TL;DR

MCP (Model Context Protocol) is an open protocol open-sourced by Anthropic in November 2024 that standardizes connections between AI applications and tools/data sources — often called "USB-C for AI." Instead of building a custom integration per tool, you implement one MCP server and any MCP-compatible client (Claude Desktop, IDEs, agent frameworks) can use it.

Architecture

RolePurposeExamples
MCP HostThe AI app initiating connectionsClaude Desktop, IDEs, agent frameworks
MCP ServerExposes tools, resources, and promptsGitHub, databases, browsers, file systems
TransportHow the two connectstdio (local subprocess), HTTP streaming

Core primitives

Why it matters

FAQ

What's the difference between MCP and plugins/function calling?

Function calling is the model-side calling convention; MCP is the tool-side standard. MCP defines how tools are exposed; function calling defines how a model invokes them.

How do I deploy an MCP server?

Local tools typically run over stdio (launched as a subprocess); remote services expose a Streamable HTTP endpoint that clients discover and call per the MCP spec.

Which transports does MCP support?

stdio and HTTP-based streaming (Streamable HTTP with SSE) are the current main transports; the spec is maintained at modelcontextprotocol.io.

Sources

最后更新:2026-08-04