# input.send_actions

PREFERRED multi-step tool: run 1–10 predictable UI actions in one call (input.click_target, input.click_xy, input.type_text, input.send_keys, input.drag, input.scroll). Side effects: all actions execute on the remote desktop; fails fast before sending if any action is invalid. observe_after defaults true (verification observe: text+targets; set observe_image=true for JPEG). Do not batch across unpredictable waits (page loads, installers, modals) — single-step those. Prefer this over chaining solo click/type/keys tools.

Agent View of the PolicyLayer registry record for `input.send_actions`. HTML page: https://policylayer.com/tools/com-glasswarp-mcp-server/input.send-actions

## Facts

- Tool: `input.send_actions`
- Server: Glasswarp (`https://mcp.glasswarp.com/mcp`) — https://policylayer.com/tools/com-glasswarp-mcp-server.md
- Homepage: https://github.com/glasswarp/mcp-server
- Risk category: Execute (High risk)
- Registry record: grade F, identity unverified
- Server auth posture: open
- Server rate-limited: no
- Parameters: 4 (2 required)
- Recommended policy verdict: Rate-limited

## Parameters

| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `actions` | array | yes | Ordered actions (max 10); input.click_target needs target_id from latest screen.observe |
| `session_id` | string | yes | Active session id |
| `observe_after` | boolean | no | Default true. When true, return a verification observe in the same result |
| `observe_image` | boolean | no | Default false. When true with observe_after, include verification JPEG unless changed=false |

Parameters from the server's own tool schema.

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "input.send_actions",
    "arguments": {
      "actions": [],
      "session_id": "<session_id>"
    }
  }
}
```

## Why input.send_actions is rated High

This tool triggers external operations (UI automation on a remote Windows PC) whose effects depend entirely on the arguments provided. An AI agent could use this to launch applications, navigate to malicious sites, enter credentials into wrong systems, or trigger unintended desktop actions. While individual actions are reversible, the combination and sequence create unpredictable side effects on a real system.

From the tool's own definition: "Tool executes multiple UI actions on remote desktop: 'run 1–10 predictable UI actions in one call', 'all actions execute on the remote desktop'. Supports click_target, click_xy, type_text, send_keys, drag, scroll — all direct desktop manipulation operations."

Risk signals: High parameter count (16 properties)

## Use case

AI agents invoke input.send_actions to trigger actions in Glasswarp. 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.

## Recommended policy (PolicyLayer)

Verdict: **Rate-limited**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Glasswarp:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "input.send_actions": {
      "limits": [
        {
          "counter": "input.send_actions_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}
```

## Other tools on Glasswarp (15)

- `app.launch` — Execute — https://policylayer.com/tools/com-glasswarp-mcp-server/app.launch.md
- `input.click_target` — Execute — https://policylayer.com/tools/com-glasswarp-mcp-server/input.click-target.md
- `input.click_xy` — Execute — https://policylayer.com/tools/com-glasswarp-mcp-server/input.click-xy.md
- `input.drag` — Execute — https://policylayer.com/tools/com-glasswarp-mcp-server/input.drag.md
- `input.scroll` — Execute — https://policylayer.com/tools/com-glasswarp-mcp-server/input.scroll.md
- `input.send_keys` — Execute — https://policylayer.com/tools/com-glasswarp-mcp-server/input.send-keys.md
- `input.type_text` — Execute — https://policylayer.com/tools/com-glasswarp-mcp-server/input.type-text.md
- `session.end` — Execute — https://policylayer.com/tools/com-glasswarp-mcp-server/session.end.md
- `session.start` — Execute — https://policylayer.com/tools/com-glasswarp-mcp-server/session.start.md
- `demos.get` — Read — https://policylayer.com/tools/com-glasswarp-mcp-server/demos.get.md
- `demos.list` — Read — https://policylayer.com/tools/com-glasswarp-mcp-server/demos.list.md
- `rigs.list` — Read — https://policylayer.com/tools/com-glasswarp-mcp-server/rigs.list.md
- `screen.observe` — Read — https://policylayer.com/tools/com-glasswarp-mcp-server/screen.observe.md
- `session.live_view` — Read — https://policylayer.com/tools/com-glasswarp-mcp-server/session.live-view.md
- `session.status` — Read — https://policylayer.com/tools/com-glasswarp-mcp-server/session.status.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=com-glasswarp-mcp-server · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/com-glasswarp-mcp-server