Ollama Python MCP Integration

Guide for integrating Ollama models with Python MCP servers using PraisonAI agents

Add Ollama Python Tool to AI Agent

Quick Start

1. Set Up Ollama

   Make sure you have Ollama installed and running locally:

   # Install Ollama from https://ollama.ai/
   # Pull the llama3.2 model
   ollama pull llama3.2
   
2. Create a file

   Create a new file ollama_stock.py with the following code:

   from praisonaiagents import Agent, MCP
   
   stock_agent = Agent(
       instructions="""You are a Stock Price Assistant.""",
       llm="ollama/llama3.2",
       tools=MCP("/path/to/your/venv/bin/python /path/to/your/app.py")
   )
   
   # NOTE: Python Path replace with yours: /path/to/your/venv/bin/python
   # NOTE: app.py file path, replace it with yours: /path/to/your/app.py
   
   stock_agent.start("What is the Stock Price of Apple?")
   
3. Install Dependencies

   Make sure you have the required packages installed:

   pip install "praisonaiagents[llm]" yfinance mcp
   
4. Run the Agent

   Execute your script:

   python ollama_stock.py
   

Requirements

• Python 3.10 or higher
• Ollama installed and running locally
• yfinance and mcp packages installed

Features

Local LLM

Run models locally using Ollama without relying on external APIs.

Stock Data

Retrieve real-time stock price information using the yfinance library.

Python MCP

Use Python-based MCP servers for custom tool functionality.

Privacy-Focused

Keep sensitive data local with on-device inference.