B2Bizzio MCP Server
A foundational MCP server for integrating B2Bizzio business intelligence services with AI applications, providing sample tools, resources, and prompts for extension.
README
B2Bizzio MCP Server
A TypeScript implementation of a Model Context Protocol (MCP) server for B2Bizzio business intelligence services.
Overview
This MCP server provides a foundation for integrating B2Bizzio services with AI applications that support the Model Context Protocol. It includes sample tools, resources, and prompts that can be extended with real business intelligence functionality.
Features
Tools
- get_info: Get information about B2Bizzio services
- echo: Echo a message back to the user
Resources
- welcome: Welcome message and server information
Prompts
- business_analysis: Generate comprehensive business analysis prompts
Prerequisites
- Node.js 18.0.0 or higher
- npm or yarn package manager
Installation
-
Clone or download this project
-
Install dependencies:
npm install -
Build the TypeScript project:
npm run build
Running the Server
As a Standalone Server
npm start
With MCP Clients
Claude Desktop
Add the server to your Claude Desktop configuration:
Windows: %APPDATA%\Claude\claude_desktop_config.json
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
{
"mcpServers": {
"b2bizzio-mcp-server": {
"command": "node",
"args": ["path/to/b2bizzio-mcp/build/index.js"]
}
}
}
VS Code with MCP Extension
The project includes a .vscode/mcp.json configuration file for development and testing.
Development
Project Structure
b2bizzio-mcp/
├── src/
│ └── index.ts # Main server implementation
├── build/ # Compiled JavaScript output
├── .vscode/
│ └── mcp.json # MCP configuration for VS Code
├── package.json
├── tsconfig.json
└── README.md
Available Scripts
npm run build- Compile TypeScript to JavaScriptnpm start- Run the compiled servernpm run dev- Build and run in one command
Extending the Server
Adding New Tools
server.registerTool(
"your_tool_name",
{
description: "Description of your tool",
inputSchema: {
param1: z.string().describe("Parameter description"),
param2: z.number().optional().describe("Optional parameter")
}
},
async ({ param1, param2 }) => {
// Your tool implementation
return {
content: [
{
type: "text",
text: `Result: ${param1}`
}
]
};
}
);
Adding New Resources
server.registerResource(
"resource_name",
"your-protocol://resource-uri",
{
description: "Resource description",
mimeType: "text/plain"
},
async () => {
return {
contents: [
{
uri: "your-protocol://resource-uri",
mimeType: "text/plain",
text: "Resource content"
}
]
};
}
);
Adding New Prompts
server.prompt(
"prompt_name",
"Prompt description",
{
param1: z.string().describe("Parameter description")
},
async ({ param1 }, extra) => {
return {
description: `Generated prompt for ${param1}`,
messages: [
{
role: "user",
content: {
type: "text",
text: `Your prompt text here with ${param1}`
}
}
]
};
}
);
Testing
You can test the server using the MCP Inspector:
npx @modelcontextprotocol/inspector node build/index.js
Architecture
This server is built on:
- @modelcontextprotocol/sdk: Official TypeScript SDK for MCP
- zod: Schema validation and type safety
- TypeScript: Type-safe development environment
The server uses the stdio transport for communication, making it compatible with most MCP clients.
Security Considerations
- The server runs with the permissions of the user account
- All tool executions require explicit approval from the MCP client
- Input validation is performed using Zod schemas
- Error handling prevents information leakage
Contributing
To contribute to this project:
- Fork the repository
- Create a feature branch
- Make your changes
- Add tests if applicable
- Build and test locally
- Submit a pull request
License
MIT License - see LICENSE file for details.
Links
推荐服务器
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。
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。
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。
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。
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。
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。
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。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
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。