MCP ExplorerExplorer

Alg Mcp

@chenlinyangon 6 months ago
28 MIT
FreeCommunity
AI Systems
Enabling intelligent querying based on the MCP protocol.

Overview

What is Alg Mcp

alg-mcp is a project designed to enable intelligent querying based on the MCP protocol. It utilizes real-time data integration and semantic indexing capabilities of the MCP Server database to transform natural language into structured queries.

Use cases

Use cases for alg-mcp include assisting enterprises in technical R&D, enhancing product design processes, and enabling intelligent querying for data-driven decision-making.

How to use

To use alg-mcp, configure the mcp-server with database connection settings and third-party weather API credentials. Then, set up the mcp-client to connect to the mcp-server and configure the large model API keys. Follow the provided operation steps for implementation.

Key features

Key features of alg-mcp include a robust MCP server and client, support for various AI models like Zhipu-AI, and functionalities for weather queries and database operations. It also provides a seamless natural language to SQL transformation.

Where to use

alg-mcp can be used in various fields including technology research and development, product design, and any domain requiring intelligent data querying and analysis.

Content

Getting Started

Algorithmic Learning Graybeard - 星星点灯,基于RAG+MCP双引擎架构实现智能查询。

在大语言模型(LLM)的基石上,依托MCP Server对数据库的数据融合与语义索引能力,构建RAG与MCP协同的双引擎架构,通过智能语法解析与查询映射,实现自然语言到结构化查询的精准转换,形成完整的技术链路闭环。可用于辅助企业/团队进行技术研发、产品设计等支撑工作。

🌟该项目如对您有帮助,欢迎点赞🌟

系统组成及文档

中文文档 | English

👉代码地址:githubgitee

如果您有上千数据目录、亿级数据事实,要做数据检索或数据分析,可以在该项目上进行扩展优化。

架构参考:

功能点

  • 天气查询

外部接口自由对接

本地路径

  • 数据库操作

一句话精准完成分组、排名、取样等SQL操作

本地路径

接入的模型

  • Zhipu-AI

  • 也可以根据个人喜好接入其他模型:

    支持DeepSeek、ChatGPT 3.5、通义千问、文心一言、Ollama等

技术栈

该仓库为后端服务

技术栈:

  • jdk 17
  • springboot 3.4.4
  • langchain4j 1.0.0-beta3
  • mcp-server 利用自定义注解,实现MCP协议。已完成的接口有:

    initialize、tools/call、tools/list、notifications/initialized、prompts/list、prompts/get等
  • mcp-client 使用RAG自定义QueryTransformer,读取MCP server prompt实现NPL2SQL功能

如何运行

mcp-server配置

a. 配置数据库连接

  • 数据库(MySQL)
spring:
  datasource:
    type: com.zaxxer.hikari.HikariDataSource
    url: jdbc:mysql://<ip>:<port>/<database_name>?characterEncoding=utf8&serverTimezone=GMT%2B8&useSSL=false
    driver-class-name: com.mysql.cj.jdbc.Driver
    username: <username>
    password: <password>

b. 配置第三方天气API

weather:
  api:
    host: <api-host>
    api-key: <api-key>

mcp-client配置

a. 配置mcp-server连接

  • SSE Endpoint
mcp:
  server:
    sse-url: http://localhost:3002/sse

b. 配置大模型

  • 大模型api-key和model配置
zhipu-ai:
  api-key: <api-key>
  model: <model>

Tools

No tools

Comments

Recommend MCP Servers

View All MCP Servers