Transports - Model Context Protocol

modelcontextprotocol.io/specification/2025-06-18/basic/transports
MCP uses JSON-RPC to encode messages. JSON-RPC messages MUST be UTF-8 encoded. The protocol currently defines two standard transport mechanisms for client-server communication: stdio, communication over standard in and standard out Streamable HTTP Clients SHOULD support stdio whenever possible. It is also possible for clients and servers to implement custom transports in a pluggable fashion.

stdio - Model Context Protocol

modelcontextprotocol.io/specification/2026-07-28/basic/transports/stdio
In the stdio transport, the client launches the MCP server as a subprocess. The two ends communicate over the subprocess's standard streams: The server reads JSON-RPC messages from stdin and writes JSON-RPC messages to stdout. Each message is a single JSON-RPC request, notification, or response.

Building Model Context Protocol (MCP) Servers with stdio: A Complete ...

dev.to/elsayed85/building-model-context-protocol-mcp-servers-with-stdio-a-complete-guide-513k
Learn how to build Model Context Protocol (MCP) servers using stdio transport with Python. Complete guide with examples from simple calculators to complex API integrations.

Transports - Model Context Protocol (MCP)

modelcontextprotocol.info/docs/concepts/transports/
Transports in the Model Context Protocol (MCP) provide the foundation for communication between clients and servers. A transport handles the underlying mechanics of how messages are sent and received. Message Format MCP uses JSON-RPC 2.0 as its wire format. The transport layer is responsible for converting MCP protocol messages into JSON-RPC format for transmission and converting received JSON ...

Create a new Model Context Protocol (MCP) server

learn.microsoft.com/en-us/microsoft-copilot-studio/mcp-create-new-server
Create a new Model Context Protocol (MCP) server for your service. Then add the server to your agent through a custom connector.

Model Context Protocol - GitHub

github.com/modelcontextprotocol
The Model Context Protocol (MCP) is an open protocol that enables seamless integration between LLM applications and external data sources and tools. Whether you're building an AI-powered IDE, enhancing a chat interface, or creating custom AI workflows, MCP provides a standardized way to connect LLMs with the context they need.

Transports - Model Context Protocol (MCP)

modelcontextprotocol.info/specification/2024-11-05/basic/transports/
Protocol Revision: 2024-11-05 MCP currently defines two standard transport mechanisms for client-server communication: stdio, communication over standard in and standard out HTTP with Server-Sent Events (SSE) Clients SHOULD support stdio whenever possible.

Model context protocol (MCP) - OpenAI Agents SDK

openai.github.io/openai-agents-python/mcp/
Intro Documentation Model context protocol (MCP) The Model context protocol (MCP) standardises how applications expose tools and context to language models. From the official documentation: MCP is an open protocol that standardizes how applications provide context to LLMs. Think of MCP like a USB-C port for AI applications. Just as USB-C provides a standardized way to connect your devices to ...

MCP TypeScript SDK - GitHub

github.com/modelcontextprotocol/typescript-sdk
The Model Context Protocol (MCP) allows applications to provide context for LLMs in a standardized way, separating the concerns of providing context from the actual LLM interaction. This repository contains the TypeScript SDK implementation of the MCP specification. It runs on Node.js, Bun, and Deno, and ships: MCP server libraries (tools/resources/prompts, Streamable HTTP, stdio, auth helpers ...

Extend your agent with Model Context Protocol - Microsoft Copilot Studio

learn.microsoft.com/en-us/microsoft-copilot-studio/agent-extend-action-mcp
Extend the capabilities of your agent by connecting to tools from a Model Context Protocol (MCP) server.