modelscope·@PancrePal-xiaoyibao/get-biji-dev-by-gemini3pro
暂无描述。
<a name="english"></a>
A Model Context Protocol (MCP) server for integrating with Get Notes API. This server provides tools to search and recall knowledge from your Get Notes knowledge base.
npm install
.env file from example:
cp .env.example .env
.env:
GET_API_KEY=T0TR1HWqw+tL00gVc5PPoXDnGIUIuPw7QCBeb1dMC6afCojR9WpHyuZicEFJjkMg3oZYS0HB/S3vqOj7+0e5FGoVtYuv938zkR8=
GET_NOTE_TOPIC_ID=RYk1kmRJ
You can run the server directly without installing it using npx:
npx get_notebook_mcp_server
Option 1: Single Knowledge Base (Simple Setup)
For a single knowledge base, add this to your claude_desktop_config.json:
{
"mcpServers": {
"get-notes": {
"command": "npx",
"args": ["-y", "get_notebook_mcp_server"],
"env": {
"GET_API_KEY": "T0TR1HWqw+tL00gVc5PPoXDnGIUIuPw7QCBeb1dMC6afCojR9WpHyuZicEFJjkMg3oZYS0HB/S3vqOj7+0e5FGoVtYuv938zkR8=",
"GET_NOTE_TOPIC_ID": "RYk1kmRJ"
}
}
}
}
Option 2: Multiple Knowledge Bases (Grouped Configuration - Recommended)
For multiple knowledge bases sharing the same API key, use grouped configuration. The system will automatically expand them into individual knowledge bases:
{
"mcpServers": {
"get-notes": {
"command": "npx",
"args": ["-y", "get_notebook_mcp_server"],
"env": {
"GET_KNOWLEDGE_BASES": "[{\"id\":\"medical_group\",\"name\":\"Medical Knowledge Bases\",\"config\":{\"api_key\":\"T0TR1HWqw+tL00gVc5PPoXDnGIUIuPw7QCBeb1dMC6afCojR9WpHyuZicEFJjkMg3oZYS0HB/S3vqOj7+0e5FGoVtYuv938zkR8=\",\"topics\":[{\"id\":\"kb_pancreatic_trials\",\"name\":\"Tumor Clinical Trials KB\",\"topic_id\":\"RYk1kmRJ\"},{\"id\":\"kb_patient_experience\",\"name\":\"Patient Experience KB\",\"topic_id\":\"mnyV9OjY\"}]}}]"
}
}
}
}
This configuration will be automatically expanded into two independent knowledge bases: kb_pancreatic_trials and kb_patient_experience.
Option 3: Using Local Configuration File (Recommended for Development)
Create a knowledge_bases.json file in your project root:
[
{
"id": "demo_group",
"name": "Sam's Knowledge Bases",
"description": "Knowledge bases sharing the same API Key",
"config": {
"api_key": "T0TR1HWqw+tL00gVc5PPoXDnGIUIuPw7QCBeb1dMC6afCojR9WpHyuZicEFJjkMg3oZYS0HB/S3vqOj7+0e5FGoVtYuv938zkR8=",
"api_endpoint": "https://open-api.biji.com/getnote/openapi",
"topics": [
{
"id": "kb_pancreatic_trials",
"name": "Tumor Clinical Trials Knowledge Base",
"description": "Knowledge base about tumor clinical trials",
"topic_id": "RYk1kmRJ"
},
{
"id": "kb_patient_experience",
"name": "Patient Experience Information",
"description": "Patient experience info including guidelines and treatment experiences",
"topic_id": "mnyV9OjY"
}
]
}
}
]
Then configure Claude Desktop to use the local file:
{
"mcpServers": {
"get-notes": {
"command": "npx",
"args": ["-y", "get_notebook_mcp_server"]
}
}
}
Claude automatically selects the appropriate knowledge base - no manual selection needed!
Workflow:
list_knowledge_bases: Views all available knowledge baseskb_pancreatic_trials)search_knowledge: Passes the selected kb_id and the questionUsers can also specify explicitly:
This way Claude knows exactly which knowledge base to use.
node index.js
You can test the MCP server interactively using the MCP Inspector:
npx @modelcontextprotocol/inspector node index.js
list_knowledge_basesList all available knowledge bases with their IDs, names, and descriptions.
Parameters: None
Returns: Array of knowledge base information (without sensitive API keys)
search_knowledgeSearch the knowledge base with AI processing.
Parameters:
kb_id (string, optional): Knowledge base ID. If not provided, uses the first configured KB.question (string, required): The question to ask.deep_seek (boolean): Enable deep thinking mode (default: false).history (array): Chat history for context.recall_knowledgeRaw recall from knowledge base without AI synthesis.
Parameters:
kb_id (string, optional): Knowledge base ID. If not provided, uses the first configured KB.question (string, required): The question or query.top_k (number): Number of results to return (default: 10).intent_rewrite (boolean): Enable intent rewrite (default: false).npm test
src/api: API client implementationsrc/utils: Util…通过向量嵌入技术,为项目提供记忆库和RAG上下文支持,以增强代码理解和管理,并与RooCode和Cline集成。
通过全局和分支特定的记忆库,管理跨 Claude AI 会话的项目文档和上下文的服务器,通过结构化的 JSON 文档存储实现一致的知识管理。
快递100 MCP Server提供快递信息查询、快递运费预估比价、快递时效查询(含发货前时效查询与在途动态时效查询)等功能。
一种模型上下文协议服务器,通过在语言模型交互之间高效缓存数据来减少令牌消耗,自动存储和检索信息以最小化冗余令牌使用。
通过集成DeepSeek R1的高级推理引擎以处理复杂推理任务,从而增强Claude推理能力的服务器。
通过简化的SOLID架构,启用提示词的创建、管理和模板化,允许用户按类别组织提示词并在运行时填充模板。