MCP Hub
Back to servers

Scholar MCP Server

A local academic tool that enables searching across nine academic sources, downloading PDFs, and performing AI-powered analysis of research papers. It also supports generating citation networks and recommending papers based on local workspace code.

glamaGitHub
Stars
88
Forks
7
Updated
Mar 24, 2026
Validated
Mar 27, 2026

Scholar MCP Server

Local academic paper tool MCP server — 9-source search, multi-source download, AI-powered analysis, citation graph, code-based paper recommendation.

PyPI Python Tests License

Quick Install

pip install scholar-mcp-server[all]
scholar-mcp-install --all

That's it. Restart your IDE and start using it.

Features

ToolDescription
paper_search9-source concurrent search with relevance scoring (Semantic Scholar, OpenAlex, Crossref, PubMed, arXiv, CORE, Europe PMC, DOAJ, dblp)
paper_downloadMulti-source PDF download: Unpaywall → Publisher OA → arXiv → Sci-Hub → scidownl
paper_batch_downloadBatch download multiple papers by DOI list
paper_ai_analyzeAI analysis — downloads PDF, extracts full text (up to 20 pages / 12k chars), sends to any OpenAI-compatible API
paper_recommendScan your workspace code → multi-query auto-recommend related papers
paper_citation_graphGenerate Mermaid citation/reference network visualization
paper_healthCheck download source availability

Search Quality

Search results are ranked by a 4-factor composite score:

FactorWeightDescription
Query relevance0–40Title + abstract term matching
Citation impact0–30Log-scaled citation count
Source quality0–10Data source reliability weighting
Year recency0–15Boost for recent publications

Deduplication uses DOI matching + Jaccard title similarity (≥0.7 threshold) across all 9 sources. Each source connector has built-in retry with exponential backoff.

AI Analysis

paper_ai_analyze works with any OpenAI-compatible API. Set AI_API_BASE, AI_API_KEY, and AI_MODEL to point to your preferred provider.

Alternative Install (Git Clone)

git clone https://github.com/45645678a/scholar-mcp.git
cd scholar-mcp
pip install -r requirements.txt
python install.py --all

Environment Variables

VariableDescriptionRequired
AI_API_KEYAPI key for AI analysisFor paper_ai_analyze
AI_API_BASEAPI base URL (any OpenAI-compatible endpoint)Optional (default: https://api.deepseek.com)
AI_MODELModel nameOptional (default: deepseek-chat)
UNPAYWALL_EMAILEmail for Unpaywall APIOptional

Supported IDEs

  • Antigravity (Gemini)
  • Cursor
  • Windsurf
  • Claude Code / Claude Desktop
  • VS Code (Copilot)

Search Sources (9)

All free, no API keys required:

SourceCoverage
Semantic ScholarBroad academic (primary)
OpenAlex250M+ works, global
CrossrefDOI metadata
PubMedBiomedical
arXivPhysics, CS, Math
COREOpen Access aggregator
Europe PMCEuropean biomedical
DOAJOpen Access journals
dblpComputer Science

Development

pip install .[all] pytest
pytest tests/ -v

40 tests covering search dedup, download chain, keyword extraction, and connector mocking.

⚠️ Disclaimer

This tool includes optional Sci-Hub integration for personal academic use. Sci-Hub may be illegal in some jurisdictions. Users are solely responsible for ensuring compliance with local laws and institutional policies. The authors do not endorse copyright infringement. If you are in a compliance-sensitive environment (university, company, lab), consult your institution's policy before using the Sci-Hub download source.

License

MIT

Reviews

No reviews yet

Sign in to write a review