pdfzen

Render PDFs from 45 starter templates or raw HTML. Pay-per-render with USDC via x402.

Should I use this

Quality & Safety

A
Description quality
100%
Schema completeness
83%
Naming quality
100%
Poisoning risk
100%
Permission match
100%
Protocol compliance
100%

Based on automated analysis of tool definitions and protocol compliance.

Context Cost

~1,008Tokens (tool definitions)
~1.5 KBTypical response size
Moderate attention impact (0.79% of 128k context)

This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.

Install

One-Click Install

Add this to your `claude_desktop_config.json` file:

{
  "mcpServers": {
    "render": {
      "url": "https://api.pdfzen.site/mcp"
    }
  }
}

Remote endpoints

https://api.pdfzen.site/mcpstreamable-http

What it can do

Tool inventory

Tools (4)

🟢 Read-only🟡 Write🔴 Delete⚪ Unknown
🟢list_starters

List pdfzen's 45 public starter templates — invoices, receipts, contracts, certificates, NDAs, letters, reports, resumes, boarding passes, menus, bank statements, lab reports, lease agreements, performance reviews, and more. Returns an array of { slug, name, description, icon, pageOptions, fonts, dataKeys }. Free, no payment, no auth required. Call this first to discover what fits the user request, then optionally call get_starter to see the expected data shape, then call render_template_to_pdf to produce the PDF.

Input Schema

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}
🟢get_starter(slug)

Fetch the full HTML body, CSS, sampleData, and pageOptions for one starter template by slug. Use this when you need to understand the exact shape of `data` the template expects before calling render_template_to_pdf, or when you want to fork a starter into custom HTML. Free, no payment, no auth required.

Input Schema

{
  "type": "object",
  "properties": {
    "slug": {
      "type": "string",
      "description": "The starter slug. Examples: \"invoice\", \"receipt\", \"certificate\", \"contract\", \"nda\", \"boarding-pass\", \"menu\". Call list_starters to discover all 45 slugs."
    }
  },
  "required": [
    "slug"
  ],
  "additionalProperties": false
}
🟡render_template_to_pdf(template, data, pageOptions)

Prepare a paid PDF render from one of the 45 starter templates. Validates your template + data and returns the exact, ready-to-execute HTTP request to run against pdfzen's render endpoint — POST /v402/render/pdf (x402, $0.006 USDC on Base, no API key) or POST /v1/render/pdf (pdfzen API key, credit-billed). pdfzen renders are executed over HTTP, not streamed in-band over MCP; this tool is the bridge. Your `data` is merged ON TOP of the starter sampleData at render time, so partial payloads inherit demo defaults (e.g. ship just the customer name + total).

Input Schema

{
  "type": "object",
  "properties": {
    "template": {
      "type": "string",
      "description": "Slug of the starter to render (e.g. \"invoice\", \"receipt\", \"certificate\"). Call list_starters first if unsure which fits the user request."
    },
    "data": {
      "type": "object",
      "description": "Handlebars context. Each starter expects a specific shape — call get_starter to see the sampleData and dataKeys for the chosen slug. Your fields merge ON TOP of sampleData, so you can supply only the fields the user gave you and the rest fall back to the demo content.",
      "additionalProperties": true
    },
    "pageOptions": {
      "type": "object",
      "description": "Page format/margin/orientation overrides. Defaults come from the starter (most are A4 portrait). Example: { \"format\": \"Letter\", \"landscape\": true }.",
      "additionalProperties": true
    }
  },
  "required": [
    "template"
  ],
  "additionalProperties": false
}
🟡render_html_to_pdf(html, css, data, pageOptions)

Prepare a paid PDF render from arbitrary Handlebars-flavoured HTML. Use only when no starter fits (one-off layouts, custom branding). Prefer render_template_to_pdf when a starter matches. Validates your HTML and returns the exact, ready-to-execute HTTP request to run against pdfzen's render endpoint — POST /v402/render/pdf (x402, $0.006 USDC on Base, no API key) or POST /v1/render/pdf (pdfzen API key). pdfzen renders are executed over HTTP, not streamed in-band over MCP; this tool is the bridge.

Input Schema

{
  "type": "object",
  "properties": {
    "html": {
      "type": "string",
      "description": "The HTML body. Supports Handlebars {{ }} expressions resolved against `data`, plus pdfzen helpers ({{barChart}}, {{lineChart}}, {{pageBreak}}, {{#each}}, {{#if eq}}). Don't include <html>/<head>; just the body content + any <style> tags."
    },
    "css": {
      "type": "string",
      "description": "Optional CSS injected into the document head. Alternative to inline <style> in `html`."
    },
    "data": {
      "type": "object",
      "description": "Handlebars context object resolved against the {{...}} expressions in `html`.",
      "additionalProperties": true
    },
    "pageOptions": {
      "type": "object",
      "description": "Page format/margin/orientation. Defaults to A4 portrait. Example: { \"format\": \"A4\", \"margin\": { \"top\": \"20mm\" } }.",
      "additionalProperties": true
    }
  },
  "required": [
    "html"
  ],
  "additionalProperties": false
}

Recommended Prompts

retrieve_data
Get details about [item] from pdfzen
Expected tools: get_starter
fetch_info
Fetch [information type] using pdfzen
Expected tools: get_starter
list_items
List all [items] available in pdfzen
Expected tools: list_starters
browse_collection
Show me the [collection] from pdfzen
Expected tools: list_starters
explore_workflow
List available [items], then get details for each one using pdfzen
Expected tools: list_startersget_starter

Community

Rate this Server

Evidence

Recent observations

verifiedversion not recorded4 tools
verifiedversion not recorded4 tools