mcpField
🤖
🤖 mcp-ollama-beeai

🤖 mcp-ollama-beeai

Local
github.com/tamdilipAI & Agents5Updated 80w ago
Repository

About 🤖 mcp-ollama-beeai

mcp-ollama-beeai is a BeeAI-based chat app for using multiple MCP server tools with OLLAMA models. Its interface lets users select servers and tools, and displays agent reasoning steps and formatted responses.

Key features

  1. 01Chat with OLLAMA models
  2. 02Configure and use multiple MCP servers
  3. 03Choose servers and tools in the interface
  4. 04Display agent reasoning steps
  5. 05Render responses in Markdown

Use cases

  1. 01Use configured MCP tools through a chat interface
  2. 02Have a local OLLAMA model call the Postgres server
  3. 03Select a specific MCP server to handle a request

MCP support

As an MCP client, it reads server configurations from mcp-servers.json and uses BeeAI to call selected MCP servers and their tools.

#machine-learning#mcp#chatbot#mcpe-server#reason-react#ollama#agentic-ai#llama3-1#beeai

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

🤖 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: demo-pic

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.

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 :) !!

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.