# get_screenshot

A read tool on the UI Analyzer MCP Server MCP server.

Agent View of the PolicyLayer registry record for `get_screenshot`. HTML page: https://policylayer.com/tools/0x-professor-uianalyzermcp/get-screenshot

## Facts

- Tool: `get_screenshot`
- Server: UI Analyzer MCP Server (`0x-professor/uianalyzermcp`) — https://policylayer.com/tools/0x-professor-uianalyzermcp.md
- Homepage: https://github.com/0x-Professor/UIAnalyzerMCP
- Risk category: Read (Low risk)
- Registry record: grade A, identity unverified
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Allowed

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

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_screenshot",
    "arguments": {}
  }
}
```

## Why get_screenshot is rated Low

Screenshot capture retrieves visual data without modifying state, creating side effects, or accessing sensitive operations. While screenshots could theoretically capture sensitive information displayed on screen, the tool itself performs passive observation. Severity is low because the tool only reads UI state; misuse would expose information rather than cause destructive or operational damage.

From the tool's own definition: "Tool name 'get_screenshot' and server context (UI Analyzer using Playwright for website analysis) indicate screenshot capture. Server description emphasizes 'analyzes' and 'provides instructions' with no mention of modification."

## Use case

AI agents call get_screenshot to retrieve information from UI Analyzer MCP Server without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

## Recommended policy (PolicyLayer)

Verdict: **Allowed**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches UI Analyzer MCP Server:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "get_screenshot": {}
  }
}
```

## Other tools on UI Analyzer MCP Server (7)

- `analyze_page` — Read — https://policylayer.com/tools/0x-professor-uianalyzermcp/analyze-page.md
- `compare_viewports` — Read — https://policylayer.com/tools/0x-professor-uianalyzermcp/compare-viewports.md
- `get_accessibility_snapshot` — Read — https://policylayer.com/tools/0x-professor-uianalyzermcp/get-accessibility-snapshot.md
- `get_dom_overview` — Read — https://policylayer.com/tools/0x-professor-uianalyzermcp/get-dom-overview.md
- `get_element_details` — Read — https://policylayer.com/tools/0x-professor-uianalyzermcp/get-element-details.md
- `get_fix_instructions` — Read — https://policylayer.com/tools/0x-professor-uianalyzermcp/get-fix-instructions.md
- `get_tech_stack` — Read — https://policylayer.com/tools/0x-professor-uianalyzermcp/get-tech-stack.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=0x-professor-uianalyzermcp · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/0x-professor-uianalyzermcp