mcp-scholar
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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 |
|---|---|
| scholar_searchB | |
| adaptive_searchA | |
| paper_detailC | |
| paper_referencesA | |
| profile_papersC | |
| summarize_papersB | |
| search_papersA | |
| verify_bibtexB | Verify BibTeX by DOI first, then by a strict title match. |
| align_and_enrichC | Align preprint to published version and enrich metadata. |
| read_paper_sectionsC | Extract sections from an open-access PDF when pymupdf4llm is installed. |
| zotero_saveB | Save paper metadata to Zotero when API credentials are configured. |
| health_checkA | |
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 12 tools
Four tools do essentially the same thing: scholar_search, adaptive_search, search_papers (which explicitly claims to 'replace' the first two but the others still exist), and summarize_papers (search plus summarization). An agent must guess whether to use the deprecated wrappers or the unified tool, and there is no guidance on when summarize_papers beats search_papers followed by paper_detail. The rest of the tools are reasonably distinct.
Most names are snake_case, but the verb placement varies: verb_noun (verify_bibtex, search_papers, summarize_papers, read_paper_sections), noun_noun (paper_detail, paper_references, profile_papers, health_check), and noun_verb (zotero_save, align_and_enrich). Singular/plural and noun-first forms make the pattern unpredictable, though each name is readable on its own.
Twelve tools is a reasonable scope for an academic research server. However, two of them (scholar_search, adaptive_search) are explicitly declared obsolete by search_papers, so the set carries dead weight that inflates the count.
The surface covers the paper lifecycle well: search, detail, citing works, author profiles, summarization, BibTeX verification, PDF section extraction, preprint alignment, and Zotero export. Gaps are minor — there is no export or generation of BibTeX or citation text, no way to find an author other than by profile URL, and no way to tell 'references' (works cited by the paper) apart from 'cited-by' works.