Second Opinion MCP

Consult multiple AI models, including local, cloud, and enterprise services, to get diverse perspectives on a topic.

View on GitHub ā†’

šŸ¤– Second Opinion MCP

License Python MCP

šŸŽÆ Get instant second opinions from 17 AI platforms and 800,000+ models

OpenAI ā€¢ Gemini ā€¢ Grok ā€¢ Claude ā€¢ HuggingFace ā€¢ DeepSeek ā€¢ OpenRouter ā€¢ Mistral ā€¢ Together AI ā€¢ Cohere ā€¢ Groq ā€¢ Perplexity ā€¢ Replicate ā€¢ AI21 Labs ā€¢ Stability AI ā€¢ Fireworks AI ā€¢ Anyscale

šŸš€ What it does

This MCP server allows Claude to consult other AI models for different perspectives on:

  • Coding problems - Compare approaches across models
  • Creative writing - Get diverse style feedback
  • Problem solving - Validate logic and reasoning
  • Cross-model analysis - See how different AIs tackle the same task
  • Group discussions - Host AI debates with multiple models
  • Custom model access - Use any HuggingFace model via Inference API

āœØ Version 5.0 Features & Improvements

šŸŽ­ NEW: AI Personality System

  • 5 Distinct Personalities: honest, freind, coach, wise, creative
  • Intelligent Model Matching: Each personality uses models best suited for their character
  • Always Available: Works with any configured AI provider

šŸ§  NEW: Intelligent Model Selection

  • Quality-Based Ranking: 34+ models ranked by capability (Grok-4 ā†’ Gemini Pro ā†’ GPT-4.1)
  • Smart Defaults: Automatically selects the best available model
  • Personality Optimization: Different models for different personality types

šŸ—ļø NEW: Modular Architecture

  • 5 Clean Files: Replaced 51k+ token monolith with maintainable modules
  • Professional Structure: client_manager.py, ai_providers.py, conversation_manager.py, mcp_server.py, main.py
  • JSON Configuration: Easy model priority updates via model_priority.json

šŸš€ Major Platform Integrations

  • šŸŽ­ Replicate: Access to open-source models including Llama 2, CodeLlama, Mistral, and more
  • šŸŒŸ AI21 Labs: Jamba 1.5 models with advanced reasoning capabilities
  • šŸŽØ Stability AI: StableLM models including code-specialized variants
  • šŸ”„ Fireworks AI: Ultra-fast inference for popular open-source models
  • šŸš€ Anyscale: Ray-powered LLM serving with enterprise-grade reliability

šŸ†• Enhanced Existing Platform Support

  • šŸ¤– Mistral AI: Direct access to Mistral's latest models including mistral-large-latest and codestral-latest
  • šŸ”— Together AI: Access to 200+ open-source models with fast inference
  • šŸ§  Cohere: Enterprise-grade language models with Command R+ and Command R
  • āš” Groq Fast: Ultra-fast inference API for lightning-quick responses
  • šŸ” Perplexity AI: Web-connected AI with real-time search capabilities

šŸ”§ Previous Bug Fixes (v3.0)

  • Fixed HuggingFace Models: Completely rebuilt HuggingFace integration with advanced retry logic, better model format detection, and comprehensive error handling
  • Fixed Gemini Blank Responses: Enhanced Gemini conversation handling to prevent empty responses in long chats with smart fallback and retry mechanisms
  • Improved Error Handling: Better error messages with helpful suggestions for troubleshooting

šŸ¤– HuggingFace Integration (Enhanced)

Access any of the 800,000+ models on HuggingFace Hub via their Inference API with improved reliability:

  • meta-llama/Llama-3.1-8B-Instruct - Fast and reliable
  • meta-llama/Llama-3.1-70B-Instruct - Powerful reasoning
  • mistralai/Mistral-7B-Instruct-v0.3 - Efficient French-developed model
  • Qwen/Qwen2.5-7B-Instruct - Alibaba's latest model

šŸ§  DeepSeek Models

Get opinions from DeepSeek's powerful reasoning models:

