Unpaywall MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| UNPAYWALL_EMAIL | Yes | Your email address used as Unpaywall API identifier |
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
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| unpaywall_lookupA | Look up open-access availability for a scholarly article by DOI. Returns OA status, best OA location (PDF/landing page URL, license), all OA locations, journal info, authors, and publication details. Args: doi: The DOI to look up (e.g. "10.1038/nature12373") |
| unpaywall_searchA | Search Unpaywall for scholarly articles by title. Searches across 120M+ article titles. Supports AND (default), quoted phrases, OR, and negation (-term). Returns up to 50 results per page. Args: query: Search terms for article titles (e.g. "machine learning") is_oa: Filter by open-access status (true = OA only, false = closed only, omit for all) page: Page number for pagination (50 results per page, default 1) |
| unpaywall_export_risA | Export the most recent unpaywall_lookup or unpaywall_search results as RIS format. Save output as a .ris file and import into Zotero: File -> Import. |
| unpaywall_export_bibtexA | Export the most recent unpaywall_lookup or unpaywall_search results as BibTeX format. |
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 4 tools
Each tool has a clearly distinct purpose: lookup by DOI, search by title, and export in two different formats (BibTeX and RIS). No overlap in functionality.
All tools follow a consistent 'unpaywall_verb_noun' pattern in snake_case, making it easy to predict tool names and understand their actions.
With 4 tools, the server is focused but not overly minimal. It covers the core use cases (lookup, search, export) without unnecessary extras.
The tool surface covers the primary workflows: looking up articles by DOI, searching by title, and exporting results in common academic formats. Minor gaps like batch operations or direct DOi extraction from search results are acceptable for the scope.