History

zachary62 eb80114122 finish mcp tutorial		2025-03-29 13:15:13 -04:00
..
README.md	finish mcp tutorial	2025-03-29 13:15:13 -04:00
main.py	mcp tutorial	2025-03-29 12:19:33 -04:00
requirements.txt	add mcp example	2025-03-29 11:22:06 -04:00
simple_server.py	add mcp example	2025-03-29 11:22:06 -04:00
utils.py	mcp tutorial	2025-03-29 12:19:33 -04:00

README.md

PocketFlow MCP Demo

This project shows how to build an agent that performs addition using PocketFlow and Model Context Protocol (MCP). It presents a comparison between using MCP and basic function calling approaches.

Features

Addition operations through a simple terminal interface
Integration with Model Context Protocol (MCP)
Comparison between MCP and direct function calling

How to Run

Set your API key:
```
export OPENAI_API_KEY="your-api-key-here"
```
Or update it directly in utils.py

Install and run:

pip install -r requirements.txt
python main.py

MCP vs Basic Function Calling

Basic Function Calling

Functions are directly embedded in application code
Each new tool requires modifying the application
Tools are defined within the application itself

MCP Approach

Tools live in separate MCP servers
Standard protocol for all tool interactions
New tools can be added without changing the agent
AI can interact with tools through a consistent interface

How It Works

flowchart LR
    tools[GetToolsNode] -->|decide| decide[DecideToolNode]
    decide -->|execute| execute[ExecuteToolNode]

The agent uses PocketFlow to create a workflow where:

It takes user input about numbers
Connects to the MCP server for addition operations
Returns the result

Files

main.py: Implementation of the addition agent using PocketFlow
utils.py: Helper functions for API calls and MCP integration
simple_server.py: MCP server that provides the addition tool