  • deepseek-chat (DeepSeek-V3) - Fast and efficient
  • deepseek-reasoner (DeepSeek-R1) - Advanced reasoning

šŸ¤” Grok 4 Thinking

Access xAI's thinking models with enhanced reasoning:

  • grok-4 - Latest flagship model
  • grok-3-thinking - Step-by-step reasoning model, last gen
  • grok-3-mini - Lightweight thinking model with reasoning_effort control, last ge

šŸŽ­ Group Discussions (Enhanced)

Start multi-AI discussions where models can see and respond to each other's input:

> "Start a group discussion about the future of AI with GPT-4.1, Claude-4, Mistral, and Perplexity"

šŸ”§ Enhanced Performance

  • Longer responses: Increased max_tokens (4000 default) to prevent cut-off responses
  • Better error handling: More robust API interactions with exponential backoff
  • Conversation persistence: Enhanced memory management with better context handling
  • Smart retry logic: Automatic retries with progressive delays for better reliability

šŸ“‹ Requirements

Python Claude Desktop API Keys

  • Python 3.8+ - Programming language runtime
  • Claude Desktop or Claude Code - Choose your preferred MCP integration
  • API Keys - For any combination of the 16 supported AI platforms

šŸ“¦ Installation Guide

šŸš€ Quick Start

  1. šŸ“„ Clone the repository

    git clone https://github.com/ProCreations-Official/second-opinion.git
cd second-opinion

  2. āš™ļø Install dependencies

    pip install -r requirements.txt

  3. šŸ”‘ Get API Keys

    PlatformLinkRequired
    OpenAIplatform.openai.comā­ Popular
    Geminiaistudio.google.comā­ Popular
    Grokx.aišŸ”„ Best benchmarks
    Claudeanthropic.comšŸ§  Advanced
    HuggingFacehuggingface.cošŸ¤— 800k+ Models
    DeepSeekdeepseek.comšŸ”¬ Reasoning
    OpenRouteropenrouter.aišŸŒ 200+ Models via One API
    Mistralconsole.mistral.aišŸ‡«šŸ‡· European, fast
    Together AIapi.together.xyzšŸ”— 200+ Models
    Coheredashboard.cohere.comšŸ¢ Enterprise
    Groqconsole.groq.comāš” Ultra-Fast
    Perplexityperplexity.aišŸ” Web Search
    Replicatereplicate.comšŸŽ­ Open Source
    AI21 Labsstudio.ai21.comšŸ§¬ Jamba Models
    Stability AIplatform.stability.aišŸŽØ StableLM
    Fireworks AIfireworks.aišŸ”„ Fast Inference
    Anyscaleconsole.anyscale.comšŸš€ Ray Serving

  4. šŸ”§ Choose Your Integration Method

    Select the method that matches your Claude setup:

For Claude Desktop Users

Add this to your Claude Desktop MCP configuration:

{
  "mcpServers": {
    "second-opinion": {
      "command": "python3",
      "args": ["/path/to/your/main.py"],
      "env": {
        "OPENAI_API_KEY": "your_openai_key_here",
        "GEMINI_API_KEY": "your_gemini_key_here",
        "GROK_API_KEY": "your_grok_key_here",
        "CLAUDE_API_KEY": "your_claude_key_here",
        "HUGGINGFACE_API_KEY": "your_huggingface_key_here",
        "DEEPSEEK_API_KEY": "your_deepseek_key_here",
        "OPENROUTER_API_KEY": "your_openrouter_key_here",
        "MISTRAL_API_KEY": "your_mistral_key_here",
        "TOGETHER_API_KEY": "your_together_key_here",
        "COHERE_API_KEY": "your_cohere_key_here",
        "GROQ_FAST_API_KEY": "your_groq_key_here",
        "PERPLEXITY_API_KEY": "your_perplexity_key_here",
        "REPLICATE_API_TOKEN": "your_replicate_key_here",
        "AI21_API_KEY": "your_ai21_key_here",
        "STABILITY_API_KEY": "your_stability_key_here",
        "FIREWORKS_API_KEY": "your_fireworks_key_here",
        "ANYSCALE_API_KEY": "your_anyscale_key_here"
      }
    }
  }
}

šŸ’” Note: You only need to add API keys for the services you want to use. Missing keys will simply disable those specific features.

