What is MCP?

What is What is MCP??

The Model Context Protocol (MCP) lets you build servers that expose data and functionality to LLM applications in a secure, standardized way. Think of it like a web API, but specifically designed for LLM interactions. MCP servers can expose data through resources, provide functionality through tools, and define interaction patterns through prompts.

How to use What is MCP??

Use the provided TypeScript code examples to define resources, tools, and prompts. Import the necessary MCP library and create a server instance using server.resource(), server.tool(), and server.prompt().

Key features of What is MCP??

• Expose static or parameterized data via resources (similar to GET endpoints).
• Provide computational/side-effect actions via tools (similar to POST endpoints).
• Create reusable prompt templates for LLM interactions.
• Built for the Model Context Protocol standard.
• Written in TypeScript for Node.js.

Use cases of What is MCP??

• Load configuration or user profile data into an LLM’s context using resources.
• Execute calculations or fetch external APIs (e.g., BMI calculator, weather data) through tools.
• Guide LLM interactions with predefined code-review or other prompt templates.

FAQ from What is MCP??

What does MCP stand for?

MCP stands for Model Context Protocol.

What can MCP servers do?

They expose data through resources, functionality through tools, and define interaction patterns through prompts.

How do resources differ from tools?

Resources are like GET endpoints – they provide data without significant computation or side effects. Tools are like POST endpoints – they perform computation and may have side effects.

What runtime is required?

The server is implemented as an MCP TypeScript server with Node.js.

Are there any code examples?

Yes, the README provides TypeScript examples for resources (static and dynamic), tools (simple and async), and prompts.