mcpField
S
Spring Ai Mcp Deepseek

Spring Ai Mcp Deepseek

Local
github.com/firefly0512Developer Tools13Updated 74w ago

About Spring Ai Mcp Deepseek

A Spring AI 1.0.0 project with an MCP server and a DeepSeek-powered client. It includes text chat endpoints and a page-based client for controlling MCP tool calls.

Key features

  1. 01Built with Spring AI 1.0.0
  2. 02Includes an MCP server
  3. 03DeepSeek client integration
  4. 04Text chat endpoints
  5. 05Page client with tool calls and streaming

Use cases

  1. 01Run a local MCP server
  2. 02Send chat messages through text endpoints
  3. 03View and invoke tools in the page client

MCP support

The project includes an MCP server and clients that connect to and invoke MCP tools. The server exposes an SSE endpoint.

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

说明

使用 Spring AI 1.0.0 整合 MCP 服务,包括 MCP server 和 deepseek AI client

1、mcp-client 和 call-mcp 模块中的 application.properties 配置文件:

spring.ai.openai.api-key=你的deepseek api key

2、mcp-servers-config.json 中的部分 key 信息补充完善

MCP 服务端

启动 mcp-server 模块,端口 8085

http://localhost:8085/sse

MCP 客户端

★ 文本客户端:

启动 mcp-client 模块,端口 8082

示例:http://localhost:8082/api/chat?message=%E4%BB%8A%E6%97%A5%E6%9D%AD%E5%B7%9E%E5%A4%A9%E6%B0%94

img1.png

示例:http://localhost:8082/chat?message=%E4%BB%8A%E6%97%A5%E6%9D%AD%E5%B7%9E%E5%A4%A9%E6%B0%94

img2.png

★ 页面客户端(call + stream), MCP tool 主动控制调用

启动 mcp-tool-client 模块,端口 8083

访问入口:http://localhost:8083/

img3.png

说明:右侧展示了当前 client 客户端注册的 MCP 工具列表。

img4.png

img5.png

工具调用的效果,格式化如下:

img_3.png

img_1.png

img_2.png

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.