cnki-search
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| searchA | Search 知网空间 metadata. query may be empty if author or advisor is set. Args: query: Search text. Exact title works best with field=title. field: theme (主题), title (篇名), keyword (关键词), content (全文), summary (摘要). page: Result page, starting at 1. author: Author name (作者). advisor: Thesis advisor (导师). year: Publication or degree year, e.g. 2023. kind: all, journal (期刊), thesis (博硕), phd (博士), master (硕士). sort: relevance, date, downloads, cites. |
| get_recordA | Fetch metadata from a 知网 / CDMD / cnki.com.cn record page. Not a PDF download. Args: url: A CNKI Space or CDMD detail URL returned by search. |
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 2 tools
The two tools are distinctly separated: 'search' performs queries across metadata fields, while 'get_record' fetches details from a specific URL returned by search. There is no functional overlap between them.
Both tool names follow a clear lowercase_with_underscores convention and use verb-first naming ('search', 'get_record'). The pattern is consistent and predictable.
With only two tools, the server is minimal. The scope (searching and retrieving CNKI records) is narrow enough to justify this count, but it borders on being too thin for a productive search API.
The server covers the essential metadata search and record retrieval workflows. It lacks features like citation export or full-text download, but for its stated purpose of metadata access, the coverage is adequate with only minor gaps.