"PDF" matching MCP servers:

MCP server that indexes Markdown, Word, HTML, and PDF documents into a SQLite knowledge graph with CJK+Latin full-text search and cross-document reference tracking. Runs drift audits to surface stale policies, conflicting research claims, superseded ADRs, and undocumented code exports.

Go MCP server for multi-format document access — PDF, TXT, MD, DOCX, CSV, images. 12 tools including OCR, search, table extraction, and URL fetch. Single binary, no runtime.

Enables AI to search, filter, and process CNKI academic literature through natural language, including structured search, metadata retrieval, full-text reading, citation export, and PDF/CAJ download.

Enables LLMs to run web and academic searches across multiple engines (Baidu, Bing, DuckDuckGo, Tavily, Exa, Doubao and 9 scholarly sources) with local relevance scoring, deduplication and caching, plus SSRF-protected page fetching and PDF parsing, and works without any API key. It plugs into MCP clients like Claude Code, Cursor and Qwen Code, or can be embedded as a Go module.

MCP server for processing Markdown resumes into multiple formats (PDF, LinkedIn templates) with AI analysis and Claude integration.