šŸ”„ Restart Claude Desktop after configuration.

šŸŽÆ For Claude Code CLI Users

Claude Code MCP

šŸ“¦ Prerequisites

First, ensure Claude Code CLI is installed globally:

npm install -g @anthropic-ai/claude-code

šŸš€ Installation Methods

Use the claude mcp add command to add the Second Opinion server:

# Navigate to your second-opinion directory
cd /path/to/your/second-opinion

# Add the MCP server with environment variables (use -e for each API key)
claude mcp add second-opinion -s user \
  -e OPENAI_API_KEY=your_openai_key_here \
  -e GEMINI_API_KEY=your_gemini_key_here \
  -e GROK_API_KEY=your_grok_key_here \
  -e CLAUDE_API_KEY=your_claude_key_here \
  -e HUGGINGFACE_API_KEY=your_huggingface_key_here \
  -e DEEPSEEK_API_KEY=your_deepseek_key_here \
  -e OPENROUTER_API_KEY=your_openrouter_key_here \
  -e MISTRAL_API_KEY=your_mistral_key_here \
  -e TOGETHER_API_KEY=your_together_key_here \
  -e COHERE_API_KEY=your_cohere_key_here \
  -e GROQ_FAST_API_KEY=your_groq_key_here \
  -e PERPLEXITY_API_KEY=your_perplexity_key_here \
  -e REPLICATE_API_TOKEN=your_replicate_key_here \
  -e AI21_API_KEY=your_ai21_key_here \
  -e STABILITY_API_KEY=your_stability_key_here \
  -e FIREWORKS_API_KEY=your_fireworks_key_here \
  -e ANYSCALE_API_KEY=your_anyscale_key_here \
  -- /path/to/your/second-opinion/run.sh

šŸ’” Quick Setup: You only need to include -e flags for the API keys you have. For example, if you only have OpenAI and Gemini keys:

claude mcp add second-opinion -s user \
  -e OPENAI_API_KEY=your_openai_key_here \
  -e GEMINI_API_KEY=your_gemini_key_here \
  -- /path/to/your/second-opinion/run.sh

Alternatively, you can manually add the server to your .claude.json file:

{
  "mcpServers": {
    "second-opinion": {
      "type": "stdio",
      "command": "/path/to/your/second-opinion/run.sh",
      "env": {
        "OPENAI_API_KEY": "your_openai_key_here",
        "GEMINI_API_KEY": "your_gemini_key_here",
        "GROK_API_KEY": "your_grok_key_here",
        "CLAUDE_API_KEY": "your_claude_key_here",
        "HUGGINGFACE_API_KEY": "your_huggingface_key_here",
        "DEEPSEEK_API_KEY": "your_deepseek_key_here",
        "OPENROUTER_API_KEY": "your_openrouter_key_here",
        "MISTRAL_API_KEY": "your_mistral_key_here",
        "TOGETHER_API_KEY": "your_together_key_here",
        "COHERE_API_KEY": "your_cohere_key_here",
        "GROQ_FAST_API_KEY": "your_groq_key_here",
        "PERPLEXITY_API_KEY": "your_perplexity_key_here",
        "REPLICATE_API_TOKEN": "your_replicate_key_here",
        "AI21_API_KEY": "your_ai21_key_here",
        "STABILITY_API_KEY": "your_stability_key_here",
        "FIREWORKS_API_KEY": "your_fireworks_key_here",
        "ANYSCALE_API_KEY": "your_anyscale_key_here"
      }
    }
  }
}

šŸ”§ Why Use run.sh?

