Endnote MCP

EndNote MCP is a local tool that connects the EndNote literature library to Claude AI. It provides functions such as literature search, PDF reading, citation formatting, semantic search, and reference generation through the MCP protocol. All data is processed locally.

Research and data Knowledge management and memory #Literature management #AI assistant #Local search #Academic tool .Python

rating : 2.5 points

downloads : 3.7K

update time : 2026-03-12

Open Site

What is EndNote MCP?

EndNote MCP is a connection tool that allows you to access and manage your EndNote reference library through Claude AI. It connects your local EndNote library to the Claude desktop application via the Model Context Protocol (MCP), enabling you to directly query, cite, and manage academic literature in conversations.

How to use EndNote MCP?

Using EndNote MCP is very simple: First, export your library file in XML format from EndNote. Then, run the setup wizard for automatic configuration. Finally, restart the Claude desktop application to start using it. The whole process takes only a few minutes, and then you can directly ask questions about your reference library in Claude.

Use cases

EndNote MCP is particularly suitable for researchers, scholars, students, and anyone who needs to frequently consult and manage academic literature. When you are writing a paper, preparing a literature review, searching for related research, or need to quickly format citations, this tool can significantly improve your work efficiency.

Main features

Intelligent search

Provides multiple search methods: keyword search, full-text search (PDF content), and semantic search (based on meaning). Semantic search can understand the query intention and find relevant results even if the literature uses different terms.

Citation management

Supports multiple citation formats (APA 7th, Harvard, Vancouver, Chicago, IEEE) and can generate single citations or complete reference lists.

PDF access

Directly read specific pages from PDF attachments to help you quickly find and cite specific content in the literature.

BibTeX export

Export references in BibTeX format for easy use in LaTeX documents.

Related literature discovery

Find other papers related to specific literature based on AI embedding technology to help you discover related research.

Incremental indexing

After adding new literature, only the newly added content needs to be re-indexed, eliminating the need to rebuild the entire database and saving time.

Advantages

Completely local processing: All data is processed on your computer without uploading to the cloud

Seamless integration: Deeply integrated with the Claude desktop application for a natural and smooth user experience

Multiple search methods: Provides keyword, full-text, and semantic search to meet different needs

Fast and efficient: Extremely fast indexing and search speeds, maintaining good performance even when processing a large number of documents

Easy to use: The setup wizard simplifies the configuration process, and the command-line tool provides flexible control

Limitations

Requires EndNote 20+ version: Older versions of EndNote may not be compatible

Semantic search requires additional installation: A separate semantic search dependency package needs to be installed

Only supports Claude desktop: Currently only integrated with the Claude desktop application

PDF extraction depends on the file path: The PDF directory path needs to be correctly configured

How to use

Install EndNote MCP

Install EndNote MCP using pip or the uv package manager. It is recommended to use uv for better dependency management.

Export the library file from EndNote

Open EndNote, select 'File → Export', choose the XML format, and save the library file to a convenient location (such as the desktop).

Run the setup wizard

Run the setup wizard in the terminal. It will automatically detect your XML file and PDF directory and complete all configurations.

Restart the Claude desktop application

Quit and reopen the Claude desktop application. You will see 'EndNote Library' in the MCP connector.

Usage examples

Literature search and discovery

When you need to find literature on a specific topic, you can directly search your EndNote library in Claude.

Citation formatting

When writing a paper, you need to generate correctly formatted citations for the referenced literature.

Literature review preparation

When preparing a literature review, you need to find related literature and generate a reference list.

PDF content search

You need to find specific content or citations from downloaded PDFs.

Frequently Asked Questions

Is my data secure? Will it be uploaded to the cloud?

What should I do after adding new literature?

What's the difference between semantic search and ordinary search?

Why doesn't the EndNote tool appear in the Claude desktop?

Which citation formats are supported?

How is the performance when processing a large number of documents?

Related resources

GitHub repository

Source code, issue tracking, and latest updates

PyPI package page

Python package information and installation instructions

Model Context Protocol official website

Understand the technical details and specifications of the MCP protocol

EndNote official website

EndNote reference management software

Claude desktop application

Download the Claude desktop application

🚀 EndNote MCP

This tool connects your EndNote reference library to Claude AI. You can search references, read PDFs, format citations, find related papers, and generate bibliographies directly in Claude Desktop conversations.

🚀 Quick Start

1. Install

# With uv (recommended)
uv tool install endnote-mcp

# Or with pip
pip install endnote-mcp

2. Export your library from EndNote

In EndNote: File → Export → choose XML format → save to a convenient location (e.g., Desktop).

3. Run the setup wizard

endnote-mcp setup

The wizard will:

Auto-detect your XML export and PDF directory
Create the configuration
Index your library
Configure Claude Desktop automatically

4. Restart Claude Desktop

Quit and reopen Claude Desktop. You'll see "EndNote Library" in your MCP connectors.

That's it. Start asking Claude about your references.

✨ Features

What It Does

Once set up, you can ask Claude things like:

"Search my library for social capital and Bourdieu"
"Find papers about how organisations deal with uncertainty" (semantic search)
"Find references related to paper #3844"
"Give me the APA citation for reference #1234"
"Generate a bibliography for references 12, 45, 78, 102"
"Export references 12, 45, 78 as BibTeX"
"Read pages 5 - 7 from that Smith et al. paper"

Claude searches your local library — nothing is uploaded to the cloud beyond the normal conversation.

