pdf-mcp and pdf-reader-mcp

These are **competitors** offering overlapping PDF processing capabilities for MCP agents, with the former emphasizing raw performance through parallelization while the latter prioritizes practical usability through intelligent caching and higher adoption (1,574 vs. 0 monthly downloads).

pdf-mcp
52
Established
pdf-reader-mcp
49
Emerging
Maintenance 13/25
Adoption 12/25
Maturity 18/25
Community 9/25
Maintenance 13/25
Adoption 10/25
Maturity 9/25
Community 17/25
Stars: 7
Forks: 1
Downloads: 1,820
Commits (30d): 0
Language: Python
License: MIT
Stars: 547
Forks: 57
Downloads:
Commits (30d): 2
Language: TypeScript
License: MIT
No risk flags
No Package No Dependents

About pdf-mcp

jztan/pdf-mcp

Production-ready MCP server for PDF processing with intelligent caching. Extract text, search, and analyze PDFs with AI agents.

Implements full-text search with BM25 relevance ranking via SQLite FTS5, and extracts tables as structured data (headers + rows) detected from visible borders. Designed for Claude Desktop, Claude Code, VS Code Copilot, and other MCP clients—includes 7 specialized tools for paginated reading, metadata lookup, image extraction, and cache management to optimize token usage on large documents.

About pdf-reader-mcp

SylphxAI/pdf-reader-mcp

📄 Production-ready MCP server for PDF processing - 5-10x faster with parallel processing and 94%+ test coverage

Implements Model Context Protocol server using stdio transport with automatic error recovery per-page, enabling seamless integration with Claude, VS Code, and Cursor. Features Y-coordinate-based content ordering to preserve natural document layout and supports both local file paths (absolute/relative) and HTTP(S) URLs for batch processing. Built with TypeScript and optimized for low-latency operations through multi-core parallelization.

Scores updated daily from GitHub, PyPI, and npm data. How scores work