academic-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| ACADEMIC_HEADLESS | No | Set to 'false' to run browser in non-headless mode for login | true |
| ACADEMIC_EXPORT_DIR | No | Override path for export directory | |
| ACADEMIC_LIBRARY_DB | No | Override path for the SQLite library database |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| extensions | {
"io.modelcontextprotocol/ui": {}
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_cnkiA | 搜索中国知网 (CNKI) 学术论文。 Args: keyword: 搜索关键词 search_type: 搜索类型 (主题/篇名/关键词/作者/单位/DOI/摘要/全文) page_count: 搜索页数 (1-5,每页约20条) sort_by: 排序方式 (相关度/被引/下载/发表时间) Returns: JSON 格式的搜索结果列表 |
| get_paper_detailA | 获取知网论文的详细信息。 Args: url: 论文详情页 URL(来自 search_cnki 的结果) Returns: JSON 格式的论文详细信息(标题/作者/摘要/关键词/DOI 等) |
| download_paperA | 下载知网论文 PDF/CAJ。需要已登录(机构 IP 认证或账号登录)。 Args: url: 论文详情页 URL save_dir: 保存目录,默认 ~/.academic-mcp/downloads/ Returns: 下载结果(文件路径或错误信息) |
| login_cnkiA | 打开知网登录页面进行手动登录。 首次使用时调用一次,之后登录态会自动持久化。 会打开一个可见的浏览器窗口。 Returns: 登录状态信息 |
| check_cnki_statusA | 检查知网连接状态和登录状态。 Returns: 当前连接状态、登录状态、IP 认证信息 |
| search_wosA | 在 Web of Science 中进行高级检索。 使用 WoS 字段标签语法,例如: TS=(machine learning AND finance) AU=(Zhang Wei) AND PY=(2020-2025) TI=(neural network) AND SO=(Nature) 常用字段标签: TS=主题, TI=标题, AU=作者, SO=期刊, DO=DOI, PY=年份, AB=摘要, AK=作者关键词, OG=机构, FU=基金 Args: query: WoS 高级检索查询语句 sort_by: 排序 (relevance/date_newest/date_oldest/cited/usage) page_count: 页数 (1-5,每页约10-50条) Returns: JSON 格式的搜索结果列表 |
| get_wos_detailA | 获取 Web of Science 论文的完整记录。 Args: url: WoS 论文详情页 URL(来自 search_wos 的结果) Returns: JSON 格式的论文完整记录(标题/作者/摘要/关键词/DOI/被引/基金等) |
| export_wosA | 导出当前 WoS 搜索结果的引文数据。需要先运行 search_wos。 Args: format: 导出格式 (bibtex/ris/csv/excel/plaintext) count: 导出记录数 (1-1000,默认50) Returns: 下载结果(文件路径或错误信息) |
| login_wosA | 打开浏览器通过大学代理登录 Web of Science。 首次使用时调用一次,之后登录态会自动持久化。 会打开一个可见的浏览器窗口。 Returns: 登录状态信息 |
| check_wos_statusA | 检查 Web of Science 连接和认证状态。 Returns: 连接状态、代理认证状态 |
| debug_wosA | 调试工具:截图并分析 WoS 页面的 DOM 结构。 用于诊断选择器失效等问题。 Args: target: 要调试的页面 (advanced_search / home / current_url) Returns: 页面截图路径 + DOM 结构摘要(表单元素、按钮等) |
| search_deepxivC | Search open literature through DeepXiv and return normalized JSON. |
| get_deepxiv_paperA | Read an arXiv paper via DeepXiv: brief, metadata, preview, raw, or json. |
| get_deepxiv_pmcB | Read PMC metadata or full structured content via DeepXiv. |
| check_deepxiv_statusA | Check whether deepxiv-sdk is importable and whether a token is configured. |
| search_literatureB | Search literature across open DeepXiv sources and optional CNKI/WoS. |
| save_papers_to_collectionA | Save normalized papers JSON into a named local collection. |
| list_paper_collectionsB | List local paper collections. |
| get_paper_collectionB | Return one local paper collection with normalized records. |
| export_paper_collectionC | Export a collection as bibtex, ris, csv, jsonl, json, or md. |
| check_academic_sourcesB | Check open-source availability and optionally CNKI/WoS browser auth status. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| get_search_types | 可用的搜索类型 |
| get_wos_field_tags | WoS 高级检索字段标签参考 |
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/dopawei/academic-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server