mr-model MCP Server
Standalone Model Context Protocol (MCP) server for the mr-model platform, offering 5 tools to query video lists, comments, OCR transcripts, search, and blogger opinions via a web API.
README
mr-model MCP 独立服务
mr-model 平台的 MCP (Model Context Protocol) 独立服务,从主仓 mr-model 拆分出来。
- 主服务(8866):
mrmodel.cesario.top—— Web/API/会员/支付/推送 - MCP 服务(本仓,8868):
mcp.cesario.top—— 5 个 Model Context Protocol 工具
为什么拆
| 动机 | 详情 |
|---|---|
| 稳定独立升级 | MCP 想走自己的迭代节奏,不被主站 PR 阻塞 |
| 未来国内腾讯云迁移 | 必须先拆仓,否则主站 + MCP 一起迁成本翻倍 |
| 业务已 90% 独立 | systemd / 端口 / 域名 / Caddy / Restart 早独立,只差代码仓 + venv |
仓库结构
mr-model-mcp/
├── .env.example # 环境变量模板(真实 .env 不入库)
├── README.md # 本文件
├── requirements.txt # 5 个精简依赖
├── deploy-mcp.sh # 拉码/venv/语法/restart/verify/失败回滚
├── backend/
│ ├── mcp_server.py # 1081 行,5 tools
│ ├── mcp_auth.py # Bearer token 鉴权
│ ├── database.py # 最小版(只 get_connection)
│ ├── user_service.py # 最小版(只 _now_cst)
│ ├── membership_service.py # 最小版(只 get_active_membership)
│ ├── agent_service.py # 最小版(只 _labelize_text)
│ ├── config.py # 最小版(MCP 需要的常量)
│ └── mrmodel_common.py # = 复制自主仓 addons/_mcp_shared/mrmodel_common.py
└── deploy/
├── mr-model-mcp.service # systemd unit
└── mcp.cesario.top.conf # Caddy 反代配置
与主仓的共享代码
backend/mrmodel_common.py 是复制自主仓 backend/addons/_mcp_shared/mrmodel_common.py 的副本。
DRY 务实策略:主仓是源头,MCP 仓是副本,手动 cp 同步(见 [[../mr-model/docs/mr-model-扩展包架构方案-2026-08-19]] §C 章节)。
每次主仓改源头:
- 主仓 commit + push
cp backend/addons/_mcp_shared/mrmodel_common.py ../mr-model-mcp/backend/mrmodel_common.py- MCP 仓 commit + push
- 部署顺序:先主仓 deploy(schema 可能变)→ 再 MCP 仓 deploy-mcp.sh
开发(本地)
# 准备 venv(首次)
python3 -m venv venv
venv/bin/pip install --upgrade pip
venv/bin/pip install -r requirements.txt
# 启动(默认 127.0.0.1:8868)
cp .env.example .env # 按需改 DATABASE_PATH 指向主仓 DB
venv/bin/python3 backend/mcp_server.py
# 健康检查
curl http://127.0.0.1:8868/healthz
部署(A1)
# 首次部署
sudo cp deploy/mr-model-mcp.service /etc/systemd/system/
sudo systemctl daemon-reload
sudo systemctl enable mr-model-mcp
bash deploy-mcp.sh # 第一次跑会建 venv(60-120s)
# 后续升级
bash deploy-mcp.sh
deploy-mcp.sh 7 步:备份 service → 拉码 → venv → 语法检查 → 重启 → 健康检查 → 失败回滚。
故障排查
| 症状 | 排查 |
|---|---|
| 8868 起不来 | journalctl -u mr-model-mcp -n 50 看 systemd 日志 |
| healthz 5s 内非 200 | deploy-mcp.sh 自动 git revert + restart |
| 5 tools 全 401 | 主仓 sessions 表无有效 token(先登录主站拿 token 再试) |
| SQLite lock | 走主仓 mrmodel.db,并发已被 busy_timeout=15s 兜底 |
| Caddy 502 | systemctl status caddy + caddy reload |
5 个 MCP 工具
| 工具 | 用途 |
|---|---|
query_video_list |
按博主/标签/时间窗查视频列表 |
query_comments |
查视频评论(带点赞/时间/AI 标签) |
search_video_transcripts |
全文检索视频 OCR 文本 |
search_videos |
综合搜索(标题/简介/标签) |
query_blogger_opinions |
查博主历史观点(用于辩证法) |
详见 backend/mcp_server.py 每 tool 的 docstring。
维护
- 版本:跟随主仓节奏,无独立版本号
- 回滚:
git revert HEAD+bash deploy-mcp.sh - 监控:主仓 mcp_addon
/api/_addon/mcp/healthz探活 8868
创建于 2026-08-19(mr-model B 档 MCP 拆分)
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.