Overview
OneCite provides complete Model Context Protocol (MCP) support, enabling AI assistants to directly use its functionality for literature search, processing, and formatting. The MCP integration exposes three core operations: cite (generate a single formatted citation), batch_cite (process a list of references), and search (query academic databases by keywords). Installation includes pip install onecite and running onecite-mcp to start the MCP server. The README describes configuration steps for Claude Desktop and Cursor editors, showing how to register the MCP server under onecite with a command, and how to wire it into editors for seamless interaction. Once running, the MCP server can automatically recognize entry types, fetch metadata from multiple sources (CrossRef, Semantic Scholar, OpenAlex, PubMed, dblp, arXiv, DataCite, Zenodo, Google Books), and output citations in BibTeX, APA, or MLA formats. The tool emphasizes interactive disambiguation, metadata auto-completion (journal, volume, pages, authors), and flexible templates to control final formatting via YAML. This MCP capability enables AI-powered workflows to search, refine, and format references in a scalable, repeatable way.
Features
Smart Recognition
Fuzzy matching against multiple academic databases to find references from incomplete or inaccurate info.
Universal Formats
Input .txt/.bib → Output BibTeX, APA, or MLA formats with ease.
High-Accuracy Pipeline
A 4-stage process (clean → query → validate → format) ensures the highest quality output.
Auto-Completion
Automatically enriches entries by filling in missing data like journal, volume, pages, and authors.
7+ Citation Types
Handles journal articles, conference papers, books, software, datasets, theses, and preprints.
Intelligent Routing
Auto-detects content type and domain (Medical/CS/General) for optimal data retrieval.
Universal Identifiers
Accepts DOI, PMID, arXiv ID, ISBN, GitHub URL, Zenodo DOI, or even plain text queries.
Interactive Mode
Manually select the correct entry when multiple potential matches are found.
Who Is This For?
- AI assistants:Directs AI assistants to perform search, processing, and formatting tasks for literature.
- Developers integrating citation tools into editors:Embed MCP endpoints to power automated citation workflows in editors.
- Researchers and scholars:Automate and streamline bibliography generation and citation formatting for papers.
