MCP Server

MCP Server

A remote Model Context Protocol server that enables AI assistants to interact with external services through standardized JSON-RPC, providing tools for basic operations and conversation archiving.

Category
访问服务器

README

MCP Server

A remote Model Context Protocol (MCP) server implementation that provides tools for AI assistants to interact with external services and perform various operations.

Overview

This MCP server implements the Model Context Protocol specification, allowing AI assistants to access custom tools and capabilities through a standardized JSON-RPC interface. The server runs on port 8000 and provides several built-in tools for basic operations and conversation archiving.

Features

  • JSON-RPC 2.0 Protocol: Full implementation of the MCP specification
  • Built-in Tools:
    • add: Perform basic arithmetic operations
    • reverse: Reverse text strings
    • save_conversation: Archive conversations to aiarchives.duckdns.org
  • Health Monitoring: Built-in health check endpoint
  • CORS Support: Cross-origin resource sharing enabled
  • Error Handling: Comprehensive error handling with proper JSON-RPC error codes

Prerequisites

  • Node.js (version 16 or higher)
  • npm or yarn package manager

Usage

Configuring Claude Desktop

To use this MCP server with Claude Desktop, you need to add it to your Claude Desktop configuration file.

Finding the Configuration File

  1. Open Claude Desktop
  2. Go to Settings (gear icon in the bottom left)
  3. Click on Advanced in the left sidebar
  4. Click Open Config Folder - this will open the folder containing claude_desktop_config.json
  5. Open the claude_desktop_config.json file in your preferred text editor

Adding the MCP Server Configuration

Add the following configuration to your claude_desktop_config.json file:

{
  "mcpServers": {
    "aiarchives": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://aiarchives.duckdns.org/mcp",
        "--allow-http",
        "--transport",
        "http-only"
      ]
    }
  }
}

Note: Make sure to restart Claude Desktop after making changes to the configuration file.

Server Access

This MCP server is hosted remotely and accessible at https://aiarchives.duckdns.org/mcp. Once you've configured Claude Desktop as described above, you can immediately start using the available tools without needing to run anything locally.

Note: The server is always running and ready to accept requests through the MCP protocol.

Local Deployment (Optional)

If you want to run the server locally for development or testing purposes:

  1. Start the server:

    npm start
    

    Or run directly with Node.js:

    node server-mcp.js
    
  2. Update the Claude Desktop configuration to point to your local server:

    {
      "mcpServers": {
        "aiarchives": {
          "command": "npx",
          "args": [
            "-y",
            "mcp-remote",
            "http://localhost:8000/mcp",
            "--allow-http",
            "--transport",
            "http-only"
          ]
        }
      }
    }
    

Important: When running locally, the save_conversation tool will not work because it depends on the remote aiarchives API that's only available on the hosted server. The add and reverse tools will work normally.

Available Endpoints

POST /mcp

Main MCP protocol endpoint that handles JSON-RPC requests.

Example request:

{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/list"
}

GET /health

Health check endpoint that returns server status.

Response:

{
  "status": "healthy",
  "server": "Remote MCP Server",
  "timestamp": "2024-01-01T00:00:00.000Z"
}

GET /mcp

Debug endpoint that confirms the server is running.

Available Tools

1. add

Performs addition of two numbers.

Parameters:

  • a (number): First number
  • b (number): Second number

Example:

{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "add",
    "arguments": {
      "a": 5,
      "b": 3
    }
  }
}

2. reverse

Reverses a text string.

Parameters:

  • text (string): Text to reverse

Example:

{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "reverse",
    "arguments": {
      "text": "Hello World"
    }
  }
}

3. save_conversation

Saves conversation content to aiarchives.duckdns.org and returns a shareable URL.

Parameters:

  • conversation (string): Full conversation content as HTML or plain text

Example:

{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "save_conversation",
    "arguments": {
      "conversation": "<html><body>Conversation content...</body></html>"
    }
  }
}

MCP Protocol Methods

The server implements the following MCP protocol methods:

  • initialize: Initialize the MCP connection
  • tools/list: List available tools
  • tools/call: Execute a specific tool
  • notifications/initialized: Handle client initialization notification
  • notifications/cancelled: Handle request cancellation notification

Error Handling

The server returns proper JSON-RPC 2.0 error responses with standard error codes:

  • -32600: Invalid Request
  • -32601: Method not found
  • -32602: Invalid params
  • -32603: Internal error

Development

Project Structure

mcp-server/
├── server-mcp.js      # Main server implementation
├── package.json       # Dependencies and scripts
├── .gitignore        # Git ignore rules
└── README.md         # This file

Adding New Tools

To add a new tool, modify the tools/list response and add a corresponding case in the tools/call switch statement in server-mcp.js.

Testing

Currently, there are no automated tests. You can test the server manually using curl or any HTTP client:

# Health check
curl http://localhost:8000/health

# List tools
curl -X POST http://localhost:8000/mcp \
  -H "Content-Type: application/json" \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'

Dependencies

  • express: Web framework for Node.js
  • body-parser: Middleware for parsing request bodies
  • cors: Cross-origin resource sharing middleware

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