Best for
- Researchers, librarians, and academic writing assistants.
- Developers needing up-to-date scholarly metadata.
- Those building AI tools on top of a large academic knowledge base.
O
OpenAlex MCP Server
Community
Access the OpenAlex academic research catalog - 270M+ publications through MCP. STDIO & Streamable HTTP.
GitHub source repository ↗
63FMRS · C
The OpenAlex MCP Server provides structured access to a large scholarly knowledge base for discovery, trend analysis, and citation graph traversal. It is useful for integrating academic data into AI assistant workflows.
The OpenAlex MCP Server is a community-developed server that enables AI assistants to query the OpenAlex scholarly catalog, which contains over 270 million publications. It offers five tools for searching, filtering, and aggregating scholarly data, plus two prompts for literature review and research landscape analysis. It can run as a local stdio server or as an HTTP server, and is deployable via Docker.
Tools
openalex_search_entities
Search, filter, sort, or retrieve by ID across all 8 entity types (works, authors, sources, institutions, topics, keywords, publishers, funders).
openalex_analyze_trends
Group-by aggregation for trend and distribution analysis, e.g., count publications by publication year or OA status.
openalex_resolve_name
Resolve a name or an identifier (DOI, ORCID, ROR, PMID, PMCID, ISSN, OpenAlex ID) to an OpenAlex ID.
openalex_get_citation_graph
Walk the citation graph one hop from a seed work: cites, cited_by, or related_to.
openalex_describe_fields
List valid filter, group_by, and select field names for an entity type — call before building a query to avoid invalid-field errors.
Setup
- Ensure Node.js is installed (and Bun for development). 2. Add the server to your MCP client config, e.g., in Claude Desktop using stdio transport:
{
"mcpServers": {
"openalex-mcp-server": {
"type": "stdio",
"command": "npx",
"args": ["-y", "@cyanheads/openalex-mcp-server"],
"env": {
"OPENALEX_API_KEY": "your-openalex-api-key"
}
}
}
}- Alternatively, use the public hosted endpoint:
https://openalex.caseyjhand.com/mcp(configured as streamable HTTP). 4. Optionally set environment variablesOPENALEX_API_KEY(free from OpenAlex) andOPENALEX_MAILTO(for the polite pool).
claude_desktop_config.json
{
"mcpServers": {
"openalex-mcp-server": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@cyanheads/openalex-mcp-server"
],
"env": {
"OPENALEX_API_KEY": "your-openalex-api-key"
}
}
}
}
Fit and risk
Not for
- Access to full-text PDFs—the server provides metadata only.
- Users seeking everyday non-academic search.
- Applications requiring extremely low latency for massive concurrent requests without rate limit handling.
Required permissions
- Requires access to the OpenAlex API, either anonymous or with an API key.
- For HTTP transport, needs to open a port locally or configure a public endpoint.
- May read or parse input data containing names or identifiers.
Risks and side effects
- API rate limits may be more restrictive with anonymous access; without a mailto identifier, requests may be throttled.
- OpenAlex data is updated regularly but may not be real-time, and some records may be missing.
- If exposed over the internet, the server could be a target for abuse; protect the endpoint if public.
- Tools returning large data sets may cause high network traffic and memory usage.
Troubleshooting
- If queries fail with invalid field errors, call `openalex_describe_fields` first to validate field names.
- If you get 429 rate limit errors, wait or set `OPENALEX_API_KEY` and `OPENALEX_MAILTO` to raise limits.
- If HTTP connections fail, check the host and port configuration, and ensure the auth mode matches.
- If you see invalid auth errors, check that `OPENALEX_API_KEY` is correct.
Use cases
Have AI assistants conduct academic literature searches and answer questions on specific topics.
Automate systematic literature reviews, including query building, filtering, and citation network analysis.
Analyze the research landscape of a field, including volume trends, top authors and institutions.
Integrate scholarly metadata and citation data into applications.
Supported clients
Claude DesktopFull support
CursorFull support
VS CodeFull support