MCP.so
登录

PDF.co MCP Server

@nikolausm

代码仓库

关于 PDF.co MCP Server

MCP server for PDF.co API integration - enables AI assistants to perform PDF operations

#pdf-co#pdf-operations#api-integration

基本信息

分类

文件与存储

许可证

MIT license

运行时

node

传输方式

stdio

发布者

nikolausm

配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "pdf-co": {
      "command": "node",
      "args": [
        "/path/to/pdf-co-mcp-server/dist/index.js"
      ],
      "env": {
        "PDFCO_API_KEY": ""
      }
    }
  }
}

工具

6

Merge multiple PDFs

Split PDF pages

Extract text

Convert to JSON

HTML to PDF

Check API credits

概览

What is PDF.co MCP Server?

The PDF.co MCP Server is a Model Context Protocol server that integrates PDF.co’s API into AI assistants, enabling them to perform common PDF operations such as merging, splitting, text extraction, conversion, and HTML-to-PDF generation. It is designed for developers and AI users who need to manipulate PDF documents programmatically through natural language or tool calls.

How to use PDF.co MCP Server?

  1. Clone the repository, run npm install && npm run build.
  2. Obtain an API key from PDF.co.
  3. Configure your MCP client (e.g., Claude Desktop) by adding the server definition to your mcpServers config, setting the PDFCO_API_KEY environment variable, and pointing command to the built dist/index.js.

Key features of PDF.co MCP Server

  • Merge multiple PDFs into one document.
  • Split a PDF into individual pages or ranges.
  • Extract text content from PDF files.
  • Convert PDF data to JSON format.
  • Generate PDF from HTML input.
  • Check your API credits balance.

Use cases of PDF.co MCP Server

  • Automate document assembly by merging several PDF reports.
  • Extract structured text from scanned invoices or forms.
  • Convert web pages (HTML) to PDF for archival or sharing.
  • Split a large PDF into smaller, page‑specific files.
  • Programmatically check remaining API usage before processing.

FAQ from PDF.co MCP Server

What does PDF.co MCP Server do exactly?

It acts as a bridge between AI assistants (via the MCP protocol) and the PDF.co API, exposing six tools for common PDF operations: merging, splitting, text extraction, JSON conversion, HTML-to-PDF, and credit balance checks.

How do I get an API key?

Obtain your API key from PDF.co’s dashboard. The key must be set as the environment variable PDFCO_API_KEY in your MCP client configuration.

What dependencies are required?

Node.js and npm are needed to build and run the server. No additional runtime is required beyond the PDF.co API key.

Where are my PDFs processed?

All PDF operations are performed on PDF.co’s cloud servers. The server sends your files to the API and returns the results; no local processing of PDF content occurs.

How can I check my API usage?

Use the get_credits_balance tool to view your remaining credits, helping you avoid exceeding your plan limit.

评论

文件与存储 分类下的更多 MCP 服务器

S3 MCP Server

samuraikun

MCP server to integrate AWS S3 and LLM

26

Storacha MCP Storage Server

storacha

Storacha MCP storage server - self-sovereign data for your AI applications.

13

Google Drive MCP Server

hxie-pallas

A google drive mcp servers based on Python

8

mcp-v8: V8 JavaScript MCP Server

r33drichards

MCP server that exposes a V8 JavaScript runtime as a tool for AI agents like Claude and Cursor. Supports persistent heap snapshots via S3 or local filesystem, and is ready for integration with modern AI development environments.

47

Bulk Filesystem Operations MCP Server

strawgate

MCP Server for reading many files at the same time

25