MCP Base - A Generic Model Context Protocol Framework
This folder contains a general-purpose base implementation of the Model Context Protocol (MCP) for building AI-powered applications. It provides a standardized way to create MCP servers and clients that can be used to integrate LLMs into your applications.
📋 Features
- Standardized MCP Server: A base server implementation with support for HTTP and stdio transports
- Generic MCP Client: A client for connecting to any MCP server
- Ollama Integration: Ready-to-use services for generating embeddings and text with Ollama
- Supabase Integration: Built-in support for Supabase vector database
- Modular Design: Clearly organized structure for resources, tools, and prompts
- Sample Templates: Example implementations to help you get started quickly
🛠️ Directory Structure
_mcp-base/
├── server.ts # Main MCP server implementation
├── client.ts # Generic MCP client
├── utils/ # Utility services
│ ├── ollama_embedding.ts # Embedding generation with Ollama
│ └── ollama_text_generation.ts # Text generation with Ollama
├── tools/ # Tool implementations
│ └── sample-tool.ts # Example tool template
├── resources/ # Resource implementations
│ └── sample-resource.ts # Example resource template
├── prompts/ # Prompt implementations
│ └── sample-prompt.ts # Example prompt template
└── README.md # This documentation
🚀 Getting Started
Prerequisites
- Node.js and npm/pnpm
- Ollama for local embedding and text generation
- Supabase account for vector storage
Environment Setup
Create a .env file with the following variables:
PORT=3000
SUPABASE_URL=https://your-project.supabase.co
SUPABASE_SERVICE_KEY=your-service-key
OLLAMA_URL=http://localhost:11434
OLLAMA_EMBED_MODEL=nomic-embed-text
OLLAMA_LLM_MODEL=llama3
SERVER_MODE=http # 'http' or 'stdio'
Server Initialization
- Import the required modules
- Register your resources, tools, and prompts
- Start the server
// Import base server and utilities
import server from "./server";
import { registerSampleResources } from "./resources/sample-resource";
import { registerSampleTool } from "./tools/sample-tool";
import { registerSamplePrompts } from "./prompts/sample-prompt";
// Initialize database if needed
async function initializeDatabase() {
// Your database initialization logic
}
// Register your components
registerSampleResources(server, supabase);
registerSampleTool(server, textGenerator, embeddings, supabase);
registerSamplePrompts(server, supabase);
// Start the server
startServer();
Client Usage
import MCPClient from "./client";
// Create a client instance
const client = new MCPClient({
serverUrl: "http://localhost:3000",
});
// Example: Call a tool
async function callSampleTool() {
const result = await client.callTool("sample-tool", {
query: "example query",
maxResults: 5,
});
console.log(result);
}
// Example: Read a resource
async function readResource() {
const items = await client.readResource("items://all");
console.log(items);
}
// Example: Get a prompt
async function getPrompt() {
const prompt = await client.getPrompt("simple-prompt", {
task: "Explain quantum computing",
});
console.log(prompt);
}
// Don't forget to disconnect when done
await client.disconnect();
📚 Extending the Framework
- Create a new file in the
tools/ directory - Define your tool function and schema using Zod
- Implement your tool logic
- Register the tool in your server
Creating a New Resource
- Create a new file in the
resources/ directory - Define your resource endpoints and schemas
- Implement your resource logic
- Register the resource in your server
Creating a New Prompt
- Create a new file in the
prompts/ directory - Define your prompt schema and parameters
- Implement your prompt template
- Register the prompt in your server
📄 License
MIT