📌Overview

Purpose: To provide a user-friendly web interface for interacting with Large Language Models (LLMs) while managing context aggregation within the Model Context Protocol (MCP) architecture.

Overview: MCP Web UI simplifies AI language model interactions by offering a unified platform for diverse LLM providers, fostering real-time chat experiences and comprehensive model management through robust context handling mechanisms.

Key Features:

Multi-Provider LLM Integration: Supports various models from Anthropic, OpenAI, Ollama, and OpenRouter, allowing users to switch easily between them.
Intuitive Chat Interface: Enhances user experience with an accessible and interactive chat environment for seamless communication with AI.
Real-time Response Streaming: Employs Server-Sent Events (SSE) for providing instantaneous responses, enriching the user engagement during conversations.
Dynamic Configuration Management: Facilitates customizable settings for model management, including advanced parameters for fine-tuning AI behavior.
Advanced Context Aggregation: Utilizes the MCP protocol for efficient context handling across multiple interactions, maintaining continuity in conversation.
Persistent Chat History: Ensures users can access past interactions via BoltDB, promoting better follow-up and analysis of previous AI interactions.
Flexible Model Selection: Empowers users to choose and configure different language models as per their specific needs and preferences.

MCP Web UI

MCP Web UI is a web-based user interface designed to facilitate interaction with Large Language Models (LLMs) within the Model Context Protocol (MCP) architecture.

Overview

MCP Web UI simplifies interactions with AI language models by providing:

A unified interface for multiple LLM providers
Real-time, streaming chat experiences
Flexible configuration and model management
Robust context handling using the MCP protocol

Features

Multi-Provider LLM Integration:
- Anthropic (Claude models)
- OpenAI (GPT models)
- Ollama (local models)
- OpenRouter (multiple providers)
Intuitive Chat Interface
Real-time Response Streaming
Dynamic Configuration Management
Advanced Context Aggregation
Persistent Chat History
Flexible Model Selection

Prerequisites

Go 1.23+
Docker (optional)
API keys for desired LLM providers

Installation

Quick Start

Clone the repository:

git clone https://github.com/MegaGrindStone/mcp-web-ui.git
cd mcp-web-ui

Configure your environment:

mkdir -p $HOME/.config/mcpwebui
cp config.example.yaml $HOME/.config/mcpwebui/config.yaml

Set up API keys:

export ANTHROPIC_API_KEY=your_anthropic_key
export OPENAI_API_KEY=your_openai_key
export OPENROUTER_API_KEY=your_openrouter_key

Running the Application

Local Development

go mod download
go run ./cmd/server/main.go

Docker Deployment

docker build -t mcp-web-ui .
docker run -p 8080:8080 \
  -v $HOME/.config/mcpwebui/config.yaml:/app/config.yaml \
  -e ANTHROPIC_API_KEY \
  -e OPENAI_API_KEY \
  -e OPENROUTER_API_KEY \
  mcp-web-ui

Configuration

The configuration file (config.yaml) customizes the MCP Web UI. Key settings include:

Server Configuration

port: Server port (default: 8080)
logLevel: Logging verbosity (options: debug, info, warn, error; default: info)

LLM Configuration

provider: Options include: ollama, anthropic, openai, openrouter
model: Name of the specific model
parameters: Customize model behavior (e.g., temperature, maxTokens)

Example Configuration Snippet

port: 8080
logLevel: info
llm:
  provider: anthropic
  model: claude-3-5-sonnet-20241022
  parameters:
    temperature: 0.7
    maxTokens: 1000

Project Structure

cmd/: Application entry point
internal/handlers/: Web request handlers
internal/models/: Data models
internal/services/: LLM provider integrations
static/: Static assets (CSS)
templates/: HTML templates

Contributing

Fork the repository
Create a feature branch
Commit your changes
Push and create a Pull Request

License

MIT License