Model Context Protocol (MCP)
Definition
An open protocol, originally developed by Anthropic, that standardizes how AI models connect to external data sources and tools. MCP provides a universal interface — similar to USB-C for hardware — allowing any AI model to call any tool through a consistent request/response format. It replaces brittle, per-tool API integrations with a single protocol layer. MCP servers expose capabilities (tools, resources, prompts) that MCP clients (AI models, IDEs, agent frameworks) can discover and invoke at runtime.
Builder Context
MCP is the integration layer you should default to when connecting your agent to external tools. If a tool has an MCP server, use it — you get tool discovery, structured I/O, and error handling for free. If it doesn't, consider wrapping the tool's API in a lightweight MCP server yourself. The protocol is transport-agnostic (stdio, HTTP+SSE) and model-agnostic — it works with Claude, GPT, Gemini, and open-source models. The main trade-off: MCP is synchronous request/response, so it's not ideal for long-running background tasks (that's where A2A comes in).