KnowS MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| KNOWS_API_KEY | Yes | KnowS API 密钥 | |
| KNOWS_API_HOST | No | API 地址,默认 https://dev-api.nullht.com | https://dev-api.nullht.com |
Capabilities
Features and capabilities supported by this server
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| ai_searchC | AI 检索:用户提问,返回与该问题相关的医学证据列表 |
| evidence_summaryB | 对单篇证据进行 AI 概要总结 |
| all_evidence_summaryA | 获取所有证据的单篇 AI 总结(收集完整的流式响应后返回) |
| evidence_highlightB | 返回单篇证据被引用的原文部分(高亮内容) |
| answerB | 基于问题和检索出来的证据,生成场景总结(非流式) |
| answer_streamC | 基于问题和检索出来的证据,生成场景总结(收集完整的流式响应后返回) |
| auto_taggingC | 对证据进行自动化标签提取(如研究类型、疾病领域、样本量等) |
| get_paper_enA | 获取英文文献的详细信息(标题、摘要、影响因子、分区等) |
| get_paper_cnC | 获取中文文献的详细信息 |
| get_guideC | 获取医学指南的详细信息 |
| get_meetingC | 获取医学会议记录的详细信息 |
| list_questionsC | 获取用户的历史提问列表,支持时间范围和分页 |
| list_interpretationsC | 获取用户的单篇文献 AI 解读历史记录,支持时间范围和分页 |
| create_evidence_by_pdfB | 通过上传 PDF 文件创建新的证据 |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Latest Blog Posts
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/PancrePal-xiaoyibao/MCP-KnowS-AI'
If you have feedback or need assistance with the MCP directory API, please join our Discord server