mcp-openalex
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MCP_HOST | No | Host for HTTP transport (default 127.0.0.1) | |
| MCP_PORT | No | Port for HTTP transport (default 8000) | |
| MCP_TRANSPORT | No | Transport mode: http or stdio (default is stdio) | |
| OPENALEX_API_KEY | Yes | Your OpenAlex API key (get one for free at https://docs.openalex.org/) |
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": true
} |
| logging | {} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| extensions | {
"io.modelcontextprotocol/ui": {}
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_worksA | Search works in OpenAlex by keyword, filtered by institution, date, type, and more. |
| semantic_search_worksA | Find works similar to a given text using AI-powered semantic search. Searches by meaning rather than exact keyword match. |
| fetch_workA | Fetch complete metadata for one work. Set fulltext=True to retrieve the open-access PDF as markdown, or pass a prompt to get an LLM summary instead. |
| search_authorsA | Search author profiles by name, optionally filtered by institution. |
| get_author_worksA | List all works by a given author. |
| search_institutionsA | Search institutions by name, optionally filtered by country or type. |
| fetch_authorA | Fetch full author profile including topics and institutions. |
| fetch_institutionA | Fetch full institution profile. |
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
Every tool has a clearly distinct purpose: fetching profiles, searching by name/keyword/semantic, and listing works. No overlap or ambiguity.
All tool names follow a consistent verb_noun pattern using snake_case (e.g., fetch_author, search_works, semantic_search_works). Perfectly predictable.
8 tools is well-scoped for a scholarly database API, covering fetching, searching, and listing without unnecessary bloat.
Core operations are covered: fetching authors, institutions, works; searching with filters; and semantic search. Minor gaps like missing get_institution_works or concept endpoints are acceptable given the scope.