Provides tools to search for and download academic preprints and papers from the arXiv repository.
Enables searching for computer science bibliographical data and author information through the dblp computer science bibliography.
Supports retrieving paper metadata and performing batch downloads of academic papers using Digital Object Identifiers (DOIs).
Facilitates the generation of visual citation and reference networks using Mermaid diagram syntax.
Integrates with various open-access sources and aggregators like DOAJ, CORE, and Unpaywall to find and download freely available research papers.
Enables AI-powered full-text analysis of academic papers using OpenAI-compatible API endpoints for extracting and summarizing information.
Provides tools for searching biomedical literature and life sciences research papers via PubMed and Europe PMC.
Offers broad academic search capabilities and paper data retrieval using the Semantic Scholar database.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Scholar MCP ServerSearch for recent papers on LLM pruning and summarize the top result"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Scholar MCP Server
Local academic paper tool MCP server — 9-source search, multi-source download, AI-powered analysis, citation graph, code-based paper recommendation.
Quick Install
pip install scholar-mcp-server[all]
scholar-mcp-install --allThat's it. Restart your IDE and start using it.
Features
Tool | Description |
| 9-source concurrent search: Semantic Scholar, OpenAlex, Crossref, PubMed, arXiv, CORE, Europe PMC, DOAJ, dblp |
| Multi-source PDF download: Unpaywall → Publisher OA → Sci-Hub → arXiv |
| Batch download multiple papers by DOI list |
| AI full-text analysis — downloads PDF, extracts text, sends to any OpenAI-compatible API |
| Scan your workspace code → auto-recommend related papers |
| Generate Mermaid citation/reference network visualization |
| Check download source availability |
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 --allEnvironment Variables
Variable | Description | Required |
| API key for AI analysis | For |
| API base URL (any OpenAI-compatible endpoint) | Optional (default: |
| Model name | Optional (default: |
| Email for Unpaywall API | Optional |
Supported IDEs
Antigravity (Gemini)
Cursor
Windsurf
Claude Code / Claude Desktop
VS Code (Copilot)
Search Sources (9)
All free, no API keys required:
Source | Coverage |
Semantic Scholar | Broad academic (primary) |
OpenAlex | 250M+ works, global |
Crossref | DOI metadata |
PubMed | Biomedical |
arXiv | Physics, CS, Math |
CORE | Open Access aggregator |
Europe PMC | European biomedical |
DOAJ | Open Access journals |
dblp | Computer Science |
License
MIT
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.