Updated March 2026

Install PDF MCP

Pick your client, copy the command, done.

Run this in a terminal.

Run in terminal

claude mcp add pdf-mcp -- uvx --from git+https://github.com/I-CAN-hack/pdf-mcp.git pdf-mcp

Available Tools (5)

Once configured, PDF MCP gives your AI agent access to:

get_pdf_infoGet metadata about a PDF (page count, author, title, etc.)

filename

get_table_of_contentsGet the outline/bookmarks with page numbers for each section

filename

get_page_textExtract text from a page range in json, text, markdown, or html format.

filenamepage_rangeformatexclude_headers_footers

get_page_imageRender a single page as a PNG image, returned as base64 or written to a temp file.

filenamepage_numberdpi

search_textCase-insensitive text search across the entire PDF, returning page numbers and surrounding context

filenamequery

After setup, try these prompts with your AI agent:

→Extract the text from pages 5 to 10 of the document 'manual.pdf' in markdown format.

→Search for the term 'error code 404' in 'datasheet.pdf' and tell me which page it appears on.

→Get the table of contents for 'report.pdf' to understand the document structure.

→Render page 1 of 'diagram.pdf' as an image so I can analyze the technical drawing.

→What is the author and total page count of 'research_paper.pdf'?

Prerequisites & system requirements

An MCP-compatible client (Claude Code, Cursor, Windsurf, Claude Desktop, or Codex)
Python 3.8+ with pip installed

Alternative installation methods

codex mcp add pdf-mcp -- uvx --from git+https://github.com/I-CAN-hack/pdf-mcp.git pdf-mcp

Save the docs, env vars, and workflow around PDF MCP in Conare so Claude Code, Codex, and Cursor remember it next time.