Budget Allocator

Budget Allocator

An interactive tool for visualizing and managing budget allocations across business categories with real-time charts and industry benchmarks. It allows users to adjust spending distributions and compare them against historical trends and startup stage data.

Category
访问服务器

README

Example: Budget Allocator App

An interactive budget allocation tool demonstrating real-time data visualization with MCP Apps.

<table> <tr> <td><a href="https://modelcontextprotocol.github.io/ext-apps/screenshots/budget-allocator-server/01-initial.png"><img src="https://modelcontextprotocol.github.io/ext-apps/screenshots/budget-allocator-server/01-initial.png" alt="Initial" width="100%"></a></td> <td><a href="https://modelcontextprotocol.github.io/ext-apps/screenshots/budget-allocator-server/02-over-budget.png"><img src="https://modelcontextprotocol.github.io/ext-apps/screenshots/budget-allocator-server/02-over-budget.png" alt="Over budget" width="100%"></a></td> <td><a href="https://modelcontextprotocol.github.io/ext-apps/screenshots/budget-allocator-server/03-tech-heavy.png"><img src="https://modelcontextprotocol.github.io/ext-apps/screenshots/budget-allocator-server/03-tech-heavy.png" alt="Tech-heavy" width="100%"></a></td> </tr> </table>

MCP Client Configuration

Add to your MCP client configuration (stdio transport):

{
  "mcpServers": {
    "budget-allocator": {
      "command": "npx",
      "args": [
        "-y",
        "--silent",
        "--registry=https://registry.npmjs.org/",
        "@modelcontextprotocol/server-budget-allocator",
        "--stdio"
      ]
    }
  }
}

Local Development

To test local modifications, use this configuration (replace ~/code/ext-apps with your clone path):

{
  "mcpServers": {
    "budget-allocator": {
      "command": "bash",
      "args": [
        "-c",
        "cd ~/code/ext-apps/examples/budget-allocator-server && npm run build >&2 && node dist/index.js --stdio"
      ]
    }
  }
}

Features

  • Interactive Sliders: Adjust budget allocation across 5 categories (Marketing, Engineering, Operations, Sales, R&D)
  • Donut Chart: Real-time visualization of allocation distribution using Chart.js
  • Sparkline Trends: 24-month historical allocation data per category
  • Percentile Badges: Compare your allocation vs. industry benchmarks
  • Stage Selector: Switch between Seed, Series A, Series B, and Growth benchmarks
  • Budget Presets: Quick selection of $50K, $100K, $250K, or $500K totals

Running

  1. Install dependencies:

    npm install
    
  2. Build and start the server:

    npm run start:http  # for Streamable HTTP transport
    # OR
    npm run start:stdio  # for stdio transport
    
  3. View using the basic-host example or another MCP Apps-compatible host.

Architecture

Server (server.ts)

Exposes a single get-budget-data tool that returns:

  • Category definitions with colors and default allocations
  • Historical data (~120 data points) - 24 months of allocation history per category
  • Industry benchmarks (~60 data points) - Aggregated percentile data by company stage

The tool is linked to a UI resource via _meta.ui.resourceUri.

App (src/mcp-app.ts)

  • Uses Chart.js for the donut chart visualization
  • Renders sparkline trends using inline SVG
  • Computes percentile rankings client-side from benchmark data
  • Updates all UI elements reactively on slider changes

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选