Skip to main content
Glama

get_recipe

Retrieve the complete recipe for creating a Shell type (A, B, C, or D) page scaffolding, including required wiki files, CSS load order, scroll model, and shell structure. Use this tool instead of reading documentation files.

Instructions

Returns the full recipe for a Shell type (A/B/C/D): required wiki files, CSS load order, scroll model, and shell structure. Read this INSTEAD of LLM-WIKI.md or INDEX.md for page scaffolding.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
shellYesA=Dashboard, B=Settings, C=Reports, D=Split-Panel/Detail

Implementation Reference

  • The get_recipe tool handler: accepts a shell letter (A/B/C/D) and returns the corresponding recipe from the RECIPES static data object.
    /* 3. get_recipe */
    server.tool("get_recipe", "Returns the full build recipe for a Shell type: required components, CSS load order, scroll model, and page structure. A=Dashboard, B=Settings, C=Reports, D=Split-Panel.", { shell: z.enum(["A","B","C","D"]) }, async ({ shell }) => {
      return { content: [{ type: "text" as const, text: RECIPES[shell] || `Unknown shell: ${shell}` }] };
    });
  • Input schema for get_recipe: 'shell' is a z.enum restricting values to A, B, C, or D.
    server.tool("get_recipe", "Returns the full build recipe for a Shell type: required components, CSS load order, scroll model, and page structure. A=Dashboard, B=Settings, C=Reports, D=Split-Panel.", { shell: z.enum(["A","B","C","D"]) }, async ({ shell }) => {
      return { content: [{ type: "text" as const, text: RECIPES[shell] || `Unknown shell: ${shell}` }] };
  • api/mcp.ts:581-581 (registration)
    Registration of the 'get_recipe' tool via server.tool() call with description and handler.
    /* 3. get_recipe */
  • The RECIPES static data object containing the full build instructions for Shell A (Dashboard), B (Settings), C (Reports), and D (Split-Panel).
    const RECIPES: Record<string, string> = {
      A: `# Recipe A — Dashboard (Shell A)\n\nPage types: Home dashboard, Security overview, Cloud Protection, Threat Hub.\n\n## ⚠️ PREREQUISITE: Call setup_project FIRST\nOutput = SINGLE index.html with ALL assets from CDN. NEVER create local folders. NEVER copy assets. NEVER read local files — use MCP tools only.\n\n## Required wiki files (open ALL before writing HTML)\n1. app_shells.md — Shell A tree\n2. layout_shell.md — base HTML skeleton\n3. design_tokens.md — CSS variables\n4. topnavbar.md — TopNavBar (data-active-tab="Home")\n5. line_tab.md — sub-tabs + dashboard variant actions\n6. header.md — Variant 1 (title + help icon)\n7. widget.md — widget cards (10 patterns)\n8. stat_card.md — KPI stat cards\n9. tile_widgets.md — tile JS API\n10. predefined_charts.md — ElegantEChart.* API\n11. echarts-widget.md — chart engine\n12. echarts-elegant-theme.md — theme\n13. icons.md — icon lookup\n14. form_input.md — filter inputs\n15. form_dropdown.md — filter dropdowns\n16. drawer.md — detail drawers\n17. button-row.md — action buttons\n\n## CSS load order\ntokens → layout → topnavbar → line-tab → widget → table → responsive → notification-banner\n\n## Scroll model\nONLY .dash scrolls (flex:1; overflow-y:auto). Everything above is fixed.\n\n## Shell A structure\n\`\`\`\ndiv.app-shell (height:100vh; flex:column)\n ├── header.topnavbar\n ├── div.line-tab (h:40px) + div.line-tab__actions\n ├── div.toolbar [OPTIONAL]\n └── div.dash (bg:#F5F5F5; flex:1; overflow-y:auto)\n      └── div.dash__grid\n           ├── div.dash__row.stat-row   — max 4 stat cards\n           ├── div.tile-grid            — max 3 tiles\n           └── div.dash__row            — hybrid widgets (max 3/row)\n\`\`\``,
      B: `# Recipe B — Settings (Shell B)\n\nPage types: Settings tab, Admin config, Device Management.\n\n## ⚠️ PREREQUISITE: Call setup_project FIRST\nOutput = SINGLE index.html with ALL assets from CDN. NEVER create local folders. NEVER copy assets. NEVER read local files — use MCP tools only.\n\n## Required wiki files\n1-15: app_shells (Shell B), layout_shell, design_tokens, topnavbar (Settings), sidemenu_variant1_settings, header, classic_tab, data_table_type1, actionbar (Types 1-7), form_input, form_dropdown, drawer, button-row, note-container, icons\n\n## CSS load order\ntokens → layout → topnavbar → sidemenu → header → classic-tab → table → form-input → form-dropdown → drawer → responsive → notification-banner\n\n## Shell B structure\n\`\`\`\ndiv.app-shell\n ├── header.topnavbar\n └── div.app-body\n      ├── aside.sidemenu (w:240px)\n      └── main.main-content\n           ├── div.page-header\n           └── div.classic-tab\n                ├── div.classic-tab__headers\n                └── div.classic-tab__body → [actionbar + data-table]\n\`\`\``,
