OpenAlex

Provides an OpenAlex MCP server to search, retrieve, and classify scholarly works, authors, institutions, topics, and more.

typescript

3

GitHub Stars

typescript

Language

5 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "reetp14-openalex-mcp": {
      "command": "npx",
      "args": [
        "openalex-mcp"
      ],
      "env": {
        "OPENALEX_BEARER_TOKEN": "YOUR_TOKEN",
        "OPENALEX_DEFAULT_EMAIL": "user@example.com"
      }
    }
  }
}

You can run a dedicated MCP server that exposes the OpenAlex data through the Model Context Protocol, enabling your applications to search, retrieve, and classify scholarly information at scale. This server makes OpenAlex’s extensive catalog accessible via MCP-compatible clients so you can build powerful research-enabled workflows.

How to use

To use the OpenAlex MCP server with your MCP client, configure your client to recognize the OpenAlex MCP as a server source. You can run the server locally or point to a remote MCP endpoint, then call the available tools to search works, authors, sources, institutions, concepts, publishers, funders, and more. You can also leverage autocomplete and text classification to streamline your workflows. Add the server configuration to your MCP client so you can invoke the supported tools directly from your applications.

Two runnable configurations are provided for starting the OpenAlex MCP server. The first runs via npx and uses the package name openalex-mcp, suitable for quick start from any environment with Node and npm installed. The second runs locally from the installed package in your project, suitable for development and offline use.

How to install

# Prerequisites: ensure Node.js and npm are installed on your system
# Global install (recommended for quick start)
npm install -g openalex-mcp

# Build from source (if you prefer cloning the repo)
# (You would typically run these in a development environment)
git clone https://github.com/reetp14/openalex-mcp.git
cd openalex-mcp
npm install
npm run build

After installing, add the MCP server to your client configuration. Two valid runtime configurations are shown below. Use the one that matches your setup.

Configuration and usage notes

Environment variables can influence authentication and rate limiting. You may set a bearer token for authenticated access and a default email to assist with higher rate limits when the client does not supply an email. Examples of environment variables you may configure are OPENALEX_BEARER_TOKEN and OPENALEX_DEFAULT_EMAIL.

Rate limits depend on whether you provide authentication. Anonymous access is lower than when using a token or a provided email. For best results, supply your bearer token or email when making requests.

Examples of common usage patterns

Once configured, you can perform searches across multiple entity types, retrieve single entities by OpenAlex ID, or obtain aggregated trends. For instance, you can search for works by a given query, filter by date ranges, and sort by impact metrics. You can also request autocomplete suggestions for journals, or classify a block of text into likely research concepts.

Available tools

search_works

Search scholarly works with full OpenAlex query grammar including full-text search, filters, sorting, pagination, and field selection.

search_authors

Search researchers and creators with support for filters, sorts, and field selection.

search_sources

Search journals, conferences, and repositories.

search_institutions

Search universities, hospitals, and labs.

search_concepts

Search hierarchical research topics across concept levels.

search_publishers

Search publishing organizations.

search_funders

Search grant-making bodies.

autocomplete

Type-ahead search across multiple entity types to quickly find candidates.

classify_text

Predict research concepts from a given title and abstract text.