Model Context Protocol (MCP)
About
Model Context Protocol (MCP) is a client-server protocol that enables communication between large language models (LLMs) and external tools or data sources. It uses JSON‑RPC 2.0 for messaging and was introduced by Anthropic.
Details
- Author
- PouyaEsmaeili
- Downloads
- 300
- Categories
- Other, AI
Jump to
- Client‑server architecture using JSON‑RPC 2.0
- Three server capabilities: Tools, Resources, and Prompts
- Supports SSE over HTTP and stdin transport layers
- FastMCP high‑level API for quick server development
- Standardized initialization and discovery flow
- Built‑in error codes for JSON‑RPC
Implement an MCP server using FastMCP or the Low‑Level APIs from the MCP Python SDK. Servers can be run over SSE (HTTP) or stdin. The README provides full Python examples for both server and client (SSE and stdio). For instance, a FastMCP server can be served with mcp.run(transport="sse") or wrapped with Starlette.
Model Context Protocol (MCP)
Model Context Protocol (MCP) is a protocol designed to establish a communication channel between large language models (LLMs) and external tools or data sources. It follows a client-server architecture and uses JSON-RPC 2.0 for messaging.
Although MCP was introduced only a few months ago by Anthropic, it has quickly gained significant attention in the AI community.
In the sections below, I’ll explain the MCP specification and provide some Python examples.
---
MCP Server
An MCP server provides three key capabilities to the client:
| Capability | Description |
|------------|-------------|
| Tool | A function or service that performs logic (e.g., a calculator), triggers side effects (e.g., modifies the environment), or is CPU-bound. |
| Resource | Any type of data such as images, files, etc. |
| Prompt | A prompt template that can be used by the client. |
An MCP server can be implemented using either FastMCP or Low-Level APIs.
It supports communication via SSE over HTTP (Server-Sent Events) or stdin.
Use stdin for local communication and SSE for network-based communication.
Type of communication is called Transport Layer in MCP specification.
FastMCP
Suppose we want to implement an MCP server for an English teaching application based on a LLM.
This MCP server will provide an assessment quiz (Resource), a triage function to determine the learner's level (Tool), and a prompt template (Prompt).
```python
from mcp.server.fastmcp import FastMCP
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
