mcp tutorial

cookbook/pocketflow-mcp/README.md

@@ -1,59 +1,51 @@
-#  Simple PocketFlow Chat
+# PocketFlow MCP Demo
 
-A basic chat application using PocketFlow with OpenAI's GPT-4o model.
+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
 
-- Conversational chat interface in the terminal
+- Addition operations through a simple terminal interface
-- Maintains full conversation history for context
+- Integration with Model Context Protocol (MCP)
-- Simple implementation demonstrating PocketFlow's node and flow concepts
+- Comparison between MCP and direct function calling
 
-## Run It
+## How to Run
 
-1. Make sure your OpenAI API key is set:
+1. Set your API key:
    ```bash
    export OPENAI_API_KEY="your-api-key-here"
    ```
-    Alternatively, you can edit the `utils.py` file to include your API key directly.
+   Or update it directly in `utils.py`
 
-2. Install requirements and run the application:
+2. Install and run:
    ```bash
    pip install -r requirements.txt
    python main.py
    ```
 
+## MCP vs Basic Function Calling
 
-## Run the MCP
+### Basic Function Calling
+- Functions are directly embedded in application code
+- Each new tool requires modifying the application
+- Tools are defined within the application itself
 
-Run the server
+### MCP Approach
-
+- Tools live in separate MCP servers
-```bash
+- Standard protocol for all tool interactions
-python simple_server.py
+- New tools can be added without changing the agent
-```
+- AI can interact with tools through a consistent interface
-
-Run the client
-
-```bash
-python simple_client.py
-```
 
 ## How It Works
 
-```mermaid
-flowchart LR
-    chat[ChatNode] -->|continue| chat
-```
-
-The chat application uses:
-- A single `ChatNode` with a self-loop that:
-  - Takes user input in the `prep` method
-  - Sends the complete conversation history to GPT-4o
-  - Adds responses to the conversation history
-  - Loops back to continue the chat until the user types 'exit'
 
+The agent uses PocketFlow to create a workflow where:
+1. It takes user input about numbers
+2. Connects to the MCP server for addition operations
+3. Returns the result
 
 ## Files
 
-- [`main.py`](./main.py): Implementation of the ChatNode and chat flow
+- [`main.py`](./main.py): Implementation of the addition agent using PocketFlow
-- [`utils.py`](./utils.py): Simple wrapper for calling the OpenAI API
+- [`utils.py`](./utils.py): Helper functions for API calls and MCP integration
- 
+- [`simple_server.py`](./simple_server.py): MCP server that provides the addition tool
+- [`simple_client.py`](./simple_client.py): Example client that connects to the MCP server