semanticscholar-mcp
MCP server that provides Semantic Scholar academic search capabilities, including paper search, detail query, citation analysis, author search, and intelligent recommendations.
README
Semantic Scholar MCP Server
一个 MCP (Model Context Protocol) 服务器,提供 Semantic Scholar 学术搜索功能。
功能特性
- 论文搜索、详情查询、引用分析
- 作者搜索和学术档案查询
- 基于论文的智能推荐
- 支持多种论文 ID 格式 (DOI, ArXiv, PMID 等)
- 内置速率限制和自动重试机制
快速开始
在 Claude Desktop 中使用
编辑配置文件:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"semanticscholar": {
"command": "npx",
"args": ["-y", "@xbghc/semanticscholar-mcp"],
"env": {
"SEMANTIC_SCHOLAR_API_KEY": "your-api-key"
}
}
}
}
配置 API Key (可选)
Semantic Scholar API 可以无需认证使用,但有速率限制。申请 API Key 可获得更高的请求配额。
- 访问 Semantic Scholar API 申请 API Key
- 在配置中设置
SEMANTIC_SCHOLAR_API_KEY环境变量
可用工具
论文相关
| 工具 | 描述 |
|---|---|
search_papers |
搜索学术论文,支持年份、学科、引用数等过滤条件 |
get_paper |
获取论文详情,支持多种 ID 格式 |
get_paper_citations |
获取引用该论文的文献列表 |
get_paper_references |
获取论文的参考文献列表 |
batch_get_papers |
批量获取多篇论文详情 (最多 500 篇) |
作者相关
| 工具 | 描述 |
|---|---|
search_authors |
搜索学术作者 |
get_author |
获取作者详情 (h-index, 论文数等) |
get_author_papers |
获取指定作者的论文列表 |
推荐
| 工具 | 描述 |
|---|---|
get_recommendations |
基于指定论文获取推荐的相关论文 |
使用示例
在支持 MCP 的客户端中直接对话即可使用:
搜索关于 transformer attention 的论文
查看论文 ARXIV:1706.03762 的详细信息
找出引用了 "Attention Is All You Need" 的论文
推荐与这篇论文相似的研究
支持的论文 ID 格式
- Semantic Scholar ID:
204e3073870fae3d05bcbc2f6a8e263d9b72e776 - DOI:
DOI:10.1038/nature12373 - ArXiv:
ARXIV:1706.03762 - PubMed:
PMID:19872477 - Corpus ID:
CorpusId:123456
其他安装方式
从源码安装
git clone https://github.com/xbghc/semanticscholar-mcp.git
cd semanticscholar-mcp
npm install
npm run build
配置文件使用本地路径:
{
"mcpServers": {
"semanticscholar": {
"command": "node",
"args": ["/path/to/semanticscholar-mcp/dist/index.js"],
"env": {
"SEMANTIC_SCHOLAR_API_KEY": "your-api-key"
}
}
}
}
全局安装
npm install -g @xbghc/semanticscholar-mcp
开发
项目结构
semanticscholar-mcp/
├── src/
│ ├── index.ts # 入口文件
│ ├── server.ts # MCP 服务器
│ ├── api/
│ │ ├── client.ts # API 客户端
│ │ ├── rate-limiter.ts # 速率限制 (p-queue)
│ │ ├── backoff.ts # 指数退避重试
│ │ └── types.ts # 类型定义
│ ├── tools/
│ │ ├── papers.ts # 论文工具
│ │ ├── authors.ts # 作者工具
│ │ └── recommendations.ts # 推荐工具
│ └── utils/
│ ├── errors.ts # 错误处理
│ └── fields.ts # 字段常量
├── tests/ # 测试文件
├── package.json
└── tsconfig.json
常用命令
# 开发模式
npm run dev
# 构建
npm run build
# 运行测试
npm test
速率限制
| 模式 | 请求间隔 |
|---|---|
| 有 API Key | 2 秒 |
| 无 API Key | 5 秒 |
遇到 429 错误时会自动指数退避重试 (1s → 2s → 4s → 8s → 16s)。
API 参考
本服务器基于 Semantic Scholar Academic Graph API。
主要端点:
/graph/v1/paper/search- 论文搜索/graph/v1/paper/{paper_id}- 论文详情/graph/v1/author/search- 作者搜索/recommendations/v1/papers- 论文推荐
许可证
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.