bib-enrich-mcp

Writing a paper and your .bib file is a mess? This tool lets AI automatically complete your citations — fill in missing metadata, find publication venues, add DOIs, and even discover if a preprint has been formally published.

Features

• Automatic metadata scraping from multiple sources:
  • arXiv API
  • DBLP API
  • CrossRef API
• BibTeX parsing and writing with full field support
• Batch processing of entire .bib files
• MCP integration for use with AI assistants

Installation

# Or install with uv (Recommended)
uv tool install bib-enrich-mcp

# Install from PyPI
pip install bib-enrich-mcp

# Or clone and install locally
git clone https://github.com/haoxiangsnr/bib-enrich-mcp.git
cd bib-enrich-mcp
uv sync

Quick Start

Step 1: Configure MCP Client

Add the server to your MCP client (e.g., Cherry Studio, Claude Desktop, Cursor):

{
  "mcpServers": {
    "bib-enrich": {
      "command": "bib-enrich-mcp"
    }
  }
}

Step 2: Enable the MCP Server

In your MCP client, enable the bib-enrich server. Look for a tools icon (usually a wrench) in the chat interface.

Step 3: Start Using

Now you can ask the AI to help with your bibliography. Example prompts:

Help me find the complete citation for: Attention Is All You Need

Enrich this BibTeX entry with arXiv ID 2401.12345

Process my references.bib file and fill in missing metadata

The AI will automatically call the appropriate tools to fetch metadata from arXiv, DBLP, and CrossRef.

Usage

As an MCP Server

Add to your MCP client configuration:

{
  "mcpServers": {
    "bib-enrich": {
      "command": "bib-enrich-mcp"
    }
  }
}

Running the Server

bib-enrich-mcp

API Documentation

MCP Tools

mcp_enrich_bib_entry

Enrich a single bibliography entry by scraping metadata from academic sources.

Parameters:

• cite_key (required): The citation key for the entry
• title (optional): Paper title to search for
• arxiv_id (optional): arXiv ID (e.g., "2401.12345")
• doi (optional): DOI of the paper

Returns: BibTeX string with enriched metadata

Example:

result = await mcp_enrich_bib_entry(
    cite_key="vaswani2017attention",
    title="Attention Is All You Need"
)

mcp_enrich_bib_file

Enrich all entries in a BibTeX file.

Parameters:

• file_path (required): Path to the .bib file

Returns: Summary of enriched entries

Example:

result = await mcp_enrich_bib_file("/path/to/references.bib")
# Returns: "Enriched 5/10 entries in /path/to/references.bib"

Python API

You can also use the library directly in Python:

from bib_enrich_mcp.bib_parser import parse_bib_file, write_bib_file
from bib_enrich_mcp.scrapers import scrape_metadata

# Parse a bib file
entries = parse_bib_file("references.bib")

# Scrape metadata for a paper
results = await scrape_metadata(
    title="Attention Is All You Need",
    arxiv_id="1706.03762"
)

Supported Metadata Sources

Source	Search by Title	Search by ID	Notes
arXiv	✅	✅ (arXiv ID)	Best for preprints
DBLP	✅	❌	Best for CS conferences
CrossRef	✅	✅ (DOI)	Best for journals

Development

Running Tests

uv run pytest tests/ -v

Project Structure

bib-enrich-mcp/
├── src/bib_enrich_mcp/
│   ├── __init__.py
│   ├── bib_parser.py    # BibTeX parsing/writing
│   ├── scrapers.py      # Metadata scrapers
│   └── server.py        # MCP server
├── tests/
│   ├── test_bib_parser.py
│   ├── test_scrapers.py
│   └── test_server.py
├── pyproject.toml
└── README.md

License

MIT