Skip to main content
Verify Metadata Compress PDF PDF Software
Model Context Protocol

PDFCheck MCP Server

Analyze, validate, and optimize PDF files directly from your favourite AI tools โ€” Claude Desktop, GitHub Copilot, Cursor, and more.

Quick Setup

No account needed โ€” you get 10 free PDF analyses per day. Just save the script and configure your AI tool.

What is the Model Context Protocol?

The Model Context Protocol (MCP) is an open standard that allows AI assistants to connect to external tools and data sources. Think of it as a universal plug that lets your AI assistant talk to services like PDFCheck โ€” directly from your chat window.

Natural Language

Just ask your AI to "analyze this PDF" and it handles the rest โ€” no manual API calls needed.

Secure

Your API token stays local on your machine. Files are processed and immediately discarded.

Works Everywhere

Compatible with Claude Desktop, GitHub Copilot, Cursor, Windsurf, and any MCP-compatible client.

How it works: The MCP server runs locally on your machine as a lightweight bridge between your AI assistant and the PDFCheck API. When you ask your AI to analyze a PDF, it calls the local MCP server, which securely forwards the request to our API and returns the results.

Prerequisites

1

Create a free PDFCheck account Optional

Optional โ€” you get 10 free analyses per day without an account. Register to unlock 50 analyses per day.

Create Free Account
2

Generate an API token Optional

For higher limits, go to your account settings and create an API token. Paste it in the Quick Setup above and all configs will auto-fill.

Manage API Tokens
3

Install Node.js (v18+)

The MCP server script requires Node.js 18 or later. Download it from nodejs.org if you do not have it installed.

Available MCP Tools

Once connected, your AI assistant gains access to the following PDF tools:

analyze_pdf

POST

Upload and analyze a PDF file. Returns metadata, creation date, author, software used, page count, and verification status.

get_analysis

GET

Retrieve a previous PDF analysis by its share token. Useful for revisiting or comparing results.

list_analyses

GET

List all your previous PDF analyses. Returns a paginated list with file names, dates, and share tokens.

check_usage

GET

Check your account info and remaining daily API quota. Returns your name, email, and how many analyses you have left today.

Setup Guide

Choose your setup method. The remote URL is the easiest โ€” no files to download or install.

No files to download or install

Just add the URL to your AI tool config. The MCP server runs on our infrastructure โ€” no Node.js, no npm install, no local scripts.

C

Claude Desktop

Open Settings โ†’ Developer โ†’ Edit Config, then add the following to your claude_desktop_config.json:

claude_desktop_config.json

GitHub Copilot

VS Code

Add an MCP server configuration to your VS Code settings. Create or edit .vscode/mcp.json in your project, or add to your global settings:

.vscode/mcp.json

You can also set this in your global VS Code settings.json under "mcp.servers". GitHub Copilot will detect MCP tools automatically in agent mode.

โŒ˜

Cursor

Go to Cursor Settings โ†’ MCP and add a new global MCP server, or create .cursor/mcp.json in your project:

.cursor/mcp.json
W

Windsurf

Open Windsurf Settings โ†’ MCP and add a new server, or edit your mcp_config.json:

~/.codeium/windsurf/mcp_config.json

Enter the full path where you saved the script. The config snippets below will update automatically.

C

Claude Desktop

Open Settings โ†’ Developer โ†’ Edit Config, then add the following to your claude_desktop_config.json:

claude_desktop_config.json

Update the path above to match where you saved pdfcheck-mcp-server.mjs on your machine. The config will update automatically. Replace your-api-token-here with your real API token (get one from the API Tokens page).

GitHub Copilot

VS Code
Install in VS Code

Add an MCP server configuration to your VS Code settings. Create or edit .vscode/mcp.json in your project, or add to your global settings:

.vscode/mcp.json

You can also set this in your global VS Code settings.json under "mcp.servers". GitHub Copilot will detect MCP tools automatically in agent mode.

โŒ˜

Cursor

Go to Cursor Settings โ†’ MCP and add a new global MCP server, or create .cursor/mcp.json in your project:

.cursor/mcp.json
W

Windsurf

Open Windsurf Settings โ†’ MCP and add a new server, or edit your mcp_config.json:

~/.codeium/windsurf/mcp_config.json

MCP Server Script

Save the following file as pdfcheck-mcp-server.mjs anywhere on your machine. This lightweight script bridges your AI tool and the PDFCheck API.

One-time setup: Before using the script, install the MCP SDK dependency: npm install @modelcontextprotocol/sdk
pdfcheck-mcp-server.mjs
Tip: The script has zero configuration files and no build step. Save it, install the SDK, and point your MCP client to it. That is it!

Usage Examples

Once connected, you can use natural language to interact with PDFCheck. Here are some things you can ask your AI assistant:

Example 1 Analyze a PDF

"Analyze the file /Users/me/Documents/contract.pdf and tell me when it was created and what software was used."

Example 2 Check for AI generation

"Check if this PDF looks like it was generated by AI: /Users/me/Downloads/report.pdf"

Example 3 Batch analysis

"Analyze all PDFs in my Downloads folder and list which ones have been modified after creation."

Example 4 Check quota

"How many PDF checks do I have left today on PDFCheck?"

Frequently Asked Questions

Do I need an API token?

No! You can use the MCP server without an API token and get 10 free PDF analyses per day. For 50 analyses per day, create a free account and generate an API token.

Is the MCP server free to use?

Yes! The MCP server is completely free. Without an account you get 10 free analyses per day. Register for a free account to get 50 analyses per day.

Are my PDF files stored on your servers?

No. PDFs are processed in memory and immediately discarded after analysis. Only the extracted metadata is stored in your account history.

Does the MCP server send my files to a third party?

The MCP server only communicates with pdfcheck.io. Your files go directly from your machine to our API over HTTPS. No data is sent to your AI provider โ€” they only see the text results.

What if my AI tool is not listed here?

Any tool that supports the Model Context Protocol should work. The server uses the standard stdio transport. Check your tool's documentation for how to add an MCP server using the "command" + "args" format.

What is the maximum PDF file size?

The API accepts PDF files up to 100 MB.

Can I use this with my own self-hosted PDFCheck instance?

Yes. Change the API_BASE constant in the server script to point to your own instance URL.

Ready to connect your AI tools?

Create a free account, grab your API token, and start analyzing PDFs from your favourite AI assistant in minutes.

Create Free Account View API Documentation