Mcp client
An MCP client is a software component that connects a host application to an MCP server to discover and invoke capabilities exposed through the Model Context Protocol.
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.
- How it is used
- Connects Spring AI applications to reusable MCP server capabilities for tool-enabled conversational requests.
- 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 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.
Build AI-Enhanced Web Apps
A client that implements the Model Context Protocol to discover and invoke capabilities exposed by an MCP server on behalf of an application or agent.
- How it is used
- Connects AI-enabled applications to MCP servers so they can discover capabilities and receive tool results.
- How deep it goes
- Walks through client creation, tool discovery, route integration, and cleanup; does not detail protocol implementation.
- Examples
- Uses a chat application whose MCP tool retrieves a fact from an external jokes API.
- What you can do after
- Build it from scratch in a Next.js route using the Vercel AI SDK, or apply it via LangChain.js.
AI Agents and Applications
An MCP client is a software component that connects to MCP servers and accesses the tools they expose.
- How it is used
- Connects agents to external MCP tools so applications can consume shared services without maintaining custom connectors.
- How deep it goes
- Explains architecture, transports, replacement steps, and asynchronous configuration, but does not detail the protocol internals.
- Examples
- Uses a travel agent, an AccuWeather server, live weather retrieval, and a Penzance weather query.
- What you can do after
- Builds an MCP connection that retrieves remote tools and supplies them to an agent.
AI Agents in Action, Second Edition
An MCP client is an application component that connects to an MCP server and discovers and uses the capabilities it exposes.
- How it is used
- Connects AI applications and agents to discoverable tools, resources, prompts, and services through a uniform interface.
- How deep it goes
- Defines client, server, and service responsibilities and explains capability discovery, but does not detail client implementation code.
- Examples
- Names agents, LLM applications, Claude Desktop, and VS Code connecting to filesystems, databases, web APIs, and other agents.
- What you can do after
- Apply MCP by connecting an AI application to a server and discovering the tools or other capabilities it exposes.
Read how AI Agents in Action, Second Edition explains mcp client →
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.
- How it is used
- Connects a host application to one MCP server for standardized tool discovery and execution.
- How deep it goes
- Explains lifecycle, stdio setup, session methods, schemas, and result handling, stopping short of broader production reliability details.
- Examples
- Uses a Python Tavily subprocess client, tool listings, a web-search call, and MCP-to-OpenAI schema conversion.
- What you can do after
- Builds a Python client that launches an MCP server, discovers tools, invokes them, and adapts schemas for an LLM provider.
Read how Build an AI Agent (From Scratch) explains mcp client →
Building LLM Applications with DSPy
A protocol component that connects to MCP servers to discover and invoke their capabilities.
- How it is used
- Connects an AI host to MCP servers so an agent can discover and invoke their capabilities through a consistent interface.
- How deep it goes
- Explains client roles and transports, then details session setup, tool discovery, conversion, and asynchronous invocation.
- Examples
- Uses a DSPy Wix support agent to discover knowledge-base search and article-reading tools from a server.
- What you can do after
- Apply it via dspy.Tool.from_mcp_tool() to give discovered server tools to a ReAct agent.
Read how Building LLM Applications with DSPy explains mcp client →
Introduction to Generative AI, Second Edition
An MCP client is a component that connects an AI model or tool to MCP servers and can request data or invoke server-defined tools.
- How it is used
- Connects language models with external data, application state, and server-defined tools through a standardized interface.
- How deep it goes
- Explains servers, functions, prompts, and tools, but stops short of implementation details.
- Examples
- Uses Splunk cloud logs, natural-language queries, filtering tools, and a server-defined log-analysis prompt.
- What you can do after
- Evaluate how an AI agent can access prepared services and where MCP integration leaves coverage gaps.
Read how Introduction to Generative AI, Second Edition explains mcp client →
Hugging Face in Action
An MCP client is an AI assistant or application component that sends requests to an MCP server to access external tools or data.
- How it is used
- Connects AI assistants or applications to external tools and data through MCP servers.
- How deep it goes
- Defines the client’s role and transport options, without detailing client implementation code.
- Examples
- Uses Claude Desktop as an AI-powered client example and illustrates local and remote client-server arrangements.
- What you can do after
- Operate MCP clients to access tools and data through local stdio or remote HTTP POST and SSE connections.
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.
These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.