AI Material Cabinet MCP
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@AI Material Cabinet MCPsearch my materials for articles about climate change"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
AI材料柜 MCP(stdio)
通过 MCP 让 Cursor / Claude Desktop 等 AI 助手访问本机 AI 材料柜:检索、读写正文、创建文档等。
产品主站:https://cailiaogui.leanmtech.cn
安装与 Windows 发行包:https://cailiaogui.leanmtech.cn/download/mcp
相关开源:剪藏油猴脚本 ai-cailiaogui-clip
依赖
须先安装并启动材料柜(本机 HTTP API,默认
http://127.0.0.1:9000/app/desktop)Python ≥ 3.10(源码运行);或使用官网 Windows zip(内含
local-app-mcp.exe)
Related MCP server: Document Search MCP Server
工具
工具 | 说明 |
| 全库混合检索(FTS + 向量) |
| 目录范围内检索 |
| 浏览虚拟目录 |
| 材料元信息 |
| 读写正文 |
| 新建文档 |
| 按 chunk_id 批量拉块正文 |
环境变量
变量 | 默认 | 说明 |
|
| 材料柜 API 根(须含 |
|
| HTTP 超时(秒) |
Host 配置里的 env 优先于本地 .env。示例见 .env.example。
源码安装与运行
pip install -e .
# 另开终端启动材料柜后:
python -m local_app_mcpMCP Host 配置示例
见 examples/mcp-host.example.json。开发态也可:
{
"mcpServers": {
"local-app-cabinet-mcp": {
"command": "python",
"args": ["-m", "local_app_mcp"],
"env": {
"LOCAL_APP_BASE_URL": "http://127.0.0.1:9000/app/desktop"
}
}
}
}许可
本仓库自有代码:Unlicense(见 LICENSE)
「AI 材料柜」「材料柜」等产品名与商标归产品方所有;本开源仓库不授予商标使用权
相关链接
This server cannot be deployed
Maintenance
Related MCP Connectors
Self-hosted AI workspace: semantic RAG document search, long-term memory, and AI chat via MCP.
- LogRackOAuthai.lograck
Shared memory for your AI tools: tasks, notes and context every tool can read and write over MCP.
Persistent memory, knowledge graph, task management and more for AI agents via MCP.
A second brain for your AI agent. Shared memory for your team's AI agents, plus public and private knowledge bases — works with ChatGPT, Claude, Cursor and any MCP client.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables AI tools to query a user's private, locally stored memories (notes, documents) with source citations, using the MCP protocol.29 npmMIT
- FlicenseNot gradedqualityCmaintenanceAn MCP server that enables Claude Desktop or Claude Code to ingest and search local documents using vector embeddings, returning relevant chunks as tool results for the model to reason over.-
- AlicenseNot gradedqualityBmaintenanceEnables AI tools to securely search and retrieve relevant, source-attributed chunks from private local documents via MCP, without sending document content to third-party services.2MIT
- FlicenseNot gradedqualityAmaintenanceExposes a local hybrid (vector + BM25) index of scattered notes, docs, PDFs, and chat logs to AI hosts like Claude Desktop, Cursor, and Cline, letting agents search and get cited answers. It publishes a set of tools, resources, and prompts so any MCP-compatible client can query that knowledge base with section-level citations.-