How It Works

EndNote Library → XML Export → endnote-mcp index → SQLite Database (FTS5 + Embeddings)
                                                          ↕
                                   Claude Desktop ← MCP Server (12 tools)

Your references and PDF text are indexed into a local SQLite database with full-text search. Optionally, AI embeddings enable semantic search — finding papers by meaning, not just keywords. When semantic dependencies are installed, new references are automatically embedded during indexing. Claude connects through the Model Context Protocol (MCP).

📦 Installation

Requirements

EndNote 20+ (any edition)
Claude Desktop app
Python 3.10+
uv (recommended) or pip

💻 Usage Examples

Semantic Search (Optional)

Enable meaning-based search that finds references even when they use different terminology than your query. For example, searching "how companies prepare for uncertain futures" finds papers on scenario planning and strategic foresight.

# Install semantic search dependencies
pip install endnote-mcp[semantic]

# Generate embeddings (~3 min for 4,000 references)
endnote-mcp embed

This uses the lightweight all-MiniLM-L6-v2 model locally — no API keys needed, everything stays on your machine.

📚 Documentation

Commands

Command	What It Does
`endnote-mcp setup`	Interactive setup wizard
`endnote-mcp index`	Re-index after adding new references (incremental)
`endnote-mcp index --full`	Full re-index from scratch
`endnote-mcp index --skip-pdfs`	Index metadata only (fast, ~1 sec)
`endnote-mcp index --embed`	Re-index and generate embeddings
`endnote-mcp embed`	Generate semantic search embeddings
`endnote-mcp embed --full`	Regenerate all embeddings from scratch
`endnote-mcp status`	Show index statistics
`endnote-mcp install`	Add to Claude Desktop config
`endnote-mcp serve`	Start MCP server (used by Claude Desktop automatically)

Tools Available to Claude

Tool	Description
`search_references`	Search by author, title, year, keywords, abstract (BM25 ranked, with DOI links)
`search_fulltext`	Search inside PDF content — find concepts, quotes, methods
`search_library`	Combined metadata + PDF search in one call
`search_semantic`	Search by meaning using AI embeddings (requires `endnote-mcp[semantic]`)
`get_reference_details`	Full metadata for a reference (abstract, keywords, DOI, etc.)
`get_citation`	Format as APA 7th, Harvard, Vancouver, Chicago, or IEEE
`get_bibtex`	Export references as BibTeX entries for LaTeX
`get_bibliography`	Generate a formatted bibliography for multiple references
`find_related`	Find similar references (uses embeddings when available)
`read_pdf_section`	Read specific pages from a PDF attachment
`list_references_by_topic`	Broad topic-based listing
`rebuild_index`	Re-index after updating your EndNote library

Adding New References

When you add new references to your EndNote library:

Re-export XML from EndNote (overwrite the same file)
Either:
- Run endnote-mcp index from a terminal, or
- Ask Claude: "Rebuild my library index"

Indexing is incremental — it only processes new references and PDFs, not the entire library again. If semantic search is installed, new references are automatically embedded.

Performance

Operation	Time (4,000 references)
Metadata indexing	~1 second
PDF extraction (first time)	~1 min per 100 PDFs
PDF extraction (incremental)	Only new PDFs
Embedding generation	~3 minutes
Keyword search	< 50 ms
Semantic search	< 200 ms

Configuration

Config is stored at:

macOS: ~/Library/Application Support/endnote-mcp/config.yaml
Windows: %APPDATA%/endnote-mcp/config.yaml
Linux: ~/.config/endnote-mcp/config.yaml

endnote_xml: /path/to/your/library.xml
pdf_dir: /path/to/your/Library.Data/PDF
db_path: /path/to/library.db    # auto-set by setup
max_pdf_pages: 30                # max pages per read request

Citation Styles

Five built-in styles:

APA 7th — get_citation(rec_number=42, style="apa7")
Harvard — style="harvard"
Vancouver — style="vancouver"
Chicago (Author-Date, 17th ed.) — style="chicago"
IEEE — style="ieee"

Use get_bibliography to format multiple references at once, sorted by author or year.

BibTeX Export

Export references as BibTeX entries for use in LaTeX:

Ask Claude: "Export references 42 and 100 as BibTeX"
Or use the get_bibtex tool directly with comma-separated record numbers

Generates complete entries with proper entry types (@article, @book, @inproceedings, etc.), cite keys, and all available fields.

Troubleshooting

"No configuration found" — Run endnote-mcp setup

"XML file not found" — Re-export from EndNote: File → Export → XML format

"PDF not found" — Check that pdf_dir in your config points to the correct .Data/PDF directory

Search returns no results — Run endnote-mcp index to rebuild the database

Claude Desktop doesn't show the tool — Run endnote-mcp install, then restart Claude Desktop

"Semantic search is not available" — Run pip install endnote-mcp[semantic] then endnote-mcp embed

Citing This Software

If you use this tool in your research, please cite it:

Gokmen, G. (2026). EndNote MCP: Connecting EndNote Reference Libraries to Claude AI (Version 1.4.5) [Computer software]. https://doi.org/10.5281/zenodo.18617546

Or use the "Cite this repository" button on GitHub for BibTeX/APA formats.