What is Mcp Ollama Beeai

mcp-ollama-beeai is a minimal client application designed to interact with local OLLAMA models. It leverages multiple MCP server tools through the BeeAI framework to facilitate communication and operations.

Use cases

Use cases for mcp-ollama-beeai include developing chatbots, automating database queries, and enhancing user interaction with AI-driven applications.

How to use

To use mcp-ollama-beeai, first ensure you have a local OLLAMA server running. Install it using the provided commands, configure your MCP agents in the ‘mcp-servers.json’ file, and set any necessary environment variables in the .env file. Finally, boot up the application using npm start.

Key features

Key features of mcp-ollama-beeai include its ability to interface with local OLLAMA models, support for multiple MCP agents, and a user-friendly chat interface that displays AI thought processes during operations.

Where to use

mcp-ollama-beeai can be used in various fields such as AI research, software development, and data analysis, particularly where interaction with language models and database operations are required.

🤖 mcp-ollama-beeai

A minimal client app to interact with local OLLAMA models leveraging multiple MCP agent tools using BeeAI framework.

Below is a sample visual of this client app with chat interface, displaying the postgres database operation performed with thinking steps the AI has taken to use the right MCP agent and tranforming the request & response with LLM:

Usage

📋 Pre-requisite

1. Local ollama server

Install and serve ollama in your local machine with the following commands.

• Make sure you have enough memory available in your machine, atleast 16GB RAM for models to perform.
• Skip this installation in your local, if you’re going to use a remote server for model.

        $ curl -fsSL https://ollama.com/install.sh | sh
        $ ollama serve
        $ ollama pull llama3.1

2. MCP servers list configuration

Add your MCP agents in the mcp-servers.json file in root folder, for the app to pickup and work along with the LLM.

• Default servers included are postgres and fetch. Make sure to update you postgres connection URL
• List of other MCP agent tools availabe for configuration - https://modelcontextprotocol.io/examples

3 .env

If you want to use a different LLM model and LLM server, override the below properties before npm start

        OLLAMA_CHAT_MODEL=llama3.1
        OLLAMA_BASE_URL=http://localhost:11434/api

🎮 Boot up your app

        $ git clone https://github.com/tamdilip/mcp-ollama-beeai.git
        $ cd mcp-ollama-beeai
        $ npm i
        $ npm start

Once the app is up and running, hit in Browser -> http://localhost:3000

Additional Context:

• By default on landing no MCP agent is referred for the questions.
• The respective MCP agent to be used a question can be selected from the Server & tools dropdown in UI.
• BeeAI framework is used for ease setup of ReAct (Reason And Act) agent with MCP tools.
• Markdown JS library is used to render the responses in proper readable visual format.

Happy coding :) !!