MCP SERVERSearch OpenAlex's catalogue of publications, authors, institutions and funders, aggregate it into counted groups, and walk the citation graph — without leaving the conversation.
LABSCO SUMMARY
The discipline is what stands out for a catalogue this size. Names are ambiguous and IDs are not, so resolution is a deliberate first step; field names are discoverable, so a filter is built from real fields instead of a guess that errors; and a default field selection per entity type stops a search dumping full records into the context. The aggregation tool earns its place — grouped counts over a filtered population answer how a field has changed without retrieving the underlying works at all.
A server over the OpenAlex academic catalogue with five tools: resolve a name or identifier to an ID, search or fetch any entity type, group entities and count them, walk one hop of the citation graph, and list the field names a query may legally use before you build it.
Published as @cyanheads/openalex-mcp-server, runnable over stdio or as a Streamable HTTP server, which binds to 127.0.0.1 on port 3010 at /mcp by default. A public hosted instance exists at https://openalex.caseyjhand.com/mcp. No credentials are required: OPENALEX_API_KEY is optional and free, and anonymous rate limits apply without it, while OPENALEX_MAILTO sends an email address to join OpenAlex's polite pool and is separate from the key.
One command — npx -y @cyanheads/openalex-mcp-server
USE CASES
Resolve the name to a single OpenAlex ID first, then search works filtered on that ID rather than on the string.
Walk one hop out from the seed work in the citing direction, or inward through its own references.
Check which fields can be grouped, then count works by publication year, open-access status or institution over a filtered population.
The identifier resolves to an OpenAlex ID and the record comes back with the default fields for a work.
Boolean keywords with a filter on year range, country or open-access status, paginated by cursor so the result set can be worked through.
Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.
openalex_analyze_trendsAggregate OpenAlex entities into groups and count them. Use for trend analysis (group works by publication_year), distribution analysis (group by oa_status, type, country), and comparative analysis (group by institution or topic). Combine with filters to scope the analysis. Returns up to 200 groups per page — use cursor pagination for fields with many distinct values.
openalex_describe_fieldsList valid field names for an OpenAlex entity type and context (filter, group_by, or select). Use proactively before constructing a filter or group_by to avoid invalid-field 400 errors. Pass query to narrow the results by name similarity — useful when you have a partial or guessed field name.
openalex_get_citation_graphWalk the citation graph one hop from a seed work. Direction picks the edge: incoming citations (cites), the seed's own references (cited_by), or OpenAlex's algorithmically-related works (related_to). Note: direction follows OpenAlex's filter convention, which inverts the common English reading — cites returns works that cite the seed; cited_by returns works the seed cites. Results use the works schema; combine with filters/sort to narrow further.
openalex_resolve_nameResolve a name or an identifier to an OpenAlex ID. ALWAYS use this before filtering by entity — names are ambiguous, IDs are not. A name returns up to 10 autocomplete matches with disambiguation hints. An identifier — OpenAlex ID, DOI, ORCID, ROR, PMID, PMCID, or ISSN, bare or in URL form — resolves directly to the one record it addresses, and needs no entity_type.
openalex_search_entitiesSearch, filter, sort, or retrieve by ID. Covers all OpenAlex entity types (works, authors, sources, institutions, topics, keywords, publishers, funders). Pass id to retrieve a single entity. Otherwise, use query and/or filters for discovery. Supports keyword search with boolean operators, exact phrase matching, and AI semantic search. Use openalex_resolve_name to resolve names to IDs before filtering. Searches and ID lookups return a curated set of fields by default; pass select to override with specific fields, or ["*"] for the full record.
BEFORE YOU INSTALL
5 tools when we connected. openalex_literature_review and openalex_research_landscape are prompts, not tools.
Of the 4 documented clients, 3 run the server on your machine and 1 connects to a hosted endpoint.
CONTEXT COST
Rated by the size of the 5 tool definitions that ride along on every turn, not by how many there are
INSTALLATION
npx -y @cyanheads/openalex-mcp-serverhttps://openalex.caseyjhand.com/mcpAdd this hosted endpoint to your MCP client.
{
"mcpServers": {
"openalex-mcp-server": {
"type": "streamable-http",
"url": "https://openalex.caseyjhand.com/mcp"
}
}
}Clients spell the "type" value differently: Claude Code and VS Code use "http", Cline uses "streamableHttp", and Roo Code uses "streamable-http". Claude Desktop does not accept a URL entry in its config file; remote servers go under Settings → Connectors.
{
"mcpServers": {
"openalex-mcp-server": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@cyanheads/openalex-mcp-server"
],
"env": {
"OPENALEX_API_KEY": "<YOUR_OPENALEX_API_KEY>"
}
}
}
}{
"mcpServers": {
"openalex-mcp-server": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@cyanheads/openalex-mcp-server"
]
}
}
}{
"servers": {
"openalex-mcp-server": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@cyanheads/openalex-mcp-server"
]
}
}
}MCP servers
xeophon
guangxiangdebizi
JonasBaath
IlyaGusev