mcpField
M
MCP服务器项目说明

MCP服务器项目说明

Local
github.com/ningwenjieDeveloper Tools3Updated 84w ago

About MCP服务器项目说明

This MCP server is a backend service for integrating file access, MongoDB, external APIs, and vector search with LLMs such as Qwen. It includes Docker deployment configuration and a Qwen client example.

Key features

  1. 01File upload, download, listing, and deletion
  2. 02MongoDB document CRUD
  3. 03External API calls
  4. 04Vector storage and similarity search
  5. 05Docker deployment configuration
  6. 06Qwen client example

Use cases

  1. 01Managing files through an integrated service
  2. 02Performing MongoDB document operations
  3. 03Searching vector data by similarity
  4. 04Deploying an MCP service with Docker

MCP support

It exposes file, MongoDB, external API, and vector database capabilities through an MCP server for clients. The README also includes a Qwen client example.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

MCP服务器项目说明

项目概述

MCP(多功能计算平台)服务器是一个功能强大的后端服务,支持文件访问、数据库连接、API集成和向量数据库访问等多种功能。本项目专为与通义千问(Qwen)等大型语言模型集成而设计,提供了完整的Docker部署配置和通义千问调用示例。

项目结构

mcp_server/
├── src/                    # 源代码目录
│   ├── __init__.py         # 初始化模块
│   ├── config.py           # 配置管理
│   ├── server.py           # 服务器主类
│   └── modules/            # 功能模块
│       ├── __init__.py     # 模块注册
│       ├── file_module.py  # 文件访问模块
│       ├── database_module.py # 数据库连接模块
│       ├── api_module.py   # API集成模块
│       └── vector_module.py # 向量数据库模块
├── docker/                 # Docker配置
│   ├── Dockerfile          # Docker镜像配置
│   └── docker-compose.yml  # Docker Compose配置
├── examples/               # 示例代码
│   ├── qwen_client.py      # 通义千问客户端库
│   └── qwen_example.py     # 通义千问使用示例
├── docs/                   # 文档
│   ├── user_guide.md       # 用户指南
│   ├── api_docs.md         # API文档
│   └── qwen_examples.md    # 通义千问示例说明
├── test_server.py          # 服务器测试脚本
├── test_qwen_client.py     # 通义千问客户端测试脚本
├── main.py                 # 主入口文件
└── requirements.txt        # 依赖列表

功能特性

  • 文件访问:上传、下载、列表和删除文件
  • 数据库连接:MongoDB集成,支持文档的增删改查
  • API集成:支持调用外部API服务
  • 向量数据库:支持向量存储和相似度搜索
  • Docker部署:完整的Docker配置,支持一键部署
  • 通义千问集成:提供通义千问调用MCP服务器的客户端和示例

快速开始

安装
  1. 克隆项目代码:
git clone https://github.com/ningwenjie/mcp_server
cd mcp_server
  1. 使用Docker Compose启动服务:
docker-compose -f docker/docker-compose.yml up -d
  1. 验证服务是否正常运行:
curl http://localhost:8000/health
使用通义千问客户端
from examples.qwen_client import QwenMCPClient

# 初始化客户端
client = QwenMCPClient("http://localhost:8000")

# 上传文件
file_info = client.upload_file("example.txt")

# 存储向量
vector = [0.1, 0.2, 0.3] * 512  # 1536维向量
metadata = {"text": "这是一个示例文本", "source": "通义千问"}
vector_info = client.store_vector("qwen_embeddings", vector, metadata)

# 搜索向量
query_vector = [0.15, 0.25, 0.35] * 512
search_results = client.search_vector("qwen_embeddings", query_vector, top_k=3)

文档

详细文档请参阅:

测试

运行服务器测试:

python test_server.py

运行通义千问客户端测试:

python test_qwen_client.py

依赖

  • Python 3.10+
  • FastAPI
  • Uvicorn
  • PyMongo
  • FAISS
  • Docker (用于部署)

详细依赖列表请参阅 requirements.txt。

许可证

MIT License

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.