CNKI-Enhanced-MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CNKI_MCP_DATA_DIR | Yes | Absolute path to the data directory (e.g., /ABSOLUTE/PATH/CNKI-Enhanced-MCP/.cnki-data). | |
| PLAYWRIGHT_BROWSERS_PATH | Yes | Absolute path to the Playwright browsers directory (e.g., /ABSOLUTE/PATH/CNKI-Enhanced-MCP/.playwright-browsers). |
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
} |
| logging | {} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| extensions | {
"io.modelcontextprotocol/ui": {}
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| cnki_loginA | 打开可见 Playwright 浏览器，检测校园网权限或等待用户手动完成账号/机构登录。 |
| cnki_session_statusA | 检查 CNKI 可访问性、机构/账号登录状态和验证码状态。 |
| cnki_searchA | 内部规划多个查询，去重，并结合相关性、摘要、来源层级、文献类型和影响力重新排序。 |
| cnki_structured_searchB | 独立结构化检索工具：严格执行调用者指定的 CNKI 字段、布尔关系和匹配方式。 |
| cnki_get_metadataA | 按完整标题或 search_id 统一读取单篇/批量论文元数据。 |
| cnki_download_paperA | 使用当前合法 CNKI 权限下载论文，文件始终保存在工作区项目目录内。 |
| cnki_read_online_htmlA | 使用当前合法权限读取全部或分段的 CNKI 在线 HTML 正文；不处理 PDF/CAJ。 |
| cnki_export_citationsA | 将缓存题录导出为常用引文、BibTeX/RIS/EndNote/CSL-JSON/CSV 或安全自定义模板。 |
| cnki_link_referencesA | 把文本中《书名号》标出的论文标题高置信度匹配到 CNKI 详情页并添加 Markdown 链接。 |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 9 tools
Most tools target distinct operations (search, download, login, export), but cnki_search and cnki_structured_search have overlapping purposes. The descriptions clarify that one is a smart aggregated search while the other is strict structured search, so agents can differentiate with careful reading.
All tools share the cnki_ prefix and mostly follow a verb_noun pattern (download_paper, get_metadata, export_citations). cnki_login is a bare verb and cnki_session_status is noun_noun, which deviate slightly from the predominant convention, but the pattern is still predictable.
Nine tools is well within the ideal range for a domain-specific server. Each tool addresses a necessary step in the CNKI research workflow—searching, retrieving metadata, reading, downloading, linking, exporting, and session management—without redundancy.
The tool set covers the full lifecycle of working with CNKI papers: authentication, searching, structured retrieval, metadata fetching, HTML reading, PDF download, citation export, and reference linking. There are no obvious dead ends or missing core operations for the stated purpose.