What does the send_keys tool do? +

KEYBOARD INPUT: Send text input or special keystrokes to the Scenic application. Use for typing text, navigation shortcuts, testing keyboard interactions. Supports text, special keys (enter, escape, tab), and modifier combinations (ctrl+c, cmd+s). It is categorised as a Execute tool in the Scenic MCP 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_keys? +

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

What risk level is send_keys? +

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

Can I rate-limit send_keys? +

Yes. Add a rate_limit block to the send_keys 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_keys completely? +

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

send_keys is provided by the Scenic MCP server (scenic-contrib/scenic_mcp_experimental). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Scenic MCP tool call.

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

CHECK YOUR STACK →

Free to start. No card required.

10 Scenic MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.