A comprehensive tool for managing citations and academic references that generates citations from DOI, arXiv, titles, or URLs in various formats (BibTeX, APA, MLA) with intelligent metadata enrichment.

Installation

PyPI

pip install onecite

Test MCP Server

onecite-mcp

Configuration

Claude Desktop

{
  "mcpServers": { "onecite": { "command": "onecite-mcp" } }
}

Cursor

{
  "mcpServers": { "onecite": { "command": "onecite-mcp" } }
}

Available Tools

Tool	Description
cite	Generates a single citation from DOI, arXiv ID, title, or URL
batch_cite	Processes a list of references in batch mode for multiple citations
search	Searches academic literature by keywords across various databases

Features

• Smart recognition with fuzzy matching across multiple academic databases
• Universal format support - input txt/bib files, output in BibTeX, APA, or MLA
• High-precision 4-stage processing pipeline (cleaning → querying → validation → formatting)
• Automatic enrichment of missing metadata such as journal, volume, pages, authors
• Support for 7+ citation types: journal articles, conference papers, books, software, datasets, dissertations, preprints
• Intelligent routing with automatic content type and field detection
• Support for universal identifiers: DOI, PMID, arXiv ID, ISBN, GitHub URL, Zenodo DOI, plain text
• Interactive mode for manual selection when multiple matches are detected
• Custom YAML templates for controlling output formatting
• Integration with 9+ data sources: CrossRef, Semantic Scholar, OpenAlex, PubMed, dblp, arXiv, DataCite, Zenodo, Google Books

Usage Examples

Generate an APA citation for DOI: 10.1038/nature14539

Batch process these references in BibTeX format

Search for papers on machine learning

Convert this list of mixed references to MLA format

Find and format citations for attention mechanisms research

Notes

OneCite processes mixed-format references from DOI, article titles, arXiv IDs, GitHub URLs, and plain text queries. It supports interactive refinement when multiple matches are detected and can be used both as a command-line tool and a Python library.