rendoc
Generate professional PDFs from Claude, Cursor, and other AI tools. Create invoices, contracts, reports, and certificates from templates or inline HTML markup.
README
@rendoc/mcp-server
<a href="https://glama.ai/mcp/servers/@yoryocoruxo-ai/rendoc-mcp-server"> <img width="380" height="200" src="https://glama.ai/mcp/servers/@yoryocoruxo-ai/rendoc-mcp-server/badge" alt="rendoc MCP server" /> </a>
The rendoc MCP server lets AI assistants like Claude Desktop, Cursor, and any other MCP-compatible client generate professional PDF documents on demand. Connect your AI to rendoc and it can create invoices, contracts, reports, certificates, and any other PDF — from reusable templates or inline HTML/Handlebars markup — all from a natural language prompt.
Turn "Generate an invoice for Acme Corp, 40 hours of consulting at €85/h" into a delivered PDF in seconds.
Use Cases
| Use Case | Example Prompt |
|---|---|
| Invoices | "Generate an invoice for client X with these line items..." |
| Contracts | "Draft a freelance contract for TechStart SL, €18,000 fee, 50% upfront..." |
| Certificates | "Issue a course completion certificate for María González..." |
| Reports | "Create a March 2026 sales report with these KPIs..." |
| Bulk generation | "Generate certificates for all 50 attendees in this CSV" |
| Custom documents | Anything you can describe in HTML + data |
See detailed walkthroughs in examples/.
Features
- 7 tools for document generation, template management, and usage tracking
- Template-based or inline — save reusable templates or pass markup on the fly
- Handlebars syntax — use
{{variables}},{{#each}},{{#if}}in your markup - Multiple paper sizes — A4, Letter, Legal, A3, A5, portrait or landscape
- Schema validation — templates can declare a JSON Schema so the AI can't pass invalid data
- Zero config — just set
RENDOC_API_KEYand go - Lightweight — ~35 KB unpacked, pure TypeScript, only 2 runtime dependencies
- Verified on Glama — security, quality, and license checks passed
Quick Setup for Claude Desktop
Add this to your Claude Desktop configuration file (claude_desktop_config.json):
{
"mcpServers": {
"rendoc": {
"command": "npx",
"args": ["-y", "@rendoc/mcp-server"],
"env": {
"RENDOC_API_KEY": "your-api-key"
}
}
}
}
Restart Claude Desktop. The rendoc tools will appear in the MCP tools menu.
Quick Setup for Claude Code
Add this to your project or global settings (.claude/settings.json):
{
"mcpServers": {
"rendoc": {
"command": "npx",
"args": ["-y", "@rendoc/mcp-server"],
"env": {
"RENDOC_API_KEY": "your-api-key"
}
}
}
}
Quick Setup for Cursor
Add to ~/.cursor/mcp.json (or your project's .cursor/mcp.json):
{
"mcpServers": {
"rendoc": {
"command": "npx",
"args": ["-y", "@rendoc/mcp-server"],
"env": {
"RENDOC_API_KEY": "your-api-key"
}
}
}
}
Available Tools
| Tool | Description | Key Parameters |
|---|---|---|
generate_document |
Generate a PDF from a template or inline markup | template_id or markup, data, paper_size?, orientation?, filename? |
list_templates |
List available document templates | category? |
preview_template |
Inspect a template's markup, styles, and schema | template_id |
create_template |
Create a new reusable template | name, slug, markup, schema, category?, styles?, sample_data?, paper_size?, orientation?, is_public? |
delete_template |
Delete a template by ID | template_id |
get_document |
Get details of a generated document | document_id |
get_usage |
View monthly API usage statistics | (none) |
Each tool returns structured JSON with download URLs, document IDs, and metadata the assistant can act on.
Get an API Key
- Sign up at rendoc.dev
- Go to the API Keys dashboard
- Create a new key and copy it into your MCP client config
Environment Variables
| Variable | Required | Default | Description |
|---|---|---|---|
RENDOC_API_KEY |
Yes | — | Your rendoc API key for authentication |
RENDOC_API_URL |
No | https://rendoc.dev |
Base URL for the rendoc API (useful for self-hosted instances) |
Examples
Detailed walkthroughs with real prompts and tool calls:
- 01 — Invoice from inline markup — single-shot invoice generation
- 02 — Freelance contract template — create once, reuse forever
- 03 — Certificate from saved template — multi-step tool discovery
- 04 — Monthly sales report — rich visualizations with CSS
- 05 — Bulk generation from dataset — 50 PDFs from one prompt
How It Works
┌──────────────┐ MCP/stdio ┌────────────────────┐ HTTPS ┌─────────────┐
│ Claude Code │ ─────────────▶ │ @rendoc/mcp-server │ ────────▶ │ rendoc API │
│ / Desktop │ │ (this package) │ │ (PDF gen) │
└──────────────┘ ◀───────────── └────────────────────┘ ◀──────── └─────────────┘
▲ tool results download URL
│
└── User prompt: "Generate an invoice for..."
The MCP server translates natural language tool calls from your AI assistant into authenticated REST requests to the rendoc API, and returns structured responses with PDF download URLs.
Contributing
Contributions are welcome. See CONTRIBUTING.md for development setup and PR guidelines.
For security issues, please see SECURITY.md and email info@rendoc.dev — do not open a public issue.
Links
- Website: rendoc.dev
- Docs: rendoc.dev/docs
- npm Package:
@rendoc/mcp-server - Glama Listing: glama.ai/mcp/servers/@yoryocoruxo-ai/rendoc-mcp-server
- Official SDKs:
@rendoc/sdk(TypeScript),rendoc(Python)
License
MIT — see LICENSE.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。