Happy slice of mcp pizzaMCP.pizza

ollama-mcp-agent

MCP.Pizza Chef: godstale

Ollama MCP Agent is a client that lets you run large language models locally on your PC for free, leveraging Ollama's LLMs combined with the Model Context Protocol (MCP) to extend AI capabilities. It supports streaming responses, tool call monitoring, and integrates easily with MCP servers, providing a powerful, cost-effective way to enhance LLM functionality with local resources.

Unmaintained · No commits in 16 months.

Use This MCP client To

Run LLM models locally without cloud costs Extend local LLMs with MCP protocol features Monitor tool calls during LLM interactions Stream LLM response outputs in real time Integrate local LLMs with MCP servers for enhanced workflows

README

Ollama MCP Agent

Ollama MCP Agent allows you to use LLM models locally on your PC for free. Using Ollama's locally installed LLM models along with MCP (Model Context Protocol) additional features, you can easily extend LLM functionality.

Key Features

  • Run LLM models locally on your PC (no additional costs)
  • Extend LLM capabilities through MCP
  • Streaming response output
  • Tool call information monitoring

System Requirements

  • Python 3.12 or higher
  • Ollama installation
  • uv - Fast Python package installer and resolver
  • MCP server (optional)

Installation

  1. Clone repository
git clone https://github.com/godstale/ollama-mcp-agent
cd ollama-mcp-agent
  1. Install uv (if not installed)
# Using pip
pip install uv

# Or using curl (Unix-like systems)
curl -LsSf https://astral.sh/uv/install.sh | sh

# Or using PowerShell (Windows)
powershell -c "irm https://astral.sh/uv/install.ps1 | iex"
  1. Create virtual environment and install dependencies
# Install dependencies
uv sync
  1. Install Ollama and download model
# Install Ollama (refer to https://ollama.ai for platform-specific installation)
# Download LLM model which supports Tool calling feature
ollama pull qwen3:14b

Configuration

ollama-mcp-agent FAQ

How do I install Ollama MCP Agent?
Clone the GitHub repository, ensure Python 3.12+, install Ollama and uv package, then follow setup instructions.
Can I use Ollama MCP Agent without an MCP server?
Yes, the MCP server is optional; you can run local LLMs standalone.
What are the system requirements for Ollama MCP Agent?
Requires Python 3.12 or higher, Ollama installed locally, and uv package for Python.
Does Ollama MCP Agent support streaming responses?
Yes, it supports streaming output from LLMs for real-time interaction.
Can I monitor tool calls with Ollama MCP Agent?
Yes, it provides tool call information monitoring during LLM usage.
Is Ollama MCP Agent free to use?
Yes, it allows free use of local LLM models without additional costs.
Which LLM providers does Ollama MCP Agent support?
Primarily Ollama's local models, but it includes examples for Gemini and can be extended to others like OpenAI and Claude.
How does Ollama MCP Agent extend LLM capabilities?
By leveraging MCP features, it enables enhanced context handling and tool integrations with local models.