zotero-translator-mcp-server
Enables the extraction of bibliographic metadata from ACM Digital Library URLs using the Zotero translation engine.
Allows looking up and resolving bibliographic metadata for research papers using arXiv identifiers.
Supports the resolution and extraction of scholarly metadata from Digital Object Identifiers (DOIs).
Provides the capability to export extracted bibliographic metadata into Evernote-compatible formats.
Enables the conversion of bibliographic metadata into BibTeX and BibLaTeX formats commonly used in LaTeX-based academic workflows.
Allows for the generation of bibliographic citations in formats suitable for inclusion in Wikipedia articles.
Supports exporting bibliographic metadata in various XML formats, including EndNote XML and MODS.
Wraps the Zotero Translation Server to provide comprehensive tools for extracting, importing, and exporting bibliographic metadata across numerous web services and identifiers.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@zotero-translator-mcp-serverget bibliographic info for DOI 10.1145/3613904.3642743"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
zotero-translator-mcp-server
An MCP (Model Context Protocol) server that wraps the Zotero Translation Server, enabling LLMs and AI agents to extract bibliographic metadata from URLs, DOIs, ISBNs, and other identifiers.
Uses the same translation engine as the Zotero browser connector — no Zotero desktop client required.
Prerequisites
A running Zotero Translation Server instance.
Quick start with Docker
docker pull zotero/translation-server
docker run -d -p 1969:1969 --rm --name translation-server zotero/translation-serverOr from source
git clone --recurse-submodules https://github.com/zotero/translation-server.git
cd translation-server
npm install
npm startInstallation
Claude Code
claude mcp add --transport stdio --scope user zotero-translator -- npx -y zotero-translator-mcp-serverClaude Desktop / VS Code / other MCP clients
Add to your MCP configuration:
{
"mcpServers": {
"zotero-translator": {
"command": "npx",
"args": ["-y", "zotero-translator-mcp-server"],
"env": {
"ZOTERO_TRANSLATION_SERVER_URL": "http://localhost:1969"
}
}
}
}Tools
zotero_translate_url
Extract bibliographic metadata from a webpage URL using Zotero's translation engine.
Input: { "url": "https://dl.acm.org/doi/10.1145/3613904.3642743" }
Output: Zotero JSON array with title, authors, DOI, abstract, etc.zotero_search_identifier
Look up metadata by DOI, ISBN, PMID, or arXiv ID.
Input: { "identifier": "10.1145/3613904.3642743" }
Output: Zotero JSON array with resolved metadatazotero_export_bibliography
Convert Zotero JSON to BibTeX, RIS, CSL-JSON, and 13 other formats.
Input: { "items": "[...]", "format": "bibtex" }
Output: Formatted BibTeX stringSupported formats: bibtex, biblatex, bookmarks, coins, csljson, csv, endnote_xml, evernote, mods, rdf_bibliontology, rdf_dc, rdf_zotero, refer, ris, tei, wikipedia
zotero_import_bibliography
Convert BibTeX, RIS, or other formats to Zotero JSON.
Input: { "data": "@article{seo2024, title={...}, ...}" }
Output: Zotero JSON arrayConfiguration
Environment Variable | Default | Description |
|
| URL of the translation server |
License
AGPL-3.0-only — same license as the Zotero Translation Server it wraps.
Acknowledgments
This project wraps the Zotero Translation Server by the Corporation for Digital Scholarship.
Related MCP Connectors
Zotero MCP server for Claude and ChatGPT: search, citations, safe writes, PDF passages and pages.
Reliable PDF table extraction. Pass a URL, get structured JSON tables with citations.
Catch AI-fabricated citations (real DOI + fake title). Retraction, open-access, 10,000+ CSL styles.
Federated search of books and papers, BibTeX/RIS citations, open-access retrieval and reading.
