simple-mcp-server

simple-mcp-server

0

The project features a hybrid architecture MCP server that follows the official Anthropic MCP specification. It includes middleware for communication and uses Ollama's Gemma model for inference, providing a robust environment for managing conversation contexts.

Anthropic Model Context Protocol (MCP) Server with Ollama Integration

A hybrid architecture combining an Anthropic-compatible Model Context Protocol (MCP) server with Ollama/Gemma LLMs for inference.

Components

  • MCP Server: Implements the Anthropic MCP protocol on port 3000.
  • Middleware: Facilitates communication between clients and Ollama.
  • Ollama: Runs the Gemma3:4b model for inference.
  • Database: SQLite database for storing conversation contexts.

Features

  • Tools for context management and resources to expose conversation history.
  • Compatible with any client supporting the Model Context Protocol.

Protocol Compliance

Adheres strictly to the official MCP specification with JSON-RPC 2.0, protocol initialization, tool interface, and resource management.

Requirements

  • Python 3.10+
  • Docker and Docker Compose
  • Ollama with Gemma3:4b model installed.

Installation

Supports setup using either a script or manual Docker-based configuration.

Usage Example

Available for use through middleware or directly via the MCP server with compatible clients.