PDF Reader
The Pdf Reader Mcp server provides production-ready PDF processing capabilities for AI agents, enabling extraction of text, images, and metadata from PDF files. It delivers 5-10x faster parallel page processing compared to sequential approaches, implements Y-coordinate-based content ordering to preserve document layout, and offers flexible path handling for both absolute and relative file references across Windows and Unix systems. The server solves the performance and reliability challenges of traditional PDF processing through automatic parallelization, per-page error resilience, and comprehensive type safety with 94%+ test coverage.
- GitHub stars
- 711
- tools
- 4
- last updated
- Dec 15, 2025
Tools
4 toolsPublic tool metadata for what this MCP can expose to an agent.
outlineNavigate a heading tree, with node ids and unit/Markdown ranges
Navigate a heading tree, with node ids and unit/Markdown ranges
No parameter schema in public metadata yet.
readTurn a file, URL, or folder into Markdown
Turn a file, URL, or folder into Markdown
No parameter schema in public metadata yet.
searchFind text across files, folders, and URLs
Find text across files, folders, and URLs
No parameter schema in public metadata yet.
inspectGo deeper on a PDF
Go deeper on a PDF
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageReadme
anymd
PDF, Word, PowerPoint, Excel, EPUB, HTML and web pages, images (OCR), audio and video (metadata, subtitles, transcripts). A fast Rust MCP server and CLI that runs on your machine. No API key.
anymd is the free, local mode of the same crates that run Sylphx AI parse, the hosted document-parse service: the same crates, hosted and metered per page for callers that want no local runtime.
Details
- Repository
- github.com/sylphlab/pdf-reader-mcp
- Categories
- Documents & Knowledge, Search & Web Crawling
Related Documents & Knowledge MCP servers
View all
Obsidian Claude Codeiansinnott/obsidian-claude-code-mcpProvides a dual-transport MCP server for Claude Code and Claude Desktop to read and write your Obsidian vault via MCP.287stars
MCP LogSeq Serverergut/mcp-logseqMCP server to interact with LogSeq via its Local HTTP API - enabling AI assistants like Claude to seamlessly read, write, and manage your LogSeq graph.267stars
Zotero MCPkujenga/zotero-mcpSearch your Zotero library, retrieve item metadata, and read full text from AI assistants.162stars
Markdown Vault MCPpvliesdonk/markdown-vault-mcpGeneric markdown vault MCP with hybrid search38stars