FeatureBenefit
šŸ“¦ Dependency ManagementAutomatically installs/updates requirements
šŸ›”ļø Error HandlingChecks for python3 availability and required files
šŸ”„ Cross-platformWorks better than direct Python execution
āš” ReliabilityEnsures consistent execution regardless of system

āœ… Verification

Check that your MCP server is properly installed:

claude mcp list

You should see second-opinion in the list of available MCP servers.

šŸ”‘ Environment Variables: You only need to add API keys for the services you want to use. Missing keys will simply disable those specific AI platforms. The server will work with any combination of available API keys.

Total Models Platforms Updated

šŸš€ Premium AI Platforms

ModelDescriptionBest For
o4-miniFast reasoning modelāš” Quick reasoning
gpt-4.1Latest flagship non-reasoning modelšŸŽÆ General tasks
gpt-4oMultimodal powerhousešŸ–¼ļø Vision + text
gpt-4o-miniLightweight GPT-4ošŸ’° Cost-effective
ModelDescriptionBest For
gemini-2.5-flash-lite-preview-06-17Lightweight and fastāš” Quick responses
gemini-2.5-flashAdvanced reasoning and efficiencyšŸ§® Complex analysis
gemini-2.5-proMost capable Gemini modelšŸ§  Advanced tasks
ModelDescriptionBest For
grok-4Latest flagship modelšŸŽÆ General excellence, best
grok-3-thinkingStep-by-step reasoningšŸ¤” Deep thinking (use grok 4)
grok-3-miniLightweight modelšŸ’” Quick insights
ModelDescriptionBest For
claude-4-opus-20250522Most advanced ClaudešŸ§  Complex reasoning
claude-4-sonnet-20250522Versatile general tasksāš–ļø Balanced performance
claude-3-7-sonnet-20250224Stable and reliablešŸ›”ļø Production use
claude-3-5-sonnet-20241022Efficient, lighter modelšŸ’Ø Fast responses

Featured Models:

ModelDescriptionBest For
meta-llama/Llama-3.1-8B-InstructFast Meta modelāš” Speed
meta-llama/Llama-3.1-70B-InstructPowerful reasoningšŸ§  Complex tasks
mistralai/Mistral-7B-Instruct-v0.3French-developedšŸ‡«šŸ‡· European AI
Qwen/Qwen2.5-7B-InstructAlibaba's latestšŸ¢ Enterprise

šŸŒŸ Special: Access to any model on HuggingFace Hub that supports text generation

šŸ”¬ Specialized AI Platforms

ModelDescriptionBest For
deepseek-chatDeepSeek-V3 general tasksšŸ’¬ Conversations
deepseek-reasonerDeepSeek-R1 advanced reasoningšŸ§  Complex logic
ModelDescriptionBest For
anthropic/claude-3-5-sonnet-20241022OpenRouter access to Claude 3.5 SonnetšŸŽÆ Balanced excellence
openai/gpt-4-turboOpenRouter access to GPT-4 TurbošŸ§  Advanced reasoning
google/gemini-pro-1.5OpenRouter access to Gemini Pro 1.5šŸ” Long context
meta-llama/llama-3.1-405b-instructOpenRouter access to largest LlamašŸ¦£ Massive scale
mistralai/mistral-largeOpenRouter access to Mistral LargešŸ‡«šŸ‡· European excellence
perplexity/llama-3.1-sonar-huge-128k-onlineWeb-connected via OpenRouteršŸŒ Current information

šŸŒŸ Special: Access to 200+ models from multiple providers through a single OpenRouter API

ModelDescriptionBest For
mistral-large-latestMost powerful MistralšŸŽÆ Top performance
mistral-small-latestFast and cost-effectivešŸ’° Budget-friendly
mistral-medium-latestBalanced performanceāš–ļø General use
codestral-latestCode generation specialistšŸ’» Programming
ModelDescriptionBest For
meta-llama/Llama-3.1-8B-Instruct-TurboFast Llama turboāš” Speed
meta-llama/Llama-3.1-70B-Instruct-TurboPowerful Llama turbošŸš€ Performance
meta-llama/Llama-3.1-405B-Instruct-TurboLargest Llama modelšŸ¦£ Massive scale
mistralai/Mixtral-8x7B-Instruct-v0.1Mixture of expertsšŸŽ­ Specialized tasks
Qwen/Qwen2.5-72B-Instruct-TurboAlibaba's fast modelšŸ¢ Enterprise

