PDFCheck MCP
PDF मेटाडेटा देखें, AI-जनित सामग्री का पता लगाएं, संपादन इतिहास जांचें और प्रामाणिकता सत्यापित करें।
दस्तावेज़
PDFCheck MCP Server
Inspect PDF metadata and access your analysis history from an assistant that supports the remote HTTP server or the local MCP bridge.
Quick Setup
✓ Token applied — all configs below are updated. Paste your token and all setup examples below will be auto-filled.
No account needed for 10 metadata analyses per day per IP. Connect using the remote URL or local script. Keep anonymous results in your client; they cannot be retrieved later.
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 — directly from your chat window.
Natural Language
Ask your assistant to inspect a PDF. Remote clients need file-reading and base64-encoding tools; the local bridge reads the file from its path.
Secure
Store your token in client settings or environment variables; it is sent to PDFCheck for authentication. Original checker uploads are removed after processing; result metadata follows our Privacy Policy.
Choose your transport
Use a client that supports remote HTTP MCP with bearer headers, or a client that can run the local stdio bridge. OAuth-only connections are not supported by this setup.
How it works: The remote HTTP server receives base64-encoded PDF contents from your client. The optional local bridge reads a PDF from your machine and uploads it to the REST API. Both return metadata analysis as JSON inside content[0].text.
Prerequisites
1
Create a free PDFCheck account Optional
An account is optional for 10 metadata analyses per day per IP. A free account with an API token has 100 checks per day and access to its saved analyses.
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.
3
Local bridge only: install Node.js
The optional local script needs Node.js 18 or later. Remote HTTP connections do not require Node.js or a downloaded script.
Available MCP Tools
These MCP tools cover metadata analysis and account history. Compression, structural validation, signing, and other browser tools are not exposed by these methods.
analyze_pdf
POST
Inspect metadata, dates, software fields, and page count. The remote tool takes file_base64 and filename; the local bridge takes filePath. Metadata does not prove authenticity or AI authorship.
get_analysis
GET
Use the returned data.id as token to retrieve your account analysis or a public result. The remote server allows public-result retrieval anonymously; the local bridge requires a token. New anonymous analyses are private and cannot be retrieved later.
list_analyses
GET
Requires an API token. The remote server returns up to 50 recent account analyses; the local bridge returns the first REST page. Entries include file names, dates, and analysis IDs.
check_usage
GET
Check the remaining daily metadata allowance. Remote HTTP supports anonymous usage; account details and the local bridge require an API token.
Setup Guide
Choose remote HTTP for a supported client, or the local script for a stdio connection. Remote HTTP requires no download. Check your client documentation before using a configuration example.
No files to download or install
Just add the URL to your AI tool config. The MCP server runs on our infrastructure — no Node.js, no npm install, no local scripts.
C
Claude Desktop
Open Settings → Developer → Edit Config, then add the following to your 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:
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.
⌘
Cursor
Go to Cursor Settings → MCP and add a new global MCP server, or create.cursor/mcp.json in your project:
W
Windsurf
Open Windsurf Settings → MCP and add a new server, or edit your mcp_config.json:
Enter the full path where you saved the script. The config snippets below will update automatically.
C
Claude Desktop
Open Settings → Developer → Edit Config, then add the following to your 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
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:
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.
⌘
Cursor
Go to Cursor Settings → MCP and add a new global MCP server, or create.cursor/mcp.json in your project:
W
Windsurf
Open Windsurf Settings → MCP and add a new server, or edit your 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
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
After connecting, use these prompts with a client that can read the requested files. Remote analyze_pdf needs file_base64 and filename; a local path alone is not enough. The local bridge accepts filePath.
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 Inspect software indicators
"Inspect the creator and producer fields in /Users/me/Downloads/report.pdf. Explain the software indicators without treating them as proof of AI authorship."
Example 3 Batch analysis
"Analyze the PDFs I select from my Downloads folder one at a time. Compare their reported creation and modification dates, and explain missing or inconsistent metadata."
Example 4 Check quota
"How many PDF checks do I have left today on PDFCheck?"
Frequently Asked Questions
Do I need an API token?
Anonymous access allows 10 metadata analyses per day per IP. A free account with an API token has 100 checks per day. Use the token when analyzing if you want to retrieve the result through your account later.
Is the MCP server free to use?
Metadata analysis is available free: 10 checks per day per IP anonymously, or 100 checks per day with a free account token. Paid accounts use their plan allowances.
Are my PDF files stored on your servers?
The API does not retain the original checker upload after the request. Extracted metadata and result records are retained according to your account status and our Privacy Policy.
Does the MCP server send my files to a third party?
The PDF is sent to PDFCheck over HTTPS. Your MCP client or AI provider may also handle the file or tool arguments, depending on its design. Review its data policy and the PDFCheck Privacy Policy before sending sensitive documents.
What if my AI tool is not listed here?
Check whether your client supports remote HTTP MCP with bearer headers or can run a local stdio server using command and args. Configuration formats vary. OAuth-only remote connections are not supported by this setup.
What is the maximum PDF file size?
Free: up to 50 MB per PDF. Pro and AI: up to 100 MB per PDF.
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.