juergenkoller-software/pdf-content-search-mcp

Overview

An open-source MCP server that enables full-text search and OCR-based search across thousands of PDF documents. It integrates with Claude and Cursor to provide a bridge for querying PDF content programmatically.

Best for

Best for
Developers needing to add PDF search capabilities to AI-driven applications

Use cases

• Searching large PDF libraries for specific text or phrases
• Extracting searchable content from scanned documents via OCR
• Integrating PDF search capabilities into AI assistant workflows

How to use

Tools exposed

• PDF_CS_TOKEN
• PDF_CS_PORT
• PDF_CS_HOST

Tested with

Claude Desktop, Claude Code, Cursor

Example client config

{\n  "mcpServers": {\n    "pdf-content-search": {\n      "command": "/path/to/pdf-content-search-mcp",\n      "env": {\n        "PDF_CS_TOKEN": "your-token-here",\n        "PDF_CS_PORT": "44477"\n      }\n    }\n  }\n}

Notes

An open-source MCP server that enables full-text search and OCR-based search across thousands of PDF documents. It integrates with Claude and Cursor to provide a bridge for querying PDF content programmatically.

0 stars on GitHub. Last updated 2026-06-08. Licensed MIT.

Use cases

• Searching large PDF libraries for specific text or phrases
• Extracting searchable content from scanned documents via OCR
• Integrating PDF search capabilities into AI assistant workflows

Pros

• Supports both text and OCR-based search for comprehensive coverage
• Open-source and free to use with no vendor lock-in
• Works with popular AI tools like Claude and Cursor

Cons

• Written in Swift, limiting cross-platform compatibility
• No GitHub stars yet, indicating limited community adoption or testing
• Requires setup of an MCP server, adding deployment complexity

Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.