Ollama MCP Chat logo

Ollama MCP Chat

by godstale

Ollama MCP Chat is a desktop chatbot application integrating local LLM models with MCP servers, supporting tool calls and extensible features. It provides a GUI based on Python and PySide6, allowing you to extend its capabilities via MCP servers.

View on GitHub

Last updated: N/A

What is Ollama MCP Chat?

Ollama MCP Chat is a desktop application that allows users to interact with local LLM models managed by Ollama and extend their capabilities through MCP (Model Context Protocol) servers. It provides a graphical interface for chatting, managing chat history, and configuring MCP servers to integrate various tools.

How to use Ollama MCP Chat?

To use Ollama MCP Chat, first install Python 3.12+, Ollama, and uv. Clone the repository, install dependencies using uv sync, and configure MCP servers in mcp_config.json (optional). Run the application using uv run main.py. The GUI will launch, allowing you to chat with the LLM and utilize configured MCP tools.

Key features of Ollama MCP Chat

  • Run Ollama LLM models locally for free

  • Integrate and call various tools via MCP servers

  • Manage and save chat history

  • Real-time streaming responses and tool call results

  • Intuitive desktop GUI (PySide6-based)

  • GUI support for adding, editing, and removing MCP servers

Use cases of Ollama MCP Chat

  • Developing AI applications with GUI in Python

  • Creating chatbots with local LLM models

  • Integrating external tools and services into a chatbot

  • Experimenting with different LLM models and MCP configurations

FAQ from Ollama MCP Chat

Can I use Ollama MCP Chat without configuring MCP servers?

Yes, basic LLM chat functionality works even without MCP server configuration.

What languages can MCP servers be implemented in?

MCP servers can be implemented in Python, Node.js, or other languages.

Where is the chat history saved?

All conversations are automatically saved to chat_history.json.

How do I exit the application?

Type quit, exit, or bye in the program to exit.

What are the system requirements?

Python 3.12 or higher, Ollama installed, uv (recommended), and an MCP server (optional).