OpenAlex MCP Server
Enables searching and retrieving scholarly works, authors, institutions, and citation networks from the OpenAlex catalog via natural language.
README
OpenAlex MCP Server
An MCP (Model Context Protocol) server that provides access to OpenAlex, a free and open catalog of the world's scholarly works, authors, institutions, and more.
Features
- Search 250M+ scholarly works with full-text search and powerful filters
- Author discovery with publication metrics (h-index, i10-index, citations)
- Institution profiles for universities, research labs, and companies
- Citation network traversal — find what cites a paper and what it cites
- Multiple ID format support — OpenAlex IDs, DOIs, PMIDs, ORCIDs, RORs
Installation
# Clone or copy the project
cd openalex-mcp-server
# Install dependencies
npm install
# Build the TypeScript
npm run build
Configuration
Environment Variables
| Variable | Description | Default |
|---|---|---|
OPENALEX_EMAIL |
Email for polite pool (higher rate limits) | user@example.com |
TRANSPORT |
Transport type: stdio or http |
stdio |
PORT |
Port for HTTP transport | 3000 |
Set your email to get into OpenAlex's "polite pool" with higher rate limits:
export OPENALEX_EMAIL="your.email@example.com"
Usage
With Claude Desktop
Add to your Claude Desktop configuration (~/Library/Application Support/Claude/claude_desktop_config.json on macOS):
{
"mcpServers": {
"openalex": {
"command": "node",
"args": ["/path/to/openalex-mcp-server/dist/index.js"],
"env": {
"OPENALEX_EMAIL": "your.email@example.com"
}
}
}
}
With Claude Code
claude mcp add openalex node /path/to/openalex-mcp-server/dist/index.js
Standalone (HTTP mode)
TRANSPORT=http PORT=3000 npm start
Available Tools
Works (Publications)
| Tool | Description |
|---|---|
openalex_search_works |
Search works with full-text queries and filters |
openalex_get_work |
Get a single work by OpenAlex ID, DOI, or PMID |
openalex_get_citations |
Get works that cite a given work |
openalex_get_references |
Get works cited by a given work |
Authors
| Tool | Description |
|---|---|
openalex_search_authors |
Search authors by name |
openalex_get_author |
Get author profile by OpenAlex ID or ORCID |
openalex_get_author_works |
Get an author's publications |
Institutions
| Tool | Description |
|---|---|
openalex_search_institutions |
Search institutions by name |
openalex_get_institution |
Get institution profile by OpenAlex ID or ROR |
openalex_get_institution_works |
Get an institution's publications |
Example Queries
Search for recent CRISPR papers
openalex_search_works(
query: "CRISPR gene therapy",
filter: "publication_year:2023,open_access.is_oa:true",
sort: "cited_by_count:desc"
)
Find highly-cited climate research
openalex_search_works(
query: "climate change",
filter: "cited_by_count:>1000,type:review"
)
Get citation network for a paper
// Get the paper
openalex_get_work(id: "10.1038/s41586-020-2649-2")
// Get papers that cite it
openalex_get_citations(id: "10.1038/s41586-020-2649-2")
// Get papers it cites
openalex_get_references(id: "10.1038/s41586-020-2649-2")
Explore an author's profile
openalex_search_authors(query: "Fei-Fei Li")
openalex_get_author(id: "A5023888391")
openalex_get_author_works(id: "A5023888391", sort: "cited_by_count:desc")
Find Northwestern University's research output
openalex_search_institutions(query: "Northwestern University")
openalex_get_institution(id: "I111979921")
openalex_get_institution_works(
id: "I111979921",
filter: "publication_year:2024",
sort: "cited_by_count:desc"
)
Filter Syntax
OpenAlex supports powerful filtering. Common filters:
| Filter | Examples |
|---|---|
publication_year |
2023, 2020-2024 |
open_access.is_oa |
true, false |
cited_by_count |
>100, <10, 100-500 |
type |
article, book, preprint, dataset |
authorships.institutions.id |
I27837315 (filter by institution) |
authorships.author.id |
A5023888391 (filter by author) |
primary_location.source.id |
S137773608 (filter by journal) |
Combine multiple filters with commas:
filter: "publication_year:2023,open_access.is_oa:true,cited_by_count:>50"
Response Formats
All tools support two response formats:
markdown(default): Human-readable formatted outputjson: Structured data for programmatic use
Rate Limits
- Without email: ~10 requests/second
- With email (polite pool): ~100 requests/second
Always set OPENALEX_EMAIL for production use.
Development
# Watch mode for development
npm run dev
# Build for production
npm run build
# Run the server
npm start
License
MIT
Links
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.