      C: `# Recipe C — Reports (Shell C)\n\nPage types: Reports tab, Compliance pages, any sidebar report tree + chart + table.\n\n## ⚠️ PREREQUISITE: Call setup_project FIRST\nOutput = SINGLE index.html with ALL assets from CDN. NEVER create local folders. NEVER copy assets. NEVER read local files — use MCP tools only.\n\n## Required wiki files\n1-17: app_shells (Shell C), layout_shell, design_tokens, topnavbar (Reports), sidemenu_variant2_reports, header (Variant 3), classic_tab, rpt-chart-floater, predefined_charts + echarts-widget + echarts-elegant-theme, form_input, form_dropdown, data_table_type1, actionbar (Type 8), drawer, button-row, note-container, icons\n\n## Critical Shell C assembly rules\n1. .reports-quicklink is a DIRECT CHILD of .app-shell\n2. .classic-tab contains ONLY the chart area\n3. .table-scroll-area is a SIBLING of .classic-tab, NOT a child\n4. ActionBar Type 8 MANDATORY\n5. Header Variant 3 MANDATORY\n\n## Shell C structure\n\`\`\`\ndiv.app-shell\n ├── header.topnavbar (data-active-tab="Reports")\n ├── div.reports-quicklink → div.line-tab.line-tab--quicklink\n └── div.app-body\n      ├── aside.sidemenu.sidemenu--type2\n      └── main.main-content\n           ├── div.page-header (Variant 3)\n           ├── div.reports-input-row.reports-input-row--type1\n           ├── div.classic-tab [chart ONLY]\n           └── div.table-scroll-area\n                ├── div.actionbar (Type 8, sticky)\n                └── div.data-table-wrap → table.data-table\n\`\`\``,
      D: `# Recipe D — Split Panel (Shell D)\n\nPage types: AI Investigation, Incident Detail/Workbench, Playbook Editor.\n\n## ⚠️ PREREQUISITE: Call setup_project FIRST\nOutput = SINGLE index.html with ALL assets from CDN. NEVER create local folders. NEVER copy assets. NEVER read local files — use MCP tools only.\n\n## Shell D structure\n\`\`\`\ndiv.app-shell\n ├── header.topnavbar\n └── div.app-body\n      └── main.main-content (padding:0)\n           ├── div.line-tab\n           └── div.line-tab__body\n                └── div.split-layout (flex:row)\n                     ├── div.left-panel (flex:1; overflow-y:auto)\n                     └── div.right-panel (w:380px; border-left)\n\`\`\``,
    };
  • dist/index.d.ts:7-7 (registration)
    TypeScript declaration file listing get_recipe as an exposed tool returning Shell A/B/C/D recipe.
    *   get_recipe         → Shell A/B/C/D recipe (required files + structure)
Behavior3/5

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

With no annotations, the description carries the full burden for behavioral disclosure. It indicates a read-only operation by stating 'Returns', but does not disclose any additional behavioral traits like permissions, side effects, or output format details.

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, front-loaded with the core action, and contains no extraneous information. Every sentence earns its place, making it efficient and easy to parse.

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?

Given the tool's simplicity (one enumerated parameter, no output schema, no annotations), the description adequately covers the input and output scope. It could optionally mention the recipe's general structure, but it remains complete enough for correct invocation.

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?

The input schema has 100% description coverage for the single parameter, including enum values with descriptions. The tool description reiterates the shell types but adds no additional meaning beyond what the schema already provides, so 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 what the tool does: returns the full recipe for Shell types A/B/C/D, listing specific content like required wiki files, CSS load order, scroll model, and shell structure. It uses specific verbs and resources, and the purpose is distinct from sibling tools like get_shell or get_component.

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 advises to use this tool instead of LLM-WIKI.md or INDEX.md for page scaffolding, providing clear usage context. However, it does not differentiate from sibling tools such as get_shell or get_full_wiki_file, missing explicit when-not or alternative tool guidance.

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