Pdf Reader
@sunderbharath85
About Pdf Reader
An MCP server that can extract text from PDFs and images. It supports:
Basic information
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"pdf-reader-mcp": {
"command": "node",
"args": [
"dist/index.js"
],
"env": {}
}
}
}Tools
No tools detected
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
What is Pdf Reader?
Pdf Reader is an MCP server that extracts text from PDFs and images. It supports native text extraction from PDFs with embedded text and OCR for scanned PDFs and images using Tesseract.
How to use Pdf Reader?
—
Key features of Pdf Reader
- Native text extraction from PDFs with embedded text
- OCR for scanned PDFs and images via Tesseract
- Optional Poppler for faster PDF conversion
- Falls back to
tesseract.jsif Tesseract CLI is absent - Cross‑platform (macOS, Windows, Linux)
Use cases of Pdf Reader
- Extracting text from digital PDFs
- Performing OCR on scanned PDFs or document images
- Automating document processing in a server environment
FAQ from Pdf Reader
What are the runtime requirements?
Node.js >= 18.18 is required. For best OCR on PDFs, Poppler and Tesseract CLI are recommended.
How do I install Poppler and Tesseract?
Instructions differ by OS: use Homebrew on macOS, Chocolatey or manual install on Windows, and apt-get on Ubuntu/Debian.
What happens if Poppler is not installed?
The server falls back to slower whole‑file OCR instead of using pdftoppm.
What happens if Tesseract CLI is not installed?
The server falls back to tesseract.js, which downloads language data on first use.
Which platforms are supported?
macOS, Windows, and Linux (Ubuntu/Debian instructions provided).
More Files & Storage MCP servers
Filesystem MCP Server (@shtse8/filesystem-mcp)
shtse8📁 Secure, efficient MCP filesystem server - token-saving batch operations with project root confinement
Storacha MCP Storage Server
storachaStoracha MCP storage server - self-sovereign data for your AI applications.

Google Drive
modelcontextprotocolModel Context Protocol Servers
PDF Reader MCP Server (@shtse8/pdf-reader-mcp)
shtse8📄 The PDF intelligence layer for AI agents — Agent Document Twin, evidence-first extraction, visual crops, OCR provenance, trust reports, and benchmark-gated releases. MCP server for Claude, Cursor, VS Code, and any MCP client.
md-pdf-mcp (Markdown to PDF MCP Server)
seanivoreMarkdown To PDF Conversion MCP
Comments