README.md

May 12, 2026 · View on GitHub

DOI Citation Verifier MCP Server

A Model Context Protocol (MCP) server that prevents citation hallucination by verifying academic citations against 9 authoritative databases. This server enables AI assistants to verify every citation against real publications before citing them.

🚀 Quick Install

npx -y github:tfscharff/doi-mcp

Or add to your Claude Desktop config:

{
  "mcpServers": {
    "doi-mcp": {
      "command": "npx",
      "args": ["-y", "github:tfscharff/doi-mcp"]
    }
  }
}

The Problem This Solves

Large language models sometimes "hallucinate" academic citations - citing papers that don't exist, misattributing real titles to wrong authors, or mixing up publication details. This MCP server eliminates that problem by:

9-database verification: Checks citations across CrossRef, OpenAlex, PubMed, zbMATH, ERIC, HAL, INSPIRE-HEP, Semantic Scholar, and DBLP
Parallel search: Queries all databases simultaneously for fast results (~1 second)
Comprehensive coverage: 600+ million publications across all disciplines including STEM, humanities, social sciences, and education
DOI-backed citations: Every verified citation includes a valid, clickable DOI

Features

9 Database Search: CrossRef, OpenAlex, PubMed, zbMATH, ERIC, HAL, INSPIRE-HEP, Semantic Scholar, DBLP
Verify Citations: Check if a paper with specific details actually exists across all databases
Find Verified Papers: Search for real papers on a topic and get only verified citations
Parallel Processing: All database queries run simultaneously for maximum speed
LRU Caching: Repeated queries return instantly (5-minute TTL)
Early Exit: High-confidence matches (score ≥8) return immediately without waiting for all databases
Source Selection: Search all databases or target specific sources
Citation Formatting: Returns properly formatted citations with DOIs
Zero Configuration: All databases work out-of-the-box with no API keys required
Fully Tested: 41 tests covering scoring, caching, database adapters, and tool integration

How It Works

When an AI assistant is asked about research or for citations:

Without this MCP: The assistant might cite "According to Smith et al. (2023) in Nature..." referencing a paper that doesn't exist
With this MCP: The assistant uses verifyCitation first, which searches across 9 databases in parallel and returns:
- Verified match with full DOI → Can be cited
- No match found → Cannot cite; must search for real papers instead

Tools

verifyCitation

Primary anti-hallucination tool - Verifies a citation exists across multiple databases before it can be mentioned.

Input:

title (string, optional): Paper title (partial matches accepted)
authors (array, optional): Author names (last names sufficient)
year (number, optional): Publication year
doi (string, optional): DOI if known
journal (string, optional): Journal name

Returns JSON with:

verified: true/false
If verified=true: DOI, title, authors, year, journal, URL, source database
If verified=false: Warning message that no matching publication was found
Match quality indicators for transparency

Example successful verification:

{
  "verified": true,
  "doi": "10.1038/s41586-023-06004-9",
  "title": "Accurate structure prediction of biomolecular interactions...",
  "authors": ["John Jumper", "Richard Evans", "..."],
  "year": 2023,
  "journal": "Nature",
  "url": "https://doi.org/10.1038/s41586-023-06004-9",
  "source": "crossref",
  "message": "✓ Citation verified"
}

findVerifiedPapers

Search for real papers on a topic and return only verified citations with DOIs from multiple databases.

Input:

query (string): Search query (topic, keywords, author names)
source (string, optional): Which database to search - "all" (default), "crossref", "openalex", "pubmed", "zbmath", "eric", "hal", "inspirehep", "semanticscholar", or "dblp"
limit (number, optional): Number of results per source (1-20, default: 5)
yearFrom (number, optional): Minimum publication year
yearTo (number, optional): Maximum publication year

Returns: Array of verified papers from the specified database(s) with complete citation information including source

Example:

// Search all 9 databases
findVerifiedPapers({ query: "CRISPR gene editing", limit: 5 })

// Search only PubMed for biomedical papers
findVerifiedPapers({ query: "cancer immunotherapy", source: "pubmed", limit: 10 })

// Search zbMATH for mathematics papers
findVerifiedPapers({ query: "algebraic topology", source: "zbmath" })

// Search DBLP for computer science papers
findVerifiedPapers({ query: "neural networks", source: "dblp", yearFrom: 2020 })

