Token导航 LogoToken导航TokenDH.com
Agent Deploy Dashboard MCP logo
AI代理stdio官方级别未说明来源级核验

Agent Deploy Dashboard MCP

MCP Server

一个统一的AI代理部署管理平台,支持Vercel、Render、Railway和Fly.io服务的集中管理和REST API操作。

工具数

9

提示词数

0

GitHub Stars

1

资源数

0
AI代理Python多平台支持

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

作者 / 组织

aparajithn

提供方

aparajithn

最后核验

2026/5/17 20:21

运行时

Python

快速接入

先看主来源和安装命令,再打开仓库或文档;下面只保留这个条目的关键接入事实。

命令预览

python3 -m venv venv

详细介绍

代理部署仪表板MCP服务器

统一部署管理 对于AI代理-通过单个MCP+REST API管理Vercel、Render、Railway和Fly.io服务。

![License: MIT](https://opensource.org/licenses/MIT)

特性

🚀 多平台支持 --从一个界面管理Vercel、Render、Railway和Fly.io\ 📊 部署状态 --检查所有平台的部署状态和运行状况\ 📝 统一日志记录 --尾部日志和视图构建日志\ ⚙️ 环境管理 --列出、更新和管理环境变量\ 🔄 重新部署操作 --触发重新部署和回滚\ 💰 x402小额支付 -用于API货币化的内置支付中间件\ 🔒 速率限制 --50个免费请求/IP/天,带付费层支持

快速开始

MCP配置

添加到MCP设置文件(cline_mcp_settings.json 或类似):

{
  "mcpServers": {
    "agent-deploy-dashboard": {
      "url": "https://agent-deploy-dashboard-mcp.onrender.com/mcp"
    }
  }
}

REST API

基本URL: https://agent-deploy-dashboard-mcp.onrender.com

列出所有服务

curl -X GET https://agent-deploy-dashboard-mcp.onrender.com/api/v1/list_all_services

答复:

{
  "success": true,
  "services": [
    {
      "id": "prj_abc123",
      "name": "my-app",
      "platform": "vercel",
      "url": "https://my-app.vercel.app",
      "framework": "nextjs"
    },
    {
      "id": "srv_xyz789",
      "name": "api-service",
      "platform": "render",
      "type": "web_service",
      "region": "oregon"
    }
  ],
  "count": 2
}

获取部署状态

curl -X POST https://agent-deploy-dashboard-mcp.onrender.com/api/v1/get_deploy_status \
  -H "Content-Type: application/json" \
  -d '{
    "platform": "vercel",
    "service_id": "prj_abc123"
  }'

答复:

{
  "success": true,
  "platform": "vercel",
  "service_id": "prj_abc123",
  "deployment_id": "dpl_xyz",
  "status": "READY",
  "url": "https://my-app.vercel.app",
  "created_at": 1709823600000
}

尾部日志

curl -X POST https://agent-deploy-dashboard-mcp.onrender.com/api/v1/tail_logs \
  -H "Content-Type: application/json" \
  -d '{
    "platform": "render",
    "service_id": "srv_xyz789",
    "lines": 50
  }'

获取环境变量

curl -X POST https://agent-deploy-dashboard-mcp.onrender.com/api/v1/get_env_vars \
  -H "Content-Type: application/json" \
  -d '{
    "platform": "vercel",
    "service_id": "prj_abc123"
  }'

答复:

{
  "success": true,
  "platform": "vercel",
  "service_id": "prj_abc123",
  "env_vars": {
    "DATABASE_URL": {
      "value": "[ENCRYPTED]",
      "target": ["production"],
      "type": "encrypted"
    },
    "API_KEY": {
      "value": "abc123",
      "target": ["production", "preview"],
      "type": "plain"
    }
  },
  "count": 2
}

设置环境变量

curl -X POST https://agent-deploy-dashboard-mcp.onrender.com/api/v1/set_env_var \
  -H "Content-Type: application/json" \
  -d '{
    "platform": "render",
    "service_id": "srv_xyz789",
    "key": "NEW_FEATURE_FLAG",
    "value": "true"
  }'

触发器重新部署

curl -X POST https://agent-deploy-dashboard-mcp.onrender.com/api/v1/trigger_redeploy \
  -H "Content-Type: application/json" \
  -d '{
    "platform": "vercel",
    "service_id": "prj_abc123"
  }'

获取构建日志

curl -X POST https://agent-deploy-dashboard-mcp.onrender.com/api/v1/get_build_logs \
  -H "Content-Type: application/json" \
  -d '{
    "platform": "vercel",
    "deploy_id": "dpl_xyz"
  }'

检查健康状况

curl -X POST https://agent-deploy-dashboard-mcp.onrender.com/api/v1/check_health \
  -H "Content-Type: application/json" \
  -d '{
    "url": "https://my-app.vercel.app/health"
  }'