Cohere (Enterprise-grade)

ModelDescriptionBest For
command-r-plusMost capable CoherešŸŽÆ Enterprise
command-rBalanced performanceāš–ļø General business
commandStandard command modelšŸ’¼ Basic tasks

Groq (Ultra-fast inference)

ModelDescriptionBest For
llama-3.1-70b-versatileFast 70B Llamaāš” Quick power
llama-3.1-8b-instantLightning-fast 8BšŸƒ Instant responses
mixtral-8x7b-32768Fast Mixtral variantšŸŽ­ Quick specialization
gemma2-9b-itGoogle's Gemma modelšŸ” Search-optimized

Perplexity AI (Web-connected)

ModelDescriptionBest For
llama-3.1-sonar-large-128k-onlineWeb search + large contextšŸŒ Research
llama-3.1-sonar-small-128k-onlineWeb search + fast responsesšŸ” Quick search
llama-3.1-sonar-large-128k-chatPure chat without webšŸ’¬ Conversations
llama-3.1-sonar-small-128k-chatFast chat modelāš” Quick chat

Replicate (Open-source hosting)

ModelDescriptionBest For
meta/llama-2-70b-chatLarge Llama 2 chatšŸ¦£ Powerful chat
meta/llama-2-13b-chatMedium Llama 2 chatāš–ļø Balanced
meta/codellama-34b-instructCode-specialized LlamašŸ’» Programming
microsoft/wizardcoder-34bMicrosoft's coding modelšŸ§™ Code magic

AI21 Labs (Advanced reasoning)

ModelDescriptionBest For
jamba-1.5-largeState-space capabilitiesšŸ§¬ Complex reasoning
jamba-1.5-miniCompact Jamba modelšŸ’Ž Efficient reasoning
j2-ultraJurassic-2 Ultra modelšŸ¦• Powerful
j2-midJurassic-2 Mid modelāš–ļø Balanced

Stability AI (StableLM family)

ModelDescriptionBest For
stablelm-2-zephyr-1_6bEfficient 1.6B parameterāš” Lightweight
stable-code-instruct-3bCode-specialized 3BšŸ’» Programming
japanese-stablelm-instruct-beta-70bJapanese languagešŸ‡ÆšŸ‡µ Japanese tasks
stablelm-zephyr-3bBalanced 3B parameterāš–ļø General use

Fireworks AI (Ultra-fast inference)

ModelDescriptionBest For
accounts/fireworks/models/llama-v3p1-70b-instructFast Llama 3.1 70BšŸ”„ Speed + power
accounts/fireworks/models/llama-v3p1-8b-instructFast Llama 3.1 8Bāš” Quick responses
accounts/fireworks/models/mixtral-8x7b-instructFast Mixtral modelšŸŽ­ Fast specialization
accounts/fireworks/models/deepseek-coder-v2-lite-instructCode-specializedšŸ’» Fast coding

Anyscale (Ray-powered serving)

ModelDescriptionBest For
meta-llama/Llama-2-70b-chat-hfEnterprise Llama 2 70BšŸ¢ Enterprise chat
meta-llama/Llama-2-13b-chat-hfEnterprise Llama 2 13BšŸ’¼ Business tasks
codellama/CodeLlama-34b-Instruct-hfEnterprise CodeLlamašŸ’» Enterprise coding
mistralai/Mistral-7B-Instruct-v0.1Enterprise MistralšŸ‡«šŸ‡· Enterprise EU
ā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆā–ˆ

šŸ’” Usage Examples

šŸŽ­ NEW: Personality Examples

šŸ˜¤ "Give me an honest opinion about this code" (brutally frank feedback)

šŸ’• "I need some encouragement with this project" (supportive girlfriend mode)

