Skip to main content
Glama

get_screenshot

Search by keywords to find matching product screenshots and view their image URLs for layout, colors, and design patterns.

Instructions

Searches 217 real Log360 Cloud product screenshots by keywords. Returns matching image URLs you can view to understand exact layout, colors, spacing, and data patterns. ALWAYS use this to see what a page really looks like before building it.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
queryYesSearch keywords (e.g. 'windows startup', 'alerts main', 'dashboard events', 'settings device'). Searches screenshot filenames.
max_resultsNoMax results (default 5)

Implementation Reference

  • The get_screenshot tool handler. It accepts a 'query' string and optional 'max_results' number, searches the SCREENSHOTS array for matching keywords, scores results, and returns image URLs from GitHub. This is the actual implementation of the tool logic.
    server.tool("get_screenshot", "Searches 217 real product screenshots by keywords. Returns image URLs showing exact layouts, colors, and spacing. Use this for visual reference instead of looking for local files.", { query: z.string().describe("Search keywords (e.g. 'windows startup', 'alerts main', 'dashboard', 'settings device')"), max_results: z.number().optional().describe("Max results, default 5") }, async ({ query, max_results }) => {
      const keywords = query.toLowerCase().split(/[\s,]+/).filter(Boolean);
      const max = max_results || 5;
      const scored = SCREENSHOTS.map(s => {
        let score = 0;
        const lower = s.toLowerCase();
        for (const kw of keywords) { if (lower.includes(kw)) score++; }
        return { path: s, score };
      }).filter(r => r.score > 0).sort((a, b) => b.score - a.score).slice(0, max);
      if (!scored.length) return { content: [{ type: "text" as const, text: `No screenshots for "${query}". Try broader keywords.\nAvailable tabs: ALERTS, COMPLIANCE, DASHBOARD, REPORTS, SEARCH, Security, Settings, CLOUD PROTECTION.\nExample: "windows startup", "alerts main", "dashboard events", "settings device"` }] };
      const lines = scored.map((r, i) => {
        const encoded = r.path.split('/').map(p => encodeURIComponent(p)).join('/');
        return `${i+1}. **${r.path}**\n   URL: ${SCREENSHOT_BASE}/${encoded}`;
      });
      return { content: [{ type: "text" as const, text: `Found ${scored.length} screenshot(s) for "${query}":\n\n${lines.join("\n\n")}\n\nThese are real product screenshots. Match the layout exactly.` }] };
  • The input schema for get_screenshot: 'query' (required string) and 'max_results' (optional number, default 5). Defined inline in the server.tool() call.
    server.tool("get_screenshot", "Searches 217 real product screenshots by keywords. Returns image URLs showing exact layouts, colors, and spacing. Use this for visual reference instead of looking for local files.", { query: z.string().describe("Search keywords (e.g. 'windows startup', 'alerts main', 'dashboard', 'settings device')"), max_results: z.number().optional().describe("Max results, default 5") }, async ({ query, max_results }) => {
  • api/mcp.ts:673-674 (registration)
    The tool registration as the 14th tool, registered via server.tool() on the MCP server instance inside createMcpHandler.
    /* 14. get_screenshot */
    server.tool("get_screenshot", "Searches 217 real product screenshots by keywords. Returns image URLs showing exact layouts, colors, and spacing. Use this for visual reference instead of looking for local files.", { query: z.string().describe("Search keywords (e.g. 'windows startup', 'alerts main', 'dashboard', 'settings device')"), max_results: z.number().optional().describe("Max results, default 5") }, async ({ query, max_results }) => {
  • SCREENSHOTS array — the data source that get_screenshot searches. Contains 15 screenshot file paths organized by tab (ALERTS TAB, COMPLIANCE TAB, DASHBOARD TAB, etc.).
    const SCREENSHOTS: string[] = [
    "ALERTS TAB/[Main] Alerts - Main View Severity Stat Cards Table with Critical Trouble Attention Counts.png",
    "ALERTS TAB/[Main] Alerts - Manage Profiles Table with Alert Types Severity Log Source Actions.png",
    "ALERTS TAB/[Interaction] Alerts - Alert Detail Drawer EXE Process Executed with MITRE and Ticket Status.png",
    "COMPLIANCE TAB/[Main] Compliance - Landing Page Grid Row 1 PCI-DSS HIPAA FISMA GDPR SOX ISO27001.png",
    "COMPLIANCE TAB/[Main] Compliance - PCI-DSS User Logons Report Bar Chart Sidemenu Table.png",
    "DASHBOARD TAB/[Main] Events Overview - Main Dashboard with Log Trend and Severity Charts.png",
    "DASHBOARD TAB/[Main] Network Overview - Traffic Trend and Top Network Devices.png",
    "REPORTS TAB/[Main] Reports - Servers & Workstation - Windows - All Events Table View with Line Chart.png",
    "REPORTS TAB/[Main] Reports - Servers & Workstation - Windows - Sidemenu Startup Events Expanded.png",
    "REPORTS TAB/[Main] Reports - Servers & Workstation - Unix - All Events Line Chart Severity Table.png",
    "SEARCH TAB/[Main] Search - Results Page Bar Chart Severity Emergency Log List View.png",
    "Security TAB/[Main] Security - Analytics Dashboard Detection Pipeline MITRE Tactics Trends.png",
    "Settings TAB/[Main] Settings - Device Management Windows Devices Table IP Agent Status.png",
    "Settings TAB/[Main] Settings - License Page Storage Stats Feature Table Usage Bars.png",
    "CLOUD PROTECTION TAB/[Main] Cloud Protection - Application Insight Dashboard Traffic Trend Shadow Apps Banned Apps Charts.png",
    ];
    
    const SCREENSHOT_BASE = `https://raw.githubusercontent.com/${PRIVATE_REPO}/main/data/LOG360%20Cloud%20Full%20Product%20Bulk%20Screenshot_`;
  • SCREENSHOT_BASE — the base URL used to construct full image URLs for screenshots.
    const SCREENSHOT_BASE = `https://raw.githubusercontent.com/${PRIVATE_REPO}/main/data/LOG360%20Cloud%20Full%20Product%20Bulk%20Screenshot_`;
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. While the search is likely harmless, it doesn't mention any side effects, permissions, or rate limits. The description only states the function without deeper behavioral traits.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences with no wasted words. The first sentence explains the action, and the second provides usage guidance. It is front-loaded with the key purpose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple search tool, the description mentions the number of screenshots (217), the product (Log360 Cloud), and the return type (image URLs). Without an output schema, it covers the essentials. It could optionally mention pagination, but it's not critical.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, meaning both parameters already have descriptions in the schema. The description adds that it searches by filename and returns URLs, but this is only marginal value beyond the schema. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool searches 217 real screenshots by keywords and returns image URLs. It uses specific verbs like 'searches' and 'returns', and the resource ('Log360 Cloud product screenshots') is well-defined. It distinguishes itself from sibling tools like 'get_icons' or 'get_component' by focusing on visual page layout.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly says 'ALWAYS use this to see what a page really looks like before building it,' providing strong guidance on when to use. However, it doesn't mention when not to use or provide alternatives, though the implied context is clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Anguraj-zoho/elegant-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server