Stdio transport
A stdio transport is an interprocess communication mechanism that exchanges data through processes’ standard input and standard output streams.
Spring AI in Action
STDIO transport is a process communication method that exchanges data through a program's standard input and standard output streams, including for MCP client-server communication.
- How it is used
- Connects MCP clients and locally launched servers when a simple sidecar process is preferable to a separately deployed service.
- How deep it goes
- Explains configuration, process startup, protocol-safe logging, and deployment coupling, while deferring independent HTTP server operation.
- Examples
- Uses filesystem operations and board-game recommendations to demonstrate configured servers invoked through Spring AI.
- What you can do after
- Operate/configure Spring AI MCP clients that launch servers, expose their tools, and preserve protocol communication over standard streams.
AI Agents in Action, Second Edition
STDIO is the standard input and output stream interface through which a process receives input and emits output.
- How it is used
- Connects local agents or clients to subprocess MCP servers for development, command-line work, and single-machine deployments.
- How deep it goes
- Defines subprocess pipes, latency, one-to-one access, and lifecycle management, while deferring remote communication to SSE.
- Examples
- Uses MCP Inspector, mcp run commands, Python agents, research tools, and local filesystem servers.
- What you can do after
- Operate a local MCP server through an agent-controlled subprocess and manage its active lifetime.
Read how AI Agents in Action, Second Edition explains stdio transport →
Build AI-Enhanced Web Apps
Stdio transport is an interprocess communication method that exchanges data through standard input and standard output streams.
- How it is used
- Connects a local Next.js application to an MCP server without requiring network configuration or server-side HTTP endpoints.
- How deep it goes
- Explains process boundaries, message flow, tool discovery, and API mediation through runnable Vercel AI SDK and LangChain.js integrations.
- Examples
- Uses a Chuck Norris joke MCP server, a Next.js chat route, Gemini, and streamed tool results rendered in a chat interface.
- What you can do after
- Build it from scratch by launching a local MCP server, discovering its tools, and routing model requests through stdio.
Read how Build AI-Enhanced Web Apps explains stdio transport →
Related concepts
- mcp clientused by · 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.
- MCP serverused by · An MCP server is software that implements the Model Context Protocol to expose capabilities or information to compatible clients.
- MCPused by · The Model Context Protocol is an open standard protocol that defines how AI applications connect with external tools, data sources, and other contextual resources.
- http+sse transportcontrasts with · HTTP+SSE transport is a communication mechanism that uses HTTP requests and Server-Sent Events for server-to-client streaming between an MCP client and server.
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.