šŸ† "Help me stay motivated to finish this task" (motivational coach)

šŸ§™ "What's the deeper meaning behind this design pattern?" (ancient wisdom)

šŸŽØ "Think of a creative solution to this problem" (innovative thinking)

šŸ¤– "Just give me the best available opinion" (automatic smart selection)

šŸ”„ Popular Requests

šŸ’¬ "Get a second opinion from GPT-4.1 on this coding approach"

šŸ¤” "What would Grok-4 think about this solution?" (NEW: Latest model)

āš–ļø "Compare how Claude-4-opus and gemini-2.5-flash would solve this problem"

šŸ¤— "Get an opinion from meta-llama/Llama-3.1-70B-Instruct on HuggingFace"

šŸŒ "Get an OpenRouter opinion from anthropic/claude-3-5-sonnet-20241022"

šŸ§  "What does DeepSeek-reasoner think about this math problem?"

šŸ‡«šŸ‡· "Ask Mistral-large-latest to review my code architecture"

āš” "Get a fast response from Groq's llama-3.1-8b-instant model"

šŸŒ "Use Perplexity's web search to research the latest AI developments"

šŸ¢ "What does Cohere's command-r-plus think about this business strategy?"

šŸ”— "Get Together AI's Llama-405B opinion on this complex problem"

šŸŽ­ Advanced Features

šŸ—£ļø "Start a group discussion about AI ethics with GPT-4.1, Claude-4, Mistral, and Perplexity"

šŸ“Š "Cross-platform comparison of this algorithm across all 16 available platforms"

šŸŽ­ "Get a Replicate opinion from meta/llama-2-70b-chat on this open-source approach"

šŸ§¬ "What does AI21's Jamba-1.5-large think about this reasoning problem?"

šŸŽØ "Ask Stability AI's StableLM about this code optimization"

šŸ”„ "Get a super-fast response from Fireworks AI's Llama model"

šŸš€ "Use Anyscale's enterprise-grade Llama serving for this complex task"

šŸ”§ Available Tools

Single Model Opinions

  • get_openai_opinion - Get opinion from any OpenAI model
  • get_gemini_opinion - Get opinion from any Gemini model (enhanced with better conversation handling)
  • get_grok_opinion - Get opinion from any Grok model (includes thinking models)
  • get_claude_opinion - Get opinion from any Claude model
  • get_huggingface_opinion - Get opinion from any HuggingFace model (enhanced with better reliability)
  • get_deepseek_opinion - Get opinion from DeepSeek models
  • get_openrouter_opinion - Get opinion from 200+ models via OpenRouter (NEW)
  • get_mistral_opinion - Get opinion from Mistral AI models (NEW)
  • get_together_opinion - Get opinion from Together AI's 200+ models (NEW)
  • get_cohere_opinion - Get opinion from Cohere enterprise models (NEW)
  • get_groq_fast_opinion - Get ultra-fast responses from Groq (NEW)
  • get_perplexity_opinion - Get web-connected AI responses
  • get_replicate_opinion - Get opinion from Replicate's open-source models (NEW)
  • get_ai21_opinion - Get opinion from AI21 Labs' Jamba models (NEW)
  • get_stability_opinion - Get opinion from Stability AI's StableLM models (NEW)
  • get_fireworks_opinion - Get ultra-fast responses from Fireworks AI (NEW)
  • get_anyscale_opinion - Get enterprise-grade responses from Anyscale (NEW)

Model Comparisons

  • compare_openai_models - Compare multiple OpenAI models
  • compare_gemini_models - Compare multiple Gemini models
  • compare_grok_models - Compare multiple Grok models
  • compare_claude_models - Compare multiple Claude models

šŸŽ­ NEW: Personality & Smart Default Tools

  • get_personality_opinion - Get AI responses with specific personality (honest, gf, coach, wise, creative)
  • get_default_opinion - Automatically uses the best available model (Grok-4 ā†’ Gemini Pro ā†’ GPT-4.1)
  • list_personalities - See all available AI personalities and their descriptions