// Search ERIC for education research
findVerifiedPapers({ query: "active learning pedagogy", source: "eric" })

// Search HAL for French/European humanities research
findVerifiedPapers({ query: "phenomenology Husserl", source: "hal" })

// Search INSPIRE-HEP for high-energy physics papers
findVerifiedPapers({ query: "Higgs boson", source: "inspirehep" })

Installation

Add to your Claude Desktop config file:

Windows: %APPDATA%\Claude\claude_desktop_config.json macOS: ~/Library/Application Support/Claude/claude_desktop_config.json Linux: ~/.config/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "doi-mcp": {
      "command": "npx",
      "args": ["-y", "github:tfscharff/doi-mcp"]
    }
  }
}

Restart Claude Desktop and the server will be available.

Alternative: Global Install

npm install -g github:tfscharff/doi-mcp

Then use this config:

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

Alternative: Clone Locally

git clone https://github.com/tfscharff/doi-mcp.git
cd doi-mcp
npm install
npm run build

Config for local install:

{
  "mcpServers": {
    "doi-mcp": {
      "command": "node",
      "args": ["/absolute/path/to/doi-mcp/dist/index.js"]
    }
  }
}

Troubleshooting

Server not connecting

Check Node.js is installed: node --version (requires v18+)
Check Claude Desktop logs:
- Windows: %APPDATA%\Claude\logs\
- macOS: ~/Library/Logs/Claude/
- Linux: ~/.config/Claude/logs/

npx command fails

npm cache clean --force

Testing locally

npx @modelcontextprotocol/inspector node dist/index.js

Development

# Install dependencies
npm install

# Build
npm run build

# Development with watch mode
npm run dev

# Run tests
npm test

# Run tests in watch mode
npm run test:watch

# Run tests with coverage
npm run test:coverage

Architecture

Version 4.0 uses a modular architecture for maintainability and testability:

src/
├── index.ts              # Entry point
├── server.ts             # MCP server setup
├── types.ts              # Shared interfaces
├── scoring.ts            # Match scoring algorithm
├── cache.ts              # LRU cache (5-min TTL)
├── http.ts               # Fetch utilities
├── tools/                # Tool handlers
│   ├── verifyCitation.ts
│   ├── batchVerifyCitations.ts
│   └── findVerifiedPapers.ts
└── databases/            # Database adapters
    ├── index.ts          # Parallel query orchestrator
    ├── crossref.ts
    ├── openalex.ts
    ├── pubmed.ts
    └── ... (9 adapters total)

Adding a new database:

Create src/databases/newdb.ts with config, search(), and normalize()
Import and add to src/databases/index.ts
Add tests in tests/databases/newdb.test.ts

Example Usage

Before this MCP (citation hallucination):

User: "Tell me about recent AlphaFold research"
Assistant: "According to Johnson et al. (2024) in Science, AlphaFold3 achieved..."
           ❌ This paper doesn't exist

After this MCP (verified citations only):

User: "Tell me about recent AlphaFold research"
Assistant: [Uses findVerifiedPapers tool]
           "According to Jumper et al. (2023) in Nature (DOI: 10.1038/s41586-023-06004-9), 
            AlphaFold3 achieved..."
           ✓ Real paper with valid DOI verified across databases

Verification catches fake citations:

User: "Can you verify this citation: Smith et al. (2024), 'Quantum AI', Nature"
Assistant: [Uses verifyCitation tool - searches all 9 databases in parallel]
           "⚠ I cannot verify this citation - no matching publication found in
            any of the 9 databases. This citation may be incorrect."

Database Coverage

All databases are queried in parallel for maximum speed (~1 second total):

General Databases

CrossRef: 150+ million scholarly publications across all disciplines
OpenAlex: 250+ million scholarly works across all disciplines
Semantic Scholar: 200+ million papers with AI-powered search

Specialized Databases

PubMed: 35+ million biomedical and life sciences publications
zbMATH: 4+ million mathematics publications
DBLP: Comprehensive computer science bibliography (journals and conferences)
ERIC: 1.7+ million education research publications
HAL: 4.4+ million French/European scholarly documents (2.5M English)
INSPIRE-HEP: 1.7+ million high-energy physics publications