Mcp client

As explained in Spring AI in Action

An MCP client is an application component that connects to an MCP server and invokes capabilities exposed through the Model Context Protocol.

An MCP client is an application component that connects to an MCP server, discovers its tools, adds them to prompt context, and invokes them for an LLM. In Spring AI, it turns reusable server capabilities—such as filesystem or database access—into tools available to a conversational application. section 7.1

Build a client incrementally:

• Add Spring Web, an LLM integration such as OpenAI, and the Spring AI MCP Client dependency to a Spring Boot project. section 7.2
• Configure an MCP server with Spring properties or Claude Desktop-compatible JSON; STDIO configuration identifies the command and arguments that launch the server. section 7.2
• Inject ToolCallbackProvider into a ChatClient, register its callbacks as default tools, and expose an endpoint that forwards user questions to the model. section 7.2
• For HTTP+SSE, configure a server URL under spring.ai.mcp.client.sse.connections; this enables independently deployed client and server applications. section 7.4.3

Filesystem questions through /ask

A configured Filesystem MCP Server lets an MCP-enabled controller answer requests such as listing files, creating penguins.txt with generated content, and reading that file back. section 7.2

Figure 7.1 Interactions between MCP Servers and MCP Clients

Use the interaction diagram to trace how the client obtains server tools, places them in prompt context, and invokes them for the LLM. section 7.1

How Spring AI in Action covers it

How deep it goes

Explains project setup, configuration, tool registration, and STDIO versus HTTP+SSE, while deferring Streamable HTTP.

Examples

Uses Filesystem and Board Game DB servers, /ask requests, YAML or JSON configuration, and game-recommendation responses.

What it assumes

Assumes Spring Boot and LLM application basics while teaching MCP dependencies, server configuration, and callback wiring explicitly.

What you can do after

Build it from scratch with Spring Boot and Spring AI, then configure STDIO or HTTP+SSE servers for LLM tool use.

How it connects

Ties MCP clients to MCP servers, tools, prompts, resources, Spring AI, STDIO, and HTTP+SSE transports.

liveBookmanning.com

Read Spring AI in Action on liveBook Get the book at manning.com

Also explained in

• 

  liveBookmanning.com
  Build AI-Enhanced Web AppsA client that implements the Model Context Protocol to discover and invoke capabilities exposed by an MCP server on behalf of an application or agent.
• 

  liveBookmanning.com
  AI Agents and ApplicationsAn MCP client is a software component that connects to MCP servers and accesses the tools they expose.
• 

  liveBookmanning.com
  AI Agents in Action, Second EditionAn MCP client is an application component that connects to an MCP server and discovers and uses the capabilities it exposes.
• 

  liveBookmanning.com
  Build an AI Agent (From Scratch)An MCP client is the protocol component that connects a host application to one MCP server, retrieves tool definitions, and forwards tool-execution requests.
• 

  liveBookmanning.com
  Building LLM Applications with DSPyA protocol component that connects to MCP servers to discover and invoke their capabilities.
• 

  liveBookmanning.com
  Introduction to Generative AI, Second EditionAn MCP client is a component that connects an AI model or tool to MCP servers and can request data or invoke server-defined tools.
• 

  liveBookmanning.com
  Hugging Face in ActionAn MCP client is an AI assistant or application component that sends requests to an MCP server to access external tools or data.

Compare how 8 books explain mcp client →

Related concepts

• MCP serveruses · An MCP server is software that implements the Model Context Protocol to expose capabilities or information to compatible clients.
• MCP hostused by · An MCP host is an application that manages MCP clients and coordinates their communication with MCP servers and use of server capabilities.
• MCPpart of · The Model Context Protocol is an open standard protocol that defines how AI applications connect with external tools, data sources, and other contextual resources.
• stdio transportuses · A stdio transport is an interprocess communication mechanism that exchanges data through processes’ standard input and standard output streams.
• allowlistuses · An allowlist is an explicit collection of permitted entities, values, or operations, with items outside the collection disallowed.
• AI agentcontrasts with · An AI agent is a computational system that uses artificial intelligence to interpret information, select actions, and pursue goals through interaction with an environment.

This explainer was generated by Manning's knowledge graph from the text of Spring AI in Action. The section links point to the parts of the book it draws on.