Skip to main content
Glama
WOODSEE-DIGI

Qwen3 MCP Server

by WOODSEE-DIGI
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

Qwen3 MCP Server

A Model Context Protocol (MCP) server ecosystem providing access to multiple AI models optimized for different tasks: code generation, vision analysis, and complex reasoning.

๐Ÿš€ Quick Start

# Automated setup
./setup.sh

# Start default server
python src/main.py

# Or use ephemeral model switching
ask-qwen3 "Write a Python function"    # Code generation
ask-vision "Analyze this image"        # Visual analysis  
ask-ministral "Solve this equation"     # Complex reasoning

Related MCP server: imagine-mcp

๐Ÿ“š Documentation

Essential Guides

Quick Navigation

๐ŸŒŸ Features

Multi-Model Ecosystem

  • Qwen3-Coder-Next: Code generation, debugging, technical writing

  • Qwen3-VL-8B: Image analysis, UI review, document OCR

  • Qwen3-30B: Complex reasoning with thinking mode

  • Ministral-3-14B: Mathematical reasoning and logical analysis

Flexible Hosting

  • Ollama: Local model serving (recommended)

  • HTTP API: Remote model endpoints

  • Transformers: Direct model loading

  • Ephemeral Switching: Dynamic model selection

Developer Experience

  • MCP Compliance: Full Model Context Protocol support

  • Shell Integration: Quick aliases and commands

  • Warp Integration: Native Warp agent support

  • Multi-Transport: stdio and HTTP transports

  • Thinking Mode: Detailed reasoning visualization

๐ŸŽฏ Use Cases

Task

Recommended Model

Command

Code Review

Qwen3-Coder

ask-qwen3 "Review this code"

UI Analysis

Qwen3-Vision

ask-vision "Analyze this screenshot"

Math Problems

Ministral

ask-ministral "Solve step-by-step"

System Design

Qwen3-30B

python src/main.py --enable-thinking

Document OCR

Qwen3-Vision

ask-vision "Extract text from image"

Algorithm Design

Qwen3-Coder

ask-qwen3 "Implement data structure"

โšก Quick Commands

Model Switching

mcp-qwen3     # Code-focused development
mcp-vision    # Visual analysis tasks
mcp-ministral # Reasoning and mathematics
mcp-all       # Enable all models
mcp-clean     # Reset to clean state

One-Shot Tasks

ask-qwen3 "Write a REST API endpoint"
ask-vision "What's wrong with this UI?"
ask-ministral "Prove this theorem"

Server Management

# Start with specific model
python src/main.py --model-method ollama --ollama-model qwen3:30b-a3b

# Start with HTTP endpoint
python src/main.py --model-method http --http-model qwen/qwen3-coder-next

# Enable debug logging
python src/main.py --log-level DEBUG

๐Ÿ”ง System Requirements

  • Python: 3.10+ (3.12+ recommended)

  • Memory: 16GB+ RAM (32GB+ for 30B model)

  • Network: Access to HTTP endpoints or Ollama service

  • OS: macOS, Linux, Windows

  • Optional: CUDA-compatible GPU for Transformers method

๐Ÿšฆ Health Check

# Check system status
mcp-list

# Test specific model
ask-ministral "Hello, are you working?"

# Verify endpoints
curl -s http://localhost:1234/v1/models

๐Ÿ“ Project Structure

qwen3-mcp-server/
โ”œโ”€โ”€ docs/                  # ๐Ÿ“š Comprehensive documentation
โ”‚   โ”œโ”€โ”€ SETUP.md          # Installation and configuration
โ”‚   โ”œโ”€โ”€ USAGE.md          # Usage patterns and examples
โ”‚   โ””โ”€โ”€ MODELS.md         # Model reference and capabilities
โ”œโ”€โ”€ src/                   # ๐Ÿ”ง Core implementation
โ”‚   โ”œโ”€โ”€ main.py           # Entry point and CLI
โ”‚   โ”œโ”€โ”€ server.py         # MCP server implementation  
โ”‚   โ”œโ”€โ”€ model_interface.py # Model hosting abstractions
โ”‚   โ””โ”€โ”€ config.py         # Configuration management
โ”œโ”€โ”€ config/                # โš™๏ธ Model configurations
โ”‚   โ”œโ”€โ”€ qwen3-coder-http.json
โ”‚   โ”œโ”€โ”€ qwen3-vl-8b-http.json
โ”‚   โ””โ”€โ”€ ministral-3-14b-reasoning-http.json
โ”œโ”€โ”€ scripts/               # ๐Ÿค– Automation scripts
โ”‚   โ””โ”€โ”€ switch-model.sh   # Model switching logic
โ”œโ”€โ”€ AGENTS.md             # ๐Ÿค– Warp agent guidance
โ”œโ”€โ”€ setup.sh              # ๐Ÿš€ Automated setup
โ””โ”€โ”€ requirements.txt      # ๐Ÿ“ฆ Python dependencies


## ๐Ÿ“„ License

MIT License - see [LICENSE](LICENSE) file for details.

## ๐Ÿ™ Acknowledgments

- [Model Context Protocol](https://modelcontextprotocol.io/) by Anthropic
- [Qwen Team](https://github.com/QwenLM) for the Qwen3 models  
- [Ollama](https://ollama.ai/) for local model hosting
- [Mistral AI](https://mistral.ai/) for the Ministral reasoning model

This server cannot be deployed

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • Deepseek MCP Server

    arikusi
    A
    license
    A
    quality
    A
    maintenance
    MCP server for DeepSeek AI models (Chat + Reasoner). Supports multi-turn sessions, model fallback with circuit breaker, function calling, thinking mode, JSON output, multimodal input, and cost tracking.
    3
    335 npm
    19
    MIT

  • picsense

    honlnk
    A
    license
    Not graded
    quality
    D
    maintenance
    Local MCP server that provides multi-modal vision capabilities to single-modal base models via API, supporting multi-turn iterative image recognition and document image parsing.
    5 npm
    Apache 2.0