All-in-one MCP server for academic paper processing: OCR, metadata, structure extraction, translation, summary, arXiv, and Zotero.
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"fro-wang-academic-tools-mcp","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
# fro-wang-academic-tools-mcp `fro-wang-academic-tools-mcp` is an MCP server for academic paper workflows, built on FastMCP. It combines OCR, metadata extraction/enrichment, section parsing, translation, summary generation, arXiv tools, and Zotero integration. Detailed system design is documented in `docs/README_SYSTEM.md`. ## Motivation This project is dedicated to managing academic papers locally to empower AI Agents. While AI Agents excel at local tasks, they struggle with the dominant format of academic literature: PDFs. When you are conducting literature reviews, reading, or searching for papers, most of your local library consists of PDF files. Local coding agents prefer plain text. They rely on tools like `grep` or semantic search to navigate local files. These tools cannot natively search inside PDFs, making it difficult for agents to assist with literature management effectively. Having frequently encountered this bottleneck, I built `fro-wang-academic-tools-mcp` to bridge the gap. These tools extract the core workflow from my website, [frowang.com](https://frowang.com), converting PDFs into agent-friendly formats (like Markdown) and enriching them with metadata. ## Features - End-to-end paper pipeline via `process_paper` - OCR with MinerU (`ocr_paper`) - Metadata extraction + enrichment (`extract_metadata`) - Section structure extraction (`extract_sections`) - Markdown translation (`translate_paper`) - Summary report generation (`generate_summary`) - Folder rename by metadata convention (`rename_paper_folder`) - arXiv search/download tools - Zotero local read-only library tools (search, notes, collections, attachments, annotations) ## Tool Groups This server currently registers 25 MCP tools: - Paper processing: `ocr_paper`, `extract_metadata`, `extract_sections`, `translate_paper`, `generate_summary`, `rename_paper_folder` - Pipeline: `process_paper`, `start_process_paper_job`, `get_process_paper_job`, `cancel_process_paper_job`, `batch_process…
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.