inspect_viewport

THE RISK

Low Risk

Why inspect_viewport needs a policy

This tool retrieves and analyzes the current state of a UI viewport, returning descriptive information without side effects. It is a read-only operation that gathers data about the visual state of a Scenic application.

From the tool's definition Tool name 'inspect_viewport' and description 'UI ANALYSIS: Get a detailed text-based description of what' indicates retrieval of UI state information. No modification, deletion, code execution, or financial operations are performed.

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

POLICY

How to control inspect_viewport

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 inspect_viewport:

policy.json

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

inspect_viewport 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 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.

CAP 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_keys KEYBOARD INPUT: Send text input or special keystrokes to the Scenic application. Use for t 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.

All 10 Scenic MCP 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 inspect_viewport

What does the inspect_viewport tool do? +

UI ANALYSIS: Get a detailed text-based description of what\. It is categorised as a Read tool in the Scenic MCP MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on inspect_viewport? +

Register the Scenic MCP server in PolicyLayer and add a rule for inspect_viewport: 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 inspect_viewport? +

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

Can I rate-limit inspect_viewport? +

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

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

inspect_viewport 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 →