Semantic Scholar MCP Server
Provides direct access to 200M+ academic papers from Semantic Scholar, enabling paper search with advanced filters, author discovery, citation analysis, and AI-powered paper recommendations through natural language.
README
🔬 Semantic Scholar MCP Server
The most comprehensive MCP server for academic research. Direct access to 200M+ papers from Semantic Scholar within Claude Desktop.
🚀 Features
| Tool | Description |
|---|---|
semantic_scholar_search_papers |
Advanced paper search with filters (year, field, citations, open access) |
semantic_scholar_get_paper |
Full paper details with optional citations and references |
semantic_scholar_search_authors |
Find researchers by name |
semantic_scholar_get_author |
Author profiles with h-index, publications, affiliations |
semantic_scholar_recommendations |
AI-powered related paper discovery |
semantic_scholar_bulk_papers |
Batch retrieval of up to 500 papers |
Supported ID Formats:
- Semantic Scholar ID
- DOI (
DOI:10.1038/...) - ArXiv (
ARXIV:2106.15928) - PubMed (
PMID:32908142) - ACL (
ACL:P19-1285) - CorpusId (
CorpusId:215416146)
📦 Installation
Option 1: pip (Recommended)
pip install semantic-scholar-mcp
Option 2: From Source
git clone https://github.com/smaniches/semantic-scholar-mcp.git
cd semantic-scholar-mcp
pip install -e .
🔑 Get Your API Key
- Go to Semantic Scholar API
- Sign up for a free API key
- Note your rate limit (typically 1-100 requests/second depending on tier)
⚙️ Configuration
Claude Desktop Setup
Add to your Claude Desktop config file:
Windows: %APPDATA%\Claude\claude_desktop_config.json
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Linux: ~/.config/Claude/claude_desktop_config.json
{
"mcpServers": {
"semantic_scholar": {
"command": "python",
"args": ["-m", "semantic_scholar_mcp"],
"env": {
"SEMANTIC_SCHOLAR_API_KEY": "your-api-key-here"
}
}
}
}
Then restart Claude Desktop.
💡 Usage Examples
Search Papers
Search for "transformer attention mechanism" papers from 2023 with at least 100 citations
Get Paper Details
Get details for DOI:10.1038/s41586-021-03819-2 including its top 20 citations
Find Related Papers
Get recommendations based on paper 649def34f8be52c8b66281af98ae884c09aef38b
Author Search
Find author "Yoshua Bengio" and list their recent publications
Bulk Retrieval
Retrieve these papers: DOI:10.1038/nature12373, ARXIV:2106.15928, PMID:32908142
📊 Rate Limits
| Tier | Requests/Second | How to Get |
|---|---|---|
| No API Key | 1 req/sec | Default |
| Free API Key | 1 req/sec | Sign up |
| Academic Partner | 10-100 req/sec | Apply via S2 |
🏗️ Architecture
┌─────────────────┐ ┌──────────────────────┐ ┌─────────────────┐
│ Claude Desktop │────▶│ semantic-scholar-mcp │────▶│ Semantic Scholar│
│ (MCP Client) │◀────│ (This Server) │◀────│ API │
└─────────────────┘ └──────────────────────┘ └─────────────────┘
│ │ │
│ stdio (JSON-RPC) │ Your API Key │ HTTPS
│ Local process │ Local machine │ 200M+ papers
Your API key never leaves your machine. The MCP server runs locally.
🛠️ Development
# Clone
git clone https://github.com/smaniches/semantic-scholar-mcp.git
cd semantic-scholar-mcp
# Install dev dependencies
pip install -e ".[dev]"
# Run tests
pytest
# Type checking
mypy src/
📄 License
MIT License - see LICENSE file.
👤 Author
Santiago Maniches
- 🏢 Founder & CEO, TOPOLOGICA LLC
- 🔬 ORCID: 0009-0005-6480-1987
- 💼 LinkedIn: santiago-maniches
- 🌐 Website: topologica.ai
🤝 Contributing
Contributions welcome! Please read our Contributing Guidelines.
📬 Support
- 🐛 Issues: GitHub Issues
- 💬 Discussions: GitHub Discussions
- 📧 Contact: santiago@topologica.ai
⭐ Star History
If this tool helps your research, please star the repo!
<p align="center"> <b>Built with ❤️ by <a href="https://topologica.ai">TOPOLOGICA LLC</a></b><br> <i>Advancing computational research through topological intelligence</i> </p>
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。