An optimized Model Context Protocol (MCP) server for resolving author ambiguity and academic research using the OpenAlex.org API, specifically designed for AI agents with optimized data structures and extended functionality.

Installation

From Source

git clone https://github.com/drAbreu/alex-mcp.git
cd alex-mcp
python3 -m venv venv
source venv/bin/activate
pip install -e .
export OPENALEX_MAILTO=your-email@domain.com
./run_alex_mcp.sh

CLI Tool

alex-mcp

Direct uvx Execution

uvx --from git+https://github.com/drAbreu/alex-mcp.git@4.1.0 alex-mcp

uvx with Environment Variables

OPENALEX_MAILTO=your-email@domain.com uvx --from git+https://github.com/drAbreu/alex-mcp.git@4.1.0 alex-mcp

Configuration

Claude Desktop

{
  "mcpServers": {
    "alex-mcp": {
      "command": "/path/to/alex-mcp/run_alex_mcp.sh",
      "env": {
        "OPENALEX_MAILTO": "your-email@domain.com"
      }
    }
  }
}

Available Tools

Tool	Description
autocomplete_authors	Retrieves multiple author candidates using the OpenAlex autocomplete API for intelligent disambiguation...
search_authors	Search for authors with simplified output for AI agents, including filtering by institution, top...
retrieve_author_works	Retrieves works for a given author with advanced filtering capabilities, including publication year...

Features

• Advanced author disambiguation accounting for complex career transitions and name variations
• Institution resolution with tracking of current and past affiliations
• Retrieval of academic works for journal articles, letters, and research papers
• Citation analysis including H-index, citation count, and impact metrics
• ORCID integration for maximum matching accuracy
• Optimization for AI agents with simplified data structures
• Smart filtering with advanced options for targeted queries
• Multiple candidates with ranked results for automated decision-making
• Production-grade, built with FastMCP according to official guidelines

Environment Variables

Required

• OPENALEX_MAILTO - Email address for identifying polite use of the OpenAlex API

Optional

• OPENALEX_MAX_AUTHORS - Maximum number of authors per request
• OPENALEX_USER_AGENT - Custom user agent string
• ALEX_MCP_VERSION - MCP server version identifier
• OPENALEX_RATE_PER_SEC - Rate limit per second
• OPENALEX_RATE_PER_DAY - Rate limit per day

Usage Examples

Find J. Abreu at EMBO with recent publications

Get multiple author candidates for James Briscoe at Francis Crick Institute

Search for authors in developmental biology with ORCID integration

Retrieve highly-cited journal articles for a specific author

Analyze career transitions and institutional affiliations

Notes

This server is specifically optimized for academic research workflows and integration with AI agents. It includes support for integration with OpenAI Agents and provides comprehensive author disambiguation with institutional context. The server follows MCP best practices and includes proper rate limiting for courteous API usage.