scholar-search

scholar-search

Enables searching Google Scholar papers with year filtering, deduplication, and proxy support. Also provides paper detail retrieval, TF-IDF relevance analysis, and chart generation via MCP tools.

Category
Visit Server

README

Scholar Search MCP

基于 Python MCP (Model Context Protocol) 的谷歌学术搜索工具,供 CherryStudio 等 AI 客户端调用。

功能

Tool 说明
search_papers 谷歌学术论文搜索,支持年份过滤、自动精确去重、SSL 断连重试
get_paper_detail 获取单篇论文详细信息,自动从外部源(arxiv API / meta 标签)获取完整摘要
analyze_relevance TF-IDF + 余弦相似度相关性排序,关键词提取,方向聚类摘要
generate_relevance_chart Matplotlib 多角度图表(柱状图 / K-Means 聚类 / 关键词)+ 本地 HTTP 服务端

环境要求

  • Python >= 3.10
  • conda 环境 MCP(或任意虚拟环境)
  • 谷歌学术需 HTTP 代理(Clash / V2Ray 等)

安装

conda activate MCP
pip install -r requirements.txt
# 或
pip install -e .

环境变量

变量 默认值 说明
SCHOLAR_PROXY http://localhost:7890 代理地址,优先级最高
HTTP_PROXY / HTTPS_PROXY - 标准代理环境变量(备选)
SCHOLAR_NO_PROXY - 设为 1/true/yes 禁用代理
SCHOLAR_TIMEOUT 30 单次 HTTP 请求超时(秒)
SCHOLAR_RETRIES 3 搜索失败最大重试次数
SCHOLAR_CHART_PORT 8765 图表 HTTP 服务端端口

代理配置

三层优先级,从高到低:

SCHOLAR_PROXY  >  HTTP_PROXY / HTTPS_PROXY  >  默认 http://localhost:7890

摘要说明

Google Scholar 搜索结果页只提供摘要片段,多结果页面中不包含完整摘要。

工具 摘要行为
search_papers 返回 Google Scholar 片段(适合快速浏览,速度优先)
get_paper_detail 自动从外部源获取完整摘要:arxiv 走结构化 API,其他走页面 meta 标签;失败时回退到 Google Scholar 片段

CherryStudio 接入

1. MCP 配置

{
  "scholar-search": {
    "command": "C:/Users/mulim/.conda/envs/MCP/python.exe",
    "args": ["C:/Users/mulim/Desktop/Project/scholar_search/server.py"],
    "env": {
      "SCHOLAR_PROXY": "http://localhost:7890",
      "SCHOLAR_CHART_PORT": "8765"
    }
  }
}

路径需替换为实际路径。macOS/Linux 用户去掉盘符,使用 Unix 路径风格。

2. 在对话中使用

CherryStudio 对话时,直接描述你的研究需求即可,AI 会自动调用工具链:

示例

"搜索 2020 年后关于 graph neural network for recommendation system 的论文,取前 10 篇,做相关性分析并生成图表"

典型调用链

search_papers → analyze_relevance → generate_relevance_chart → 浏览器打开 http://localhost:8765

3. 图表查看

generate_relevance_chart 会启动本地 HTTP 服务并返回链接:

http://localhost:8765/

包含三个图表:

  • 相关性柱状图 /bar.png
  • K-Means 聚类散点图 /cluster.png
  • 关键词重要性图 /keywords.png

在浏览器中打开后不会自动刷新,重新调用工具即可更新数据。

开发

# 运行测试(默认跳过网络 mock 测试,~7s)
pytest

# 包含网络 mock 测试(~40s)
pytest tests/ --ignore=

# 带 coverage.xml 输出
pytest --cov=scholar_search --cov=server --cov-report=term-missing --cov-report=xml

# Lint 检查 (PEP 8, max-line=127)
flake8 --max-line-length=127 .

# 启动调试
python server.py

项目结构

scholar_search/
├── server.py              # MCP Server 入口 (FastMCP, 4 个 Tool)
├── scholar_search/        # 核心包
│   ├── config.py          # 代理 / 超时 / 重试 / 端口配置
│   ├── search.py          # requests + bs4 直连解析,外部源完整摘要(arxiv API / meta 标签)
│   ├── analysis.py        # TF-IDF + 余弦相似度 + 方向聚类
│   └── viz.py             # Matplotlib 多图表 + HTTP 服务端
├── tests/                 # pytest (137 tests, 100% 覆盖)
│   ├── test_config.py
│   ├── test_search.py
│   ├── test_analysis.py
│   ├── test_viz.py
│   └── test_server.py
├── requirements.txt
├── pyproject.toml
├── CLAUDE.md
└── .gitignore

License

MIT

Recommended Servers

playwright-mcp

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.

Official
Featured
TypeScript
Magic Component Platform (MCP)

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.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

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.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

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.

Official
Featured
TypeScript
Kagi MCP Server

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.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

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.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured