About
lumi ai mcp server
README
对 Hermes Agent 暴露带用户隔离语义的 WeKnora MCP 代理工具(错题库检索、错题列表、作业统计、小孩列表)。本服务独立于主后端部署,对 PostgreSQL 只读。
工具列表
| 工具 | 说明 |
|---|---|
search_user_mistakes |
按学科检索当前小孩的错题库(WeKnora 混合检索 + 按小孩过滤) |
list_user_mistakes |
从 PostgreSQL 列出最近错题 |
get_homework_summary |
作业检查统计 |
list_user_students |
列出当前用户的小孩 |
web_search |
网络搜索(自建 SearXNG 聚合搜索,JSON API),替代易被反爬的裸爬 |
read_web_page |
通过 r.jina.ai 阅读器代理读取网页为 markdown,可打开电商等反爬页面 |
前 4 个工具调用需传 conversation_id,服务根据会话解析用户,实现用户隔离;web_search / read_web_page 是公共工具,无需 conversation_id。
配置
复制 .env.example 为 .env,修改:
DATABASE_URL:Lumi 主库连接串(建议配只读账号)WEKNORA_BASE_URL/WEKNORA_API_KEY:WeKnora 连接SEARXNG_BASE_URL:web_search 工具使用的自建 SearXNG 地址(需已开启 json 输出格式)MCP_PROXY_API_KEY:SSE 接口鉴权密钥,Hermes 通过Authorization: Bearer传递
启动
Docker(推荐)
本服务有独立的 docker-compose.yml,通过 external 方式加入主项目的 lumi-network(访问 PostgreSQL、被 Hermes 访问),因此需先启动主项目栈(根目录 docker-compose up -d):
cd mcp-server
cp .env.example .env # 首次,按需修改
docker-compose up -d --build
本地开发
cd mcp-server
python -m venv venv
# Windows: venv\Scripts\activate macOS/Linux: source venv/bin/activate
pip install -r requirements.txt
# SSE 模式,端口 8001
uvicorn app.mcp_sse:mcp_sse_app --host 0.0.0.0 --port 8001 --reload
# stdio 模式(供 Hermes 作为子进程启动)
python -m app.mcp_proxy_server
Hermes 接入
mcp_servers:
lumi_weknora_proxy:
transport: sse
# Docker 网络内使用服务名;本机直连用 http://localhost:8001/sse
url: http://mcp-server:8001/sse
headers:
Authorization: "Bearer 与 MCP_PROXY_API_KEY 相同的值"
维护约定
app/models.py 是主库 5 张表(conversations、students、user_knowledge_bases、homework_checks、homework_mistakes)的只读镜像。新增迁移脚本或 backend/app/models.py 中对应表结构变更时,必须同步修改本文件。
Installing Lumi
This server has no published package — it is built from source. Open the repository and follow its README.
▸ github.com/tnyi/lumi-mcp-serverFAQ
Is Lumi MCP free?
Yes, Lumi MCP is free — one-click install via Unyly at no cost.
Does Lumi need an API key?
No, Lumi runs without API keys or environment variables.
Is Lumi hosted or self-hosted?
Self-hosted: the server runs locally on your machine via the install command above.
How do I install Lumi in Claude Desktop, Claude Code or Cursor?
Open Lumi on unyly.org, pick your client tab (Claude Desktop, Claude Code, Cursor) and press Install — the config is generated automatically, no JSON editing.
Related MCPs
Fetch
Web content fetching and conversion for efficient LLM usage.
Roblox Studio
Enables AI coding tools to control Roblox Studio for workspace exploration, instance manipulation, and script management. It provides tools for playtesting, sce
by paralovAWS KB Retrieval
Retrieval from AWS Knowledge Base using Bedrock Agent Runtime.
by modelcontextprotocolSpring AI MCP Server
Provides auto-configuration for setting up an MCP server in Spring Boot applications.
llm-analysis-assistant
A very streamlined mcp client that supports calling and monitoring stdio/sse/streamableHttp, and can also view request responses through the /logs page. It also
by xuzexin-hzMCP-Agent
A simple, composable framework to build agents using Model Context Protocol by [LastMile AI](https://www.lastmileai.dev)
by lastmile-aiSpring AI MCP Client
Provides auto-configuration for MCP client functionality in Spring Boot applications.
mcp.natoma.ai
A Hosted MCP Platform to discover, install, manage and deploy MCP servers by [Natoma Labs](https://www.natoma.ai)
MCPHub
Website to list high quality MCP servers and reviews by real users. Also provide online chatbot for popular LLM models with MCP server support.
MCP Servers Rating and User Reviews
Website to rate MCP servers, write authentic user reviews, and [search engine for agent & mcp](http://www.deepnlp.org/search/agent)
Compare Lumi with
Not sure what to pick?
Find your stack in 60 seconds
Author?
Embed badge for your README
Browse similar
All ai MCPs
