openalex-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| OPENALEX_EMAIL | No | Your email address for the OpenAlex polite pool. | |
| MCP_RECEIPT_LOG | No | Path to a JSONL file for query receipts. If set, logs each query. | |
| OPENALEX_API_KEY | No | Optional OpenAlex API key. | |
| MCP_RECEIPT_STRICT | No | If set to '1', makes logging failure raise an error. Otherwise swallowed. | |
| MCP_RECEIPT_SESSION | No | A session identifier for the receipt log (e.g., project or article slug). |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| oa_search_worksA | Search OpenAlex for scholarly works (articles, books, datasets, theses). Returns the unified envelope. OpenAlex matches title, abstract and indexed full text with stemming, so result.total is a loose count (matching_mode full_text_stemmed) and a high breadth is expected. Titles are typed by OpenAlex's own language field; where that is absent, a CJK title is kept only in extra.title rather than guessed into ja or ko. Filters by year, author, institution, source and open-access status narrow the set exactly. OpenAlex charges per call, not per result: a sweep that pages through results should set per_page 200. |
| oa_get_workA | Look up one work by OpenAlex ID, DOI, or PMID. Returns the unified envelope with a single item, or NOT_FOUND. |
| oa_search_authorsB | Search OpenAlex for authors by name. Returns the unified envelope; each item is an author record (record_type author) with affiliations, work and citation counts, and h-index in extra. |
| oa_get_authorA | Look up one author by OpenAlex ID or ORCID. Returns the unified envelope with a single author item, or NOT_FOUND. |
| oa_search_sourcesB | Search OpenAlex for sources: journals, repositories, conferences. Returns the unified envelope (record_type source). |
| oa_search_institutionsA | Search OpenAlex for institutions. Returns the unified envelope (record_type institution); useful for finding institution IDs to filter work searches. |
| oa_cited_byA | Works that cite a given work, most-cited first. Returns the unified envelope. This is a filter on an identifier, not a term search, so no searched_for headline is set. |
| oa_author_worksA | Works by one author, with optional year filter and sort. Returns the unified envelope. A filter on an identifier, not a term search. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 8 tools
Each tool targets a clearly distinct resource and action: single-record lookups (oa_get_work, oa_get_author), term searches over distinct entity types, and identifier-based traversals (oa_cited_by, oa_author_works). The descriptions explicitly distinguish identifier filters from term searches, so an agent can reliably choose the right tool.
All eight tools follow a consistent oa_ + verb_noun pattern (oa_get_work, oa_search_authors, oa_cited_by, oa_author_works). The shared oa_ namespace prefix and uniform snake_case make the set predictable.
Eight tools is well-scoped for a read-oriented scholarly metadata API, covering the major entity types without redundant operations. Each tool earns its place by serving a distinct query pattern.
The surface covers work lookup/search, author lookup/search/works, source search, institution search, and citation traversal, which handles most research workflows. Minor gaps remain: no direct get-by-ID for sources or institutions, and no explicit references or related-works operation.