Scholar MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| S2_API_KEY | No | Semantic Scholar API key (https://www.semanticscholar.org/product/api#api-key-form) (1 req/s) | |
| CORE_API_KEY | No | CORE API key (https://core.ac.uk/services/api) | |
| OPENALEX_EMAIL | No | Email for Unpaywall + OpenAlex polite pool | |
| SCIHUB_ENABLED | No | Enable Sci-Hub as last-resort source | false |
| SCHOLAR_DOWNLOAD_DIR | No | PDF save directory | ./downloads |
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_papersA | Discover papers that answer a research question or match a remembered idea. Searches multiple sources, merges duplicates, follows citation connections, and ranks for relevance. Natural-language queries work without extra parameters. Use paper_info when you already have a paper identifier. For cross-language discovery, formulate the query in the language of the target literature, usually English for computer science and AI research. |
| paper_infoA | Look up a paper and trace what it builds on or what followed it. Detail includes the complete available abstract and author list. Citations are papers that cite it; references are papers it cites. Each relation list is ordered by citation count and limited separately. |
| recommend_papersA | Explore related work around a paper, including connections across topics. similar finds semantic neighbours and is the default. peers finds papers cited alongside it. kin finds papers sharing its references, including connections across topics. For direct citation lists, use paper_info. |
| search_authorsA | Find researchers and their profiles, affiliations and publication metrics. Compare returned affiliations to distinguish people with the same name. |
| download_paperA | Keep a paper's PDF in your local research library. Resolves an accessible copy across archives and repositories. Use read_paper for temporary reading without keeping a PDF. A successful download keeps a separate copy when the version changes. |
| read_paperA | Read a paper's text, inspect figures and tables, or jump to its appendix. Returns page-aware Markdown from pages 1-10 by default, with selectors for figures and tables. Native structured articles are used when a PDF is unavailable, with original section IDs and continuation locators. Use visual to inspect a selected item. The temporary PDF is cleaned up; use download_paper to keep a local copy. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| scholar_status | Return server capabilities without occupying the model's tool surface. |
TDQS
Scored across 6 tools
Each tool targets a distinct stage of the research workflow, and the descriptions explicitly cross-reference each other to resolve the two riskiest pairs (search_papers vs recommend_papers, download_paper vs read_paper). The only residual overlap is between search_papers and recommend_papers, both of which return related literature, though mode language ('around a paper', 'similar/peers/kin') helps separate them.
Five of six tools follow a clean verb_noun pattern (search_papers, search_authors, recommend_papers, download_paper, read_paper) with consistent pluralization on the search pair. paper_info breaks the convention as a noun-first lookup, a minor but noticeable deviation.
Six tools map neatly onto the paper-research lifecycle: discover, inspect, explore relations, find authors, acquire, and read. Nothing feels redundant or padded, and no obvious operation is missing from the set.
Coverage spans discovery, metadata, citation tracing, author lookup, PDF retrieval, and reading with figure/table selectors, so core research workflows have no dead ends. Minor gaps remain around library management (no way to list or organize downloaded PDFs) and citation export/formatting.