baidu-scholar-mcp
Provides tools for searching Baidu Scholar by title or keywords, retrieving detailed paper metadata, and accessing reference and citation lists.
Click on "Deploy 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., "@baidu-scholar-mcp Search for papers on low-carbon economy and show me citation details for 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.
baidu-scholar-mcp
百度学术论文查询 MCP server:输入论文标题(支持部分标题/关键词)→ 搜索候选列表 → 调用方大模型挑选 → 返回该论文完整详情。
纯标准库实现 stdio JSON-RPC,不依赖任何 MCP SDK,运行时仅需
curl-cffi内置反爬自愈:Chrome TLS 指纹模拟(curl_cffi)+ cookie 自举 + 多级重试,无需浏览器
自带两套自测(爬虫 13 项 + MCP 协议 8 项),拿到代码一键验证环境可用性
⚠️ 免责声明:本项目为非官方工具,基于对百度学术公开网页接口的逆向分析实现, 仅供个人学习与研究使用。使用时请遵守目标网站的服务条款,禁止用于商业用途或高频抓取。 百度接口随时可能变更,不保证本工具持续可用;因使用本工具产生的任何问题由使用者自行承担。
MCP 工具
工具 | 说明 |
| 按标题搜索,返回候选列表:paperid、标题、作者+机构、年份、期刊卷期页、被引、关键词、截断摘要、知网/万方/维普等来源链接。恰好只命中 1 篇时自动附带 |
| 完整摘要、关键词、作者、期刊(卷/期/页码/ISSN/CN)、被引、DOI、基金、阅读量、研究领域、全部外部全文链接 |
| 参考文献(reference)/ 引证文献(citation)列表 |
典型调用流程(由调用方大模型完成"挑选"):search_papers("新技术革命下人工智能与高质量增长")
→ 从候选里选最匹配的 paperid → get_paper_detail(paperid)。
Related MCP server: Baidu Search MCP Server
安装与配置
方式一:uvx(推荐,零安装)
发布到 PyPI 后,MCP 客户端配置一行即可(uv 会自动拉取并隔离运行):
{
"mcpServers": {
"baidu-scholar": { "command": "uvx", "args": ["baidu-scholar-mcp"] }
}
}方式二:pip 安装后直接作命令
pip install baidu-scholar-mcp{ "command": "baidu-scholar-mcp" }方式三:源码运行
git clone https://github.com/<you>/baidu-scholar-mcp.git
pip install curl-cffi{
"command": "<你的python解释器>",
"args": ["<仓库路径>/baidu_scholar/mcp_server.py"]
}Windows 注意:Python 3.12+ 无 distutils,若同时安装可选的浏览器兜底依赖
undetected-chromedriver,需先 pip install setuptools。
自测
python tests/test_client.py # 爬虫 13 项检查,应"全部通过"(需联网)
python tests/test_mcp_server.py # MCP 协议 8 项检查,应"全部通过"调试时可设环境变量 BAIDU_SCHOLAR_VERBOSE=1 查看过程日志(stderr)。
反爬实现要点
百度学术已全面 SPA 化,数据全走 JSON 接口,本客户端直接调接口(2026-09 逆向实测):
搜索
GET /usercenter/paper/search?type=related&wd=<标题>&rn=20&page_no=N详情GET /scholarai/paper/detail/info?paperId=<id>引文 同搜索接口,wd=citepaperuri:(<id>) / refpaperuri:(<id>)新版搜索接口
/search/api/search必须携带混淆 JS 生成的acs-token,已弃用,上述老接口数据等价。TLS 指纹是核心风控点:python-requests 的 OpenSSL 指纹无论带什么 cookie 都会被
/usercenter系列接口拒(206 + "请输入验证码"),必须用curl_cffi impersonate='chrome'。cookie 自举无需浏览器:先 GET
https://www.baidu.com/拿 5 条 Set-Cookie (BAIDUID/BIDUPSID/PSTM 等)即可通过风控;详情接口更宽松,单条 BAIDUID 就够。风控自愈阶梯:请求被拦 → 重新 cookie 自举重试 → (可选)无头浏览器收割 cookie → 报错。
数据坑已处理:机构字段内嵌
\u0001分隔符、<em>高亮标签、"查看全部>>"截断尾巴; 搜索接口摘要服务端截断,完整摘要由详情接口补全。
已知限制
任意乱词百度都会模糊匹配出结果,调用方需自行比对标题相关性。
论文本身没有参考文献/引文数据时,
get_paper_citations返回业务错误 code=1001,属正常现象。接口为非官方逆向所得,若百度调整风控或字段结构,优先重新抓包核对
baidu_scholar/scholar_client.py顶部的接口说明。
License
Available Tools
3 toolsget_paper_citationsA
按 paperid 返回该论文的参考文献(cite_type=reference)或引证文献(cite_type=citation)列表,字段同搜索结果。论文本身无引文数据时会返回业务错误。
Inputs: paperid (required), cite_type, max_results.
get_paper_detailA
按 paperid 返回论文完整详情:完整摘要、关键词、作者、期刊(卷/期/页码/ISSN/CN)、被引、DOI、基金、阅读量、研究领域,以及知网/万方/维普等全部外部全文链接。paperid 来自 search_papers 返回结果。
Inputs: paperid (required).
search_papersA
按论文标题搜索百度学术(支持部分标题/关键词),返回候选论文列表,含 paperid、标题、作者及机构、年份、期刊、被引、来源链接(知网/万方/维普等)和截断摘要。典型流程:先 search_papers 拿候选列表,自行挑选最匹配的一篇,再调 get_paper_detail 取完整详情。
Inputs: query (required), max_results, auto_detail_on_single.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 3 tools
Each tool has a clearly distinct role: search_papers finds candidate papers, get_paper_detail retrieves full metadata for one paper, and get_paper_citations returns reference/citation lists. There is no meaningful overlap between them.
All tool names follow a consistent snake_case verb_noun pattern: search_papers, get_paper_detail, get_paper_citations. The naming style is uniform and predictable across the server.
Three tools is appropriate for a focused academic search MCP server: discovery, detail retrieval, and citation exploration. Each tool earns its place without redundancy or bloat.
The tool surface covers the core academic paper workflow: searching, viewing full details, and exploring reference/citation relationships. No obvious missing operation is apparent for the stated domain.
Related MCP Connectors
Search OpenAlex for paper titles, DOIs, years, citation counts and open-access flags
Find research papers and arXiv preprints, and get an abstract and free full text from a DOI or id.
Research paper search with real citations and reference formatting for AI assistants
Search arXiv, fetch paper metadata, and read full-text content.
Related MCP Servers
- AlicenseCqualityDmaintenanceEnables real-time search and retrieval of academic paper information from multiple sources, providing access to paper metadata, abstracts, and full-text content when available, with structured data responses for integration with AI models that support tool/function calling.3119AGPL 3.0
- AlicenseBqualityDmaintenanceProvides web search capabilities through Baidu with content fetching and parsing features, allowing LLMs to search the web and extract webpage content.157 PyPI28MIT
- FlicenseAqualityDmaintenanceEnables AI agents to search and retrieve academic papers from China National Knowledge Infrastructure (CNKI), supporting various search types including subject, keyword, author, and DOI lookups.321-
- AlicenseAqualityDmaintenanceEnables AI assistants to search and analyze Google Scholar publications, authors, citations, and download papers.112MIT