一个 MCP 服务器，用于搜索精准的学术文章。更多学术供应商即将添加。
服务器实现了一个工具：
search-arxiv：在 arxiv 中搜索与给定关键字相关的文章。
将“关键字”作为必需的字符串参数
Related MCP server: arXiv MCP Server
在 MacOS 上： ~/Library/Application\ Support/Claude/claude_desktop_config.json在 Windows 上： %APPDATA%/Claude/claude_desktop_config.json
或者如果你正在使用 Docker
要通过Smithery自动为 Claude Desktop 安装 mcp-scholarly：
npx -y @smithery/cli install mcp-scholarly --client claude准备分发包：
同步依赖项并更新锁文件：
uv sync构建软件包分发版：
uv build这将在dist/目录中创建源和轮子分布。
发布到 PyPI：
uv publish注意：您需要通过环境变量或命令标志设置 PyPI 凭据：
令牌： --token或UV_PUBLISH_TOKEN
或用户名/密码： --username / UV_PUBLISH_USERNAME和--password / UV_PUBLISH_PASSWORD
由于 MCP 服务器通过 stdio 运行，调试起来可能比较困难。为了获得最佳调试体验，我们强烈建议使用MCP Inspector 。
您可以使用以下命令通过npm启动 MCP Inspector：
npx @modelcontextprotocol/inspector uv --directory /Users/adityakarnam/PycharmProjects/mcp-scholarly/mcp-scholarly run mcp-scholarly启动后，检查器将显示一个 URL，您可以在浏览器中访问该 URL 以开始调试。
Search arxiv for articles related to the given keyword.
| Name | Required | Description | Default |
|---|---|---|---|
| keyword | Yes |
Search google scholar for articles related to the given keyword.
| Name | Required | Description | Default |
|---|---|---|---|
| keyword | Yes |
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
search-arxivsearch-google-scholarScored across 2 tools
The two tools have clearly distinct purposes: one searches ArXiv specifically, while the other searches Google Scholar. There is no overlap in their functionality, and an agent can easily choose the appropriate tool based on the desired academic database.
Both tools follow a consistent verb_noun pattern with 'search' as the verb and the database name as the noun (arxiv, google-scholar). The naming is uniform and predictable across the set.
With only 2 tools, the server feels thin for a 'Scholarly Server' that might be expected to handle broader academic tasks. While search is a core function, typical scholarly workflows could benefit from additional tools like fetching article details, citations, or managing references.
The server is severely incomplete for a scholarly domain, as it only provides search functionality without any tools for retrieving full articles, accessing metadata, or performing follow-up actions like citation analysis. This leaves significant gaps that could hinder agent workflows.
Academic research search across PubMed and arXiv
Academic paper search, scientific literature, citation analysis, arXiv & semantic related-work.
Search arXiv/Semantic Scholar/OpenAlex + medical evidence (PubMed/Europe PMC) + LaTeX/PDF tools.
Find academic papers across major sources like arXiv, PubMed, bioRxiv, and more. Download PDFs whe…