答复:

{
  "success": true,
  "url": "https://my-app.vercel.app/health",
  "status_code": 200,
  "healthy": true,
  "response_time_ms": 142,
  "headers": {
    "content-type": "application/json",
    "x-vercel-id": "sfo1::abc123"
  }
}

定价

免费等级

  • 每个IP每天50个请求
  • 包括所有工具
  • 支持所有平台
  • 无需信用卡

付费层(HTTP 402支付)

免费等级用尽后:

  • 每次请求0.01美元
  • 使用加密钱包通过HTTP 402付款
  • 钱包地址: 0x8E844a7De89d7CfBFe9B4453E65935A22F146aBB
  • 包含 X-Payment 带有付款证明的标题

平台支持

平台列出服务部署状态日志环境变量重新部署生成日志
维塞尔✅ 已满✅ 已满⚠️ 仅构建✅ 已满✅ 已满✅ 满
渲染✅ 已满✅ 已满✅ 已满✅ 已满✅ 已满✅ 满
铁路✅ 基础⏳ 计划⏳ 计划⏳ 计划⏳ 计划⏳ 计划中
Fly.io✅ 基础⏳ 计划⏳ 计划⏳ 计划⏳ 计划⏳ 计划中

✅ = 全面实施\ ⚠️ = 部分实施\ ⏳ = 计划/存根实施

工具参考

1. list_all_services()

列出所有平台上的所有服务。

参数:

退货:

{
  "success": true,
  "services": [...],
  "count": 10,
  "errors": null
}

______________________________________________________________________

2. get_deploy_status(platform, service_id)

检查特定服务的部署状态。

参数:

  • platform (string):平台名称-- vercel, render, railway,或 fly
  • service_id (string):服务/项目ID

退货:

{
  "success": true,
  "platform": "vercel",
  "service_id": "prj_abc",
  "deployment_id": "dpl_xyz",
  "status": "READY",
  "url": "https://...",
  "created_at": 1709823600000
}

______________________________________________________________________

3. tail_logs(platform, service_id, lines=100)

从服务流式传输最近的日志。

参数:

  • platform (string):平台名称
  • service_id (string):服务/项目ID
  • lines (整数,可选):日志行数(默认值:100)

退货:

{
  "success": true,
  "platform": "render",
  "service_id": "srv_xyz",
  "logs": [...],
  "count": 100
}

______________________________________________________________________

4. get_env_vars(platform, service_id)

列出服务的环境变量。

参数:

  • platform (string):平台名称
  • service_id (string):服务/项目ID

退货:

{
  "success": true,
  "platform": "vercel",
  "env_vars": {"KEY": "value"},
  "count": 5
}

______________________________________________________________________

5. set_env_var(platform, service_id, key, value)

更新环境变量。

参数:

  • platform (string):平台名称
  • service_id (string):服务/项目ID
  • key (string):环境变量名称
  • value (string):环境变量值

退货:

{
  "success": true,
  "message": "Environment variable set successfully"
}

______________________________________________________________________

6. trigger_redeploy(platform, service_id)

强制重新部署服务。

参数:

  • platform (string):平台名称
  • service_id (string):服务/项目ID

退货:

{
  "success": true,
  "deployment_id": "dpl_new",
  "message": "Redeploy triggered successfully"
}

______________________________________________________________________

7. get_build_logs(platform, deploy_id)

获取部署的构建日志。

参数:

  • platform (string):平台名称
  • deploy_id (string):部署ID

退货:

{
  "success": true,
  "logs": [...],
  "count": 50
}

______________________________________________________________________

8. check_health(url)

Ping健康端点。

参数:

  • url (string):要检查的URL

退货:

{
  "success": true,
  "status_code": 200,
  "healthy": true,
  "response_time_ms": 142
}

______________________________________________________________________

9. rollback_deploy(platform, service_id, version)

回滚到以前的部署版本。

参数:

  • platform (string):平台名称
  • service_id (string):服务/项目ID
  • version (string):要回滚到的版本/部署ID

退货:

{
  "success": false,
  "error": "Rollback not yet implemented for this platform"
}

______________________________________________________________________

环境变量

通过环境变量配置平台API访问:

# Vercel
VERCEL_TOKEN=your_vercel_token

# Render
RENDER_API_KEY=your_render_api_key

# Railway
RAILWAY_TOKEN=your_railway_token

# Fly.io
FLY_API_TOKEN=your_fly_api_token

# Payment (optional)
X402_WALLET_ADDRESS=0x8E844a7De89d7CfBFe9B4453E65935A22F146aBB

获取您的API令牌:

  • 维塞尔: https://vercel.com/account/tokens
  • 渲染: https://dashboard.render.com/u/settings#api-钥匙
  • 铁路: https://railway.app/account/tokens
  • Fly.io:运行 flyctl auth token

发展

本地设置

# Clone repo
git clone https://github.com/aparajithn/agent-deploy-dashboard-mcp.git
cd agent-deploy-dashboard-mcp

# Create virtual environment
python3 -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate

# Install dependencies
pip install -e ".[dev]"

# Set environment variables
export VERCEL_TOKEN=your_token
export RENDER_API_KEY=your_key

# Run server
uvicorn src.main:app --reload --port 8080

测试终点

# Health check
curl http://localhost:8080/health

# List services (requires platform tokens)
curl http://localhost:8080/api/v1/list_all_services

# Test MCP protocol
curl -X POST http://localhost:8080/mcp \
  -H "Content-Type: application/json" \
  -d '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2024-11-05","capabilities":{},"clientInfo":{"name":"test","version":"1.0.0"}}}'

# List MCP tools
curl -X POST http://localhost:8080/mcp \
  -H "Content-Type: application/json" \
  -d '{"jsonrpc":"2.0","id":2,"method":"tools/list","params":{}}'

码头工人

# Build
docker build -t agent-deploy-dashboard-mcp .

# Run
docker run -p 8080:8080 \
  -e VERCEL_TOKEN=your_token \
  -e RENDER_API_KEY=your_key \
  -e PUBLIC_HOST=localhost \
  agent-deploy-dashboard-mcp

渲染部署

通过Web UI

  1. 将此仓库分叉到您的GitHub帐户
  2. 首选 渲染仪表板
  3. 点击 网络服务
  4. 连接您的GitHub仓库: aparajithn/agent-deploy-dashboard-mcp
  5. 配置:

- 名称: agent-deploy-dashboard-mcp - 运行时:Docker - 区域:俄勒冈州(或最近的) - 实例类型:免费

  1. 添加环境变量:

- VERCEL_TOKEN - RENDER_API_KEY - RAILWAY_TOKEN (可选) - FLY_API_TOKEN (可选) - X402_WALLET_ADDRESS (可选) - PUBLIC_HOST = agent-deploy-dashboard-mcp.onrender.com

  1. 点击 创建Web服务

通过渲染API

curl -X POST https://api.render.com/v1/services \
  -H "Authorization: Bearer $RENDER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "type": "web_service",
    "name": "agent-deploy-dashboard-mcp",
    "repo": "https://github.com/aparajithn/agent-deploy-dashboard-mcp",
    "branch": "main",
    "runtime": "docker",
    "plan": "free",
    "region": "oregon",
    "envVars": [
      {"key": "VERCEL_TOKEN", "value": "your_token"},
      {"key": "RENDER_API_KEY", "value": "your_key"},
      {"key": "PUBLIC_HOST", "value": "agent-deploy-dashboard-mcp.onrender.com"}
    ]
  }'

建筑

agent-deploy-dashboard-mcp/
├── src/
│   ├── main.py              # FastMCP server + REST API
│   ├── tools/
│   │   ├── platforms.py     # Platform API clients (Vercel, Render, etc)
│   │   └── deploy_tools.py  # Tool implementations
│   └── middleware/
│       ├── rate_limit.py    # Rate limiting
│       └── x402.py          # Payment middleware
├── Dockerfile
├── pyproject.toml
└── README.md

技术栈

  • Python 3.11 --现代async/await
  • 快速API -REST API框架
  • FastMCP --MCP协议实现(流式HTTP)
  • httpx --快速异步HTTP客户端
  • 派丹蒂克 --数据验证

API参考文件

部署后,请在以下位置查看交互式API文档:

  • Swagger用户界面: https://agent-deploy-dashboard-mcp.onrender.com/docs
  • OpenAPI JSON: https://agent-deploy-dashboard-mcp.onrender.com/openapi.json

许可证

MIT许可证——见 许可证 了解详情。

支持

  • 问题:
  • 电子邮件:aparajith@dabaracoffee.com

______________________________________________________________________

由Forge(Aparajith的编码代理)为AI代理构建 🤖

目录标签

目录标签

AI代理Python多平台支持本地部署部署管理RESTAPI环境管理

接入字段

传输方式(transport,传输协议)

stdio

鉴权方式(authType,认证方式)

token

运行时(runtime,运行环境)

Python

工具数量(toolCount,工具数)

9

资源数量(resourceCount,资源数)

0

提示词数量(promptCount,提示词数)

0

权限和风险

stdiotoken部署方式未说明

接入前请确认传输方式、认证方式和部署位置,并根据实际工具能力限制访问范围。

安装前确认

不要直接授予不必要的文件、网络或账号权限;先核对安装命令和配置内容。

来源信息

继续浏览同类 MCP