Dashboard MCP
Dashboard MCP
MCP 连接器 + 只读 Web 查看器,用于完全由 AI 代理控制的仪表板。支持任意数量的独立仪表板——每个都有自己的 slug、文件和 URL /d/<slug>。
在线服务:https://dashboard.89-207-254-32.nip.io
仪表板列表:
/单个仪表板(只读,每 5 秒自动刷新):
/d/<slug>JSON API(同样只读):
/api/dashboards、/api/dashboards/<slug>MCP 端点(需要 OAuth):
/mcp
工作原理
mcp_app.py—— 创建唯一的MCPServer,支持启用 OAuth(如果设置了OAUTH_*环境变量)或禁用(用于本地开发)。tools.py—— MCP 工具(@mcp.tool()):list_dashboards、create_dashboard、get_dashboard、update_dashboard_meta、delete_dashboard、add_widget、update_widget、remove_widget、reorder_widgets、replace_widgets。这就是代理管理仪表板所用到的东西。它们受/mcp上的 OAuth 保护。web.py—— 公共 HTML 页面和 JSON API(@mcp.custom_route,根据 SDK 文档不要求授权)——供人们在浏览器中查看。models.py—— pydantic 小部件 schema:text、list、stats、progress、chart。store.py—— 文件存储,一个仪表板对应一个 JSON 文件,存放在data/dashboards/。
小部件类型
{"type": "text", "title": "Заметка", "body": "..."}
{"type": "list", "title": "Задачи", "ordered": false, "items": [{"label": "...", "value": "...", "note": "..."}]}
{"type": "stats", "title": "Метрики", "items": [{"label": "MRR", "value": "128k", "unit": "₽", "delta": "+12%", "trend": "up"}]}
{"type": "progress", "title": "Прогресс", "items": [{"label": "Q3", "value": 62, "max": 100, "color": "#395b4b"}]}
{"type": "chart", "title": "Динамика", "chartType": "line", "labels": ["Пн","Вт"], "series": [{"name": "Заказы", "data": [3, 7]}]}通用字段:title(可选)、size:sm|md|lg|full(网格中的宽度)。
本地运行
pip install -r requirements.txt
cp .env.example .env # можно оставить OAUTH_* пустыми — сервер поднимется без auth
MCP_TRANSPORT=streamable-http python server.py
# либо просто `python server.py` для stdio (claude mcp add / MCP Inspector)如何在 Claude 中接入连接器
服务器上已创建静态 OAuth 客户端(Client ID / Secret 已单独发放)。
在 Claude 中:Settings → Connectors → Add custom connector。
URL:
https://dashboard.89-207-254-32.nip.io/mcpClient ID / Client Secret —— 按部署时发放的填写。
授权后,代理即可使用
tools.py中的工具。
部署
生产服务器会自行拉取此仓库:deploy/deploy.sh 每 2 分钟通过 cron 运行一次,比较本地 HEAD 与 origin/main,如果有新提交——执行 git reset --hard + docker compose up -d --build + 检查 /healthz。只需 git push 到 main——生产环境中的变更将在约 2 分钟内自动生效。
最后验证的部署:2026-08-19T15:29:01Z
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
Persistent docs and memory for AI agents — read, write, organize & search a shared workspace.
Renders interactive Chart.js charts and dashboards inline in AI conversations.
Shared, governed long-term memory for AI agents across tools and sessions via MCP and REST.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
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/DUROV-OS/dashboard-MCP'
If you have feedback or need assistance with the MCP directory API, please join our Discord server