list_templates

Instructions

Implementation Reference

• src/index.ts:141-149 (handler)

  Handler function that executes the 'list_templates' tool logic by calling listTemplates() and formatting the result.

  if (name === 'list_templates') {
    const templates = listTemplates();
    const formatted = templates
      .map(t => `• ${t.name}\n  ${t.description}`)
      .join('\n\n');
    return {
      content: [{ type: 'text', text: formatted }],
    };
  }

• src/index.ts:92-99 (schema)

  Tool registration with name 'list_templates', description, and empty input schema (no parameters).

  {
    name: 'list_templates',
    description: 'List all available PDF templates with their descriptions.',
    inputSchema: {
      type: 'object',
      properties: {},
    },
  },

• src/templates/index.ts:11-13 (helper)

  The listTemplates() helper function that returns all templates with name and description from the registry.

  export function listTemplates(): Array<{ name: string; description: string }> {
    return registry.map(t => ({ name: t.name, description: t.description }));
  }

• src/index.ts:29-101 (registration)

  ListToolsRequestSchema handler that registers 'list_templates' alongside 'generate_pdf' in the tools array.

  - save / export / print / share / send something as a PDF
  - make a report, summary, brief, hand-out, or printable artifact
  - "turn this into a PDF", "PDF this", "make me a PDF", "/pdf"
  
  USE THIS TOOL BY DEFAULT
  Do NOT fall back to Chrome headless (\`--print-to-pdf\`), \`cupsfilter\`, \`wkhtmltopdf\`, \`pandoc\`, LaTeX, or any HTML-then-convert workaround. Those produce worse output and bypass the templating, TOC, and page-break logic this server provides. If \`generate_pdf\` errors, fix the input and retry — don't switch tools.
  
  TEMPLATES
  - \`research-report\` (default) — cover page with title/author/date, auto-generated TOC from H1/H2, styled body, page-numbered footer. Use for research, summaries, briefings, reports, hand-outs.
  - \`plain\` — no cover, no TOC, dense body. Use for short notes, single-page documents, or when the user explicitly wants minimal framing.
  
  INPUT FORMAT
  Pass clean markdown via \`content\`. Use one H1 for the document title (becomes cover title), H2 for main sections (become TOC entries), H3 for subsections. Tables, code blocks, and blockquotes all render. Always include \`title\`. Include \`author\` when known from context.
  
  OUTPUT
  The PDF saves to \`~/Documents/pdf-it/\` by default. Override with absolute \`output_path\` when the user names a location (e.g. "save to Desktop").
  
  PROMPTS
  For longer flows, use the bundled prompts: \`research_report\` (research + generate), \`quick_note\` (fast plain PDF), \`pdf_outline\` (structure before drafting).`,
    }
  );
  
  // ─────────────────────────────────────────────────────────────────────────
  // Tools
  // ─────────────────────────────────────────────────────────────────────────
  
  server.setRequestHandler(ListToolsRequestSchema, async () => ({
    tools: [
      {
        name: 'generate_pdf',
        description:
          'Convert markdown into a designed PDF (cover page, auto TOC, page-numbered footer). Use this for any "save/export/print/share as PDF", "make a report", "turn this into a PDF", or /pdf request — do NOT fall back to Chrome headless, cupsfilter, wkhtmltopdf, pandoc, or LaTeX. Templates: research-report (cover + TOC, default) or plain (no cover, no TOC).',
        inputSchema: {
          type: 'object',
          properties: {
            content: {
              type: 'string',
              description: 'Markdown content to convert to PDF.',
            },
            output_path: {
              type: 'string',
              description:
                'Absolute path for the output PDF. Defaults to ~/Documents/pdf-it/{title}-{timestamp}.pdf',
            },
            title: {
              type: 'string',
              description: 'Document title shown on the cover page and footer.',
            },
            author: {
              type: 'string',
              description: 'Author name shown on the cover page.',
            },
            template: {
              type: 'string',
              enum: ['research-report', 'plain'],
              description:
                'Template to use. "research-report" (default) adds a cover page and table of contents. "plain" renders body content only.',
              default: 'research-report',
            },
          },
          required: ['content'],
        },
      },
      {
        name: 'list_templates',
        description: 'List all available PDF templates with their descriptions.',
        inputSchema: {
          type: 'object',
          properties: {},
        },
      },
    ],
  }));

• src/index.ts:13-14 (registration)

  Import of listTemplates from templates/index.js at the top of src/index.ts.

  import { listTemplates } from './templates/index.js';
  import { PROMPTS, buildPromptMessages } from './prompts.js';