MCP PDF Server

MCP PDF Server

Enables conversion of Markdown content into PDF documents with customizable paper formats and orientations. Supports both inline Markdown text and file path inputs, automatically generating PDFs using Playwright and Chromium.

Category
访问服务器

README

MCP PDF Server

An MCP (Model Context Protocol) server exposing tools to render Markdown into PDF.

What’s included

  • MCP tools: pdf_from_markdown (primary) and md_to_pdf (alias).
  • Accepts inline Markdown or a file path.
  • Options for paper format and orientation; sensible output/ defaults.

Prerequisites

  • Node.js 18+ recommended.

Install

npm install
# Download browsers for Playwright (Chromium only is enough):
npx playwright install chromium

Build

npm run build

Run (stdio)

npm start

Configure in your MCP-compatible client by pointing to the compiled binary or npm start command.

MCP Tools

  • Tool ids: pdf_from_markdown (primary) and md_to_pdf (alias for discoverability)
    • Purpose: Generate a PDF from Markdown.
    • Inputs:
      • markdown (string, optional): Inline Markdown content. If set, path is ignored.
      • path (string, optional): Absolute or relative path to a .md file. Ignored if markdown is provided.
      • outputPath (string, optional): Desired output PDF path. Defaults to output/<timestamp>.pdf and creates missing directories.
      • paperFormat (string, optional): A4 | Letter | Legal (default: A4).
      • paperOrientation (string, optional): portrait | landscape (default: portrait).
      • Provide exactly one of markdown or path. If both are set, markdown takes precedence.
    • Output:
      • Returns a text message containing the absolute path to the created PDF.
    • Example (inline):
      {
        "tool": "md_to_pdf",
        "arguments": {
          "markdown": "# Hello\nThis will render to PDF.",
          "paperFormat": "A4"
        }
      }
      
    • Example (file path):
      {
        "tool": "pdf_from_markdown",
        "arguments": {
          "path": "examples/sample.md",
          "outputPath": "output/sample.pdf",
          "paperOrientation": "landscape"
        }
      }
      

Tool Schema (compact)

tools:
  - id: pdf_from_markdown
    alias: md_to_pdf
    params:
      markdown?: string                # Inline Markdown (preferred if both set)
      path?: string                    # Path to a .md file
      outputPath?: string              # Output PDF path (default: output/<timestamp>.pdf)
      paperFormat?: 'A4'|'Letter'|'Legal'      # default: 'A4'
      paperOrientation?: 'portrait'|'landscape' # default: 'portrait'
    constraints:
      - Provide exactly one of markdown or path (if both provided, markdown is used)
    result:
      - type: text
        text: "PDF created at: <absolute path>"

Client configuration (example) If your MCP client supports JSON configuration for a stdio server, a minimal entry might look like:

{
  "servers": {
    "mcp-pdf": {
      "command": "node",
      "args": ["dist/index.js"]
    }
  }
}

Notes

  • Uses Playwright (Chromium) to render HTML from Markdown and print to PDF.
  • On first install, Playwright may download a browser. You can also point it to an existing Chrome/Chromium.

One‑liner with npx

  • After this package is published to npm, you can run the server directly:
    • npx -y md-2-pdf-mcp (runs the md-2-pdf-mcp bin)
    • Or explicitly: npx -y -p md-2-pdf-mcp mcp-pdf
    • The package defines bin entries and a postinstall that installs Chromium.
  • From the local repo (without publishing):
    • npx --yes .
    • This uses the bin in package.json and the prepare script to build.

推荐服务器

Baidu Map

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。

官方
精选
JavaScript
Playwright MCP Server

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。

官方
精选
TypeScript
Audiense Insights MCP Server

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。

官方
精选
本地
TypeScript
Magic Component Platform (MCP)

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。

官方
精选
本地
TypeScript
VeyraX

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。

官方
精选
本地
Kagi MCP Server

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。

官方
精选
Python
graphlit-mcp-server

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。

官方
精选
TypeScript
Exa MCP Server

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。

官方
精选
mcp-server-qdrant

mcp-server-qdrant

这个仓库展示了如何为向量搜索引擎 Qdrant 创建一个 MCP (Managed Control Plane) 服务器的示例。

官方
精选
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选