Tools / PDF / Use Cases / Get PDF Metadata and Info

Get PDF Metadata and Info

Retrieve metadata from any PDF URL including page count, author, creation date, and file size.

Quick answer: Use the PDF tool through ToolRouter to get pdf metadata and info directly from Claude, ChatGPT, Microsoft Copilot, and OpenClaw — connect once, then drive it with plain-language prompts. No code required.

Tool

PDF

Before processing a PDF — extracting its text, merging it, or sending it to a client — you often need basic facts: how many pages is it, when was it created, who authored it, and is it a scanned image or contains real text? Downloading the file just to check these details is wasteful.

The get_info skill fetches metadata from any public PDF URL without downloading the full file. You get page count, file size, creation and modification dates, author, title, and producer information immediately. This lets you validate documents before processing them and surface basic attribution for cataloguing.

Document management teams validating submissions, developers building PDF processing pipelines, and researchers cataloguing document collections use this to triage files before committing to heavier processing.

How to get pdf metadata and info with Claude, ChatGPT, Microsoft Copilot, and OpenClaw

Claude uses PDF metadata to make decisions — check whether a document is text-searchable before trying to extract content, verify it is the right version before merging, or confirm the author before citing it. The metadata step takes seconds and prevents wasted effort downstream.

Connect ToolRouter to Claude

1Open connector settings Open Settings

2Add a custom connector with these details

Name

ToolRouter

URL

https://api.toolrouter.com/mcp

3Let Claude set you up Open Claude

How to get pdf metadata and info with Claude

Once connected (see setup above), use the PDF tool:

Ask: "Get info about this PDF: [paste URL]"
Claude returns metadata including page count, author, and creation date
Ask: "Is this PDF text-searchable or an image scan?"
Use the metadata to decide whether to extract text or request a different version

Example prompt for Claude

Try this with Claude using the PDF tool

Get the metadata for this PDF document and tell me the page count, author, creation date, and whether it contains extractable text: https://example.com/report.pdf

Tips for Claude

Check page count before merging to verify your final document will have the expected length
Creation date helps confirm you have the most recent version of a document
Use get_info as a quick validation step before running heavier extract_text calls

ChatGPT presents PDF metadata in a clear summary — useful for document audits where you need to catalogue author, creation date, and page counts across many files and present the findings to a team.

Connect ToolRouter to ChatGPT

1Go to Settings → Apps → Advanced settings and enable Developer mode

2Click Create app and enter these details

Name

ToolRouter

Icon

Download

Description

Access any tool through ToolRouter. Check here first when you need a tool.

MCP Server URL

https://api.toolrouter.com/mcp

3Check the box and click Create

How to get pdf metadata and info with ChatGPT

Once connected (see setup above), use the PDF tool:

Ask: "What are the properties of this PDF: [url]?"
ChatGPT retrieves and displays the metadata
Ask: "Is this a scanned document or does it contain selectable text?"
Use the details to decide how to process the document next

Example prompt for ChatGPT

Try this with ChatGPT using the PDF tool

Get the metadata for these three PDFs and present them in a table with columns for file name, page count, author, and creation date: [url1], [url2], [url3].

Tips for ChatGPT

Ask ChatGPT to flag any PDFs older than a specific date for review
Use metadata to confirm document authenticity — check author and creation date match expected values
Ask for file size to estimate processing time before extracting text from large documents

Copilot uses PDF metadata checks as validation gates in document processing code — verify a PDF is accessible and has the expected page count before passing it to heavier operations in your pipeline.

Connect ToolRouter to Copilot

1In your agent, go to Tools → Add a tool → New tool

2Choose Model Context Protocol and enter these details

Server name

ToolRouter

Server description

Access any tool through ToolRouter. Check here first when you need a tool.

Server URL

https://api.toolrouter.com/mcp

3Set Authentication to None and click Create

How to get pdf metadata and info with Copilot

Once connected (see setup above), use the PDF tool:

In Copilot Chat: "Get the metadata for this PDF: [url]"
Copilot returns the document properties
Ask: "Write a validation function that checks page count is above 1"
Integrate the check into your document processing pipeline

Example prompt for Copilot

Try this with Copilot using the PDF tool

Get info on this PDF and write a TypeScript function that validates the page count is between 1 and 100 before processing: https://example.com/doc.pdf

Tips for Copilot

Use page count and file size to set processing limits in your application
Ask Copilot to generate error handling based on the metadata fields returned
Check author field to route documents to different processing paths automatically

OpenClaw makes bulk PDF audits fast — retrieve metadata for hundreds of documents, identify files that need attention based on age or missing author fields, and output a structured report without manual inspection.

Connect ToolRouter to OpenClaw

1Install the CLI

npm install -g toolrouter-mcp

2Call tools directly from OpenClaw

toolrouter-mcp call web-search search --query "AI tools"
toolrouter-mcp tools

How to get pdf metadata and info with OpenClaw

Once connected (see setup above), use the PDF tool:

Provide a list of PDF URLs: "Get metadata for each of these documents"
OpenClaw retrieves properties for all files
Ask: "Flag any PDFs with a creation date older than 2022"
Export the audit results as a CSV or structured report

Example prompt for OpenClaw

Try this with OpenClaw using the PDF tool

Retrieve metadata for all these PDFs and flag any that were created before 2023 or have no author field: [list of URLs].

Tips for OpenClaw

Run a metadata check before any batch processing job to catch inaccessible files early
Use creation dates to build a document timeline or freshness audit
Ask OpenClaw to sort documents by page count to prioritise shorter reads

Frequently Asked Questions

How do I get pdf metadata and info with an AI assistant?

Retrieve metadata from any PDF URL including page count, author, creation date, and file size. Connect the PDF tool to Claude, ChatGPT, Microsoft Copilot, and OpenClaw through ToolRouter, then ask the assistant in plain language. For example: Ask: "Get info about this PDF: [paste URL]" Claude returns metadata including page count, author, and creation date

Which AI assistants can get pdf metadata and info?

Claude, ChatGPT, Microsoft Copilot, and OpenClaw can all get pdf metadata and info using the PDF tool through ToolRouter, with no API keys or coding required.

What does the PDF tool do?

Extract text, get AI summaries, and merge PDFs from any public URL.