MCP Assistant Server
An MCP server that provides task analysis and tool recommendation capabilities
Lutra23
README
<div align="center">
MCP Assistant Server
<p align="center"> <img src="docs/images/logo.png" alt="MCP Assistant Server Logo" width="200"/> </p>
🤖 一个强大的 MCP 服务器,提供智能任务分析和工具推荐功能
English | 简体中文
</div>
✨ 特性
- 🎯 智能任务分析 - 自动分析用户任务,提取关键信息
- 🔍 工具推荐 - 基于任务特点智能推荐最适合的 MCP 工具
- 🧠 LLM 集成 - 集成大语言模型进行高级分析
- 🔄 上下文管理 - 智能维护任务执行过程中的上下文信息
- 🔌 工具发现 - 自动发现和集成可用的 MCP 工具
- 🚀 高性能 - 异步处理,快速响应
- 📦 易扩展 - 模块化设计,便于扩展
🚀 快速开始
环境要求
- Node.js >= 16.0.0
- npm >= 7.0.0
安装
# 克隆仓库
git clone https://github.com/Lutra23/mcp-assistant-server.git
# 进入项目目录
cd mcp-assistant-server
# 安装依赖
npm install
配置
- 复制配置文件模板:
cp mcp-config.json.example mcp-config.json
- 根据需要修改
mcp-config.json
配置,现在只支持硅基流动api调用:
{
"port": 3000,
"logLevel": "info",
"llm": {
"apiKey": "your-api-key"
}
}
运行
# 开发模式
npm run dev
# 生产模式
npm run build
npm start
📚 在 Cline 中使用
配置 MCP 服务器
- 打开 Cline 的 MCP 设置文件:
# Linux/WSL
~/.vscode-server/data/User/globalStorage/rooveterinaryinc.roo-cline/settings/cline_mcp_settings.json
# macOS
~/Library/Application Support/Code/User/globalStorage/rooveterinaryinc.roo-cline/settings/cline_mcp_settings.json
# Windows
%APPDATA%\Code\User\globalStorage\rooveterinaryinc.roo-cline\settings\cline_mcp_settings.json
- 添加服务器配置:
{
"mcpServers": {
"assistant": {
"command": "node",
"args": ["/path/to/mcp-assistant-server/build/index.js"],
"env": {
"PORT": "3000",
"LOG_LEVEL": "info"
}
}
}
}
使用示例
在 Cline 中,你可以使用以下工具:
// 分析任务
<use_mcp_tool>
<server_name>assistant</server_name>
<tool_name>analyze_task</tool_name>
<arguments>
{
"description": "获取天气信息并保存到文件",
"context": {
"location": "上海",
"format": "json"
}
}
</arguments>
</use_mcp_tool>
// 推荐工具
<use_mcp_tool>
<server_name>assistant</server_name>
<tool_name>recommend_tools</tool_name>
<arguments>
{
"taskId": "task-123",
"useHybridRecommendation": true
}
</arguments>
</use_mcp_tool>
📚 在 Cursor 中使用
配置 MCP 服务器
- 打开 Cursor 的配置文件:
# Linux
~/.cursor/cursor_config.json
# macOS
~/Library/Application Support/Cursor/cursor_config.json
# Windows
%APPDATA%\Cursor\cursor_config.json
- 添加 MCP 服务器配置:
{
"mcpServers": {
"assistant": {
"command": "node",
"args": ["/path/to/mcp-assistant-server/build/index.js"],
"env": {
"PORT": "3000",
"LOG_LEVEL": "info"
}
}
}
}
使用方式
在 Cursor 中,你可以通过命令面板(Cmd/Ctrl + Shift + P)使用以下命令:
MCP: 分析任务
- 分析当前选中的代码或文本MCP: 推荐工具
- 获取针对当前任务的工具推荐MCP: 更新上下文
- 更新任务上下文信息
也可以通过 Cursor API 在插件中使用:
import { workspace } from 'cursor';
// 分析任务
const analysis = await workspace.mcp.callTool('assistant', 'analyze_task', {
description: '当前任务描述',
context: {
// 上下文信息
}
});
// 获取工具推荐
const recommendations = await workspace.mcp.callTool('assistant', 'recommend_tools', {
taskId: 'current-task-id'
});
🎯 核心功能
任务分析器
分析用户输入的任务描述,提取关键信息:
- 任务类型识别
- 参数提取
- 上下文关联
- 依赖分析
工具推荐系统
根据任务特点智能推荐工具:
- 基于规则的推荐
- 混合推荐算法
- 上下文感知
- 历史数据分析
上下文管理器
维护任务执行过程中的上下文信息:
- 状态追踪
- 数据持久化
- 会话管理
- 错误恢复
📦 项目结构
src/
├── controllers/ # 控制器层
│ └── LLMApiController.ts
├── core/ # 核心功能实现
│ ├── TaskAnalyzer.ts
│ ├── ToolRecommender.ts
│ └── ContextManager.ts
├── services/ # 服务层
│ ├── LLMService.ts
│ └── MCPDiscoveryService.ts
├── routes/ # 路由定义
│ └── llmApiRoutes.ts
└── types/ # 类型定义
└── interfaces.ts
🔌 API 文档
详细的 API 文档请查看 API 文档。
🤝 贡献指南
我们欢迎所有形式的贡献,无论是新功能、文档改进还是问题反馈。详情请查看 贡献指南。
📄 更新日志
查看 CHANGELOG.md 了解详细的更新历史。
📝 开源协议
本项目采用 MIT 许可证 - 查看 LICENSE 了解详情。
🙏 致谢
感谢所有为这个项目做出贡献的开发者们!
<div align="center">
Made with ❤️ by Lutra23
</div>
Recommended Servers
Crypto Price & Market Analysis MCP Server
A Model Context Protocol (MCP) server that provides comprehensive cryptocurrency analysis using the CoinCap API. This server offers real-time price data, market analysis, and historical trends through an easy-to-use interface.
MCP PubMed Search
Server to search PubMed (PubMed is a free, online database that allows users to search for biomedical and life sciences literature). I have created on a day MCP came out but was on vacation, I saw someone post similar server in your DB, but figured to post mine.
dbt Semantic Layer MCP Server
A server that enables querying the dbt Semantic Layer through natural language conversations with Claude Desktop and other AI assistants, allowing users to discover metrics, create queries, analyze data, and visualize results.
mixpanel
Connect to your Mixpanel data. Query events, retention, and funnel data from Mixpanel analytics.

Sequential Thinking MCP Server
This server facilitates structured problem-solving by breaking down complex issues into sequential steps, supporting revisions, and enabling multiple solution paths through full MCP integration.

Nefino MCP Server
Provides large language models with access to news and information about renewable energy projects in Germany, allowing filtering by location, topic (solar, wind, hydrogen), and date range.
Vectorize
Vectorize MCP server for advanced retrieval, Private Deep Research, Anything-to-Markdown file extraction and text chunking.
Mathematica Documentation MCP server
A server that provides access to Mathematica documentation through FastMCP, enabling users to retrieve function documentation and list package symbols from Wolfram Mathematica.
kb-mcp-server
An MCP server aimed to be portable, local, easy and convenient to support semantic/graph based retrieval of txtai "all in one" embeddings database. Any txtai embeddings db in tar.gz form can be loaded
Research MCP Server
The server functions as an MCP server to interact with Notion for retrieving and creating survey data, integrating with the Claude Desktop Client for conducting and reviewing surveys.