Cross-Platform Features

  • cross_platform_comparison - Compare across all 17 AI platforms: OpenAI, Gemini, Grok, Claude, HuggingFace, DeepSeek, OpenRouter, Mistral, Together AI, Cohere, Groq Fast, Perplexity, Replicate, AI21 Labs, Stability AI, Fireworks AI & Anyscale
  • group_discussion - Multi-round discussions between AI models with shared context (supports all platforms)

Conversation Management

  • list_conversation_histories - See active conversation threads
  • clear_conversation_history - Reset conversation memory for specific models

šŸ§  Advanced Features

GPT 5 Thinking Models

For deeper reasoning, use thinking models:

> "Get a GPT 5 thinking opinion on this complex math problem with high reasoning effort"

This will use GPT 5 with reasoning effort set to high.

Group Discussions

Create AI debates and collaborative problem-solving:

> "Start a group discussion about renewable energy solutions with 3 rounds between GPT-4.1, Claude-4, Gemini, and DeepSeek"

Each AI can see previous responses and build on the discussion.

HuggingFace Model Access

Access cutting-edge open source models:

> "Get an opinion from Qwen/Qwen3-30B-A3B-Instruct-2507 about chatbot design patterns"

may be broken Perfect for testing specialized models or comparing open source vs proprietary AI.

šŸ”’ Security

Your API keys stay private on your machine. The MCP server only sends model responses to the client, never your credentials.

šŸ›Ÿ Troubleshooting

Import errors: Ensure you've installed all dependencies with pip install -r requirements.txt

API errors: Check that your API keys are correct and active

Server not connecting: Verify the file path in your MCP configuration

Cut-off responses: The new version uses 4000 max_tokens by default to prevent truncation

HuggingFace timeouts: Some models may take time to load. Try again after a few moments.

Model not available: Check if the HuggingFace model supports text generation or chat completion

šŸš€ What's New in v5.0

  • āœ… šŸŽ­ AI Personality System: 5 distinct personalities (honest, gf, coach, wise, creative) with optimized model selection
  • āœ… šŸ§  Intelligent Model Selection: Quality-ranked models with Grok-4 as top priority, smart defaults
  • āœ… šŸ—ļø Modular Architecture: Refactored from 51k+ token monolith into 5 maintainable modules
  • āœ… šŸ“Š JSON Configuration: Easy model priority updates via configuration files
  • āœ… šŸ¤– Always-Available Tools: Personality and default tools work with any provider setup
  • āœ… āš” Enhanced Performance: Optimized model selection and better error handling
  • āœ… šŸ”„ Future-Proof: Easy to add new models and update priorities

Previous Updates (v4.0)

  • āœ… 5 New Major AI Platforms: Replicate, AI21 Labs, Stability AI, Fireworks AI, Anyscale
  • āœ… 16 Total Platforms: Now supporting 16 different AI platforms and 800,000+ models
  • āœ… Advanced Reasoning: AI21 Labs' Jamba models with state-space architecture
  • āœ… Ultra-Fast Inference: Fireworks AI for blazing-fast open model serving

Previous Improvements (v3.0)

  • āœ… Major Bug Fixes: Fixed HuggingFace empty responses and Gemini blank chat issues
  • āœ… Enhanced HuggingFace: Completely rebuilt with advanced retry logic and better error handling
  • āœ… Improved Gemini: Smart conversation handling prevents blank responses in long chats
  • āœ… Web-Connected AI: Perplexity AI with real-time search capabilities
  • āœ… Enterprise Models: Cohere's command models for business use cases

šŸ¤ Contributing

Issues and pull requests welcome! This is an open-source project for the AI community.

ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“

šŸ§ āœØ Built for developers who want access to the entire AI ecosystem at their fingertips

GitHub stars GitHub forks GitHub watchers

ā­ Star us on GitHub ā€¢ šŸ“ Fork the project ā€¢ šŸ’– Contribute to the future of AI

ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“ā–“

Related Servers