OpenAlex MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| OPENALEX_BEARER_TOKEN | No | Bearer token for authenticated API access (optional) | |
| OPENALEX_DEFAULT_EMAIL | No | Default email for rate limiting when no mailto parameter provided |
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
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_worksC | Search scholarly works in OpenAlex |
| search_authorsC | Search authors and researchers |
| search_sourcesC | Search journals and sources |
| search_institutionsD | Search institutions |
| search_topicsC | Search research topics (formerly concepts) |
| search_publishersD | Search publishers |
| search_fundersC | Search funders |
| get_entityC | Get a single entity by its OpenAlex ID |
| autocompleteC | Type ahead search across any OpenAlex entity type |
| classify_textC | Classify arbitrary text to predict research concepts and confidence scores |
| get_filterable_fieldsC | Get a list of filterable field names and their types for a specified OpenAlex entity. |
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 11 tools
Every tool has a clearly distinct purpose with no ambiguity. The search tools target specific entity types (authors, funders, institutions, etc.), while get_entity, autocomplete, classify_text, and get_filterable_fields serve unique functions. An agent can easily distinguish between searching for works versus classifying text or getting filterable fields.
The tool names follow a highly consistent verb_noun pattern throughout. All search tools use 'search_' prefix followed by the entity type (e.g., search_authors, search_works), while other tools use clear verbs like get_entity, autocomplete, classify_text, and get_filterable_fields. There are no deviations in naming conventions.
With 11 tools, this server is well-scoped for interacting with the OpenAlex scholarly database. Each tool earns its place by covering distinct entity searches, entity retrieval, text classification, and metadata access. The count aligns with the domain's complexity without being overwhelming or insufficient.
The tool surface provides complete coverage for the OpenAlex domain. It includes search capabilities for all major entity types (works, authors, funders, institutions, publishers, sources, topics), direct entity retrieval via get_entity, utility functions like autocomplete and classify_text, and metadata access with get_filterable_fields. There are no obvious gaps that would hinder agent workflows.