P

thoughtful-claude

...
Created 1/23/2025bymartinbowling

Language:

Python

Stars:

46

Forks:

5

πŸ€” Thoughtful Claude - DeepSeek R1 Reasoning Server

An MCP server that enhances Claude's reasoning capabilities by integrating DeepSeek R1's advanced reasoning engine. This server provides Claude with access to DeepSeek's state-of-the-art reasoning model, developed through large-scale reinforcement learning.

🌟 Features

  • Advanced Reasoning Integration

    • Leverages DeepSeek R1's reasoning engine
    • Seamlessly integrates with Claude's thought process
    • Handles complex multi-step reasoning tasks
  • Enterprise-Grade Security

    • Environment variable support (.env file)
    • Secure API key handling
    • No key exposure in responses
  • MCP Protocol Support

    • Full MCP server implementation
    • Streaming response handling
    • Proper error management
  • Modern Python Architecture

    • Async/await for efficient processing
    • Proper exception handling
    • Clean code organization

πŸ“¦ Installation

  1. Prerequisites

  2. Quick Start

# Clone repository
git clone https://github.com/martinbowling/thoughtful-claude.git
cd thoughtful-claude

# Install MCP and dependencies
pip install "mcp[cli]" httpx python-dotenv

# Create .env file with your API key
echo "DEEPSEEK_API_KEY=your_key_here" > .env

# Install the MCP server with environment variables
mcp install server.py -f .env

The mcp install command will:

  • Register the server with Claude Desktop
  • Set up the environment variables from .env
  • Configure the server to run with the correct Python interpreter

You can verify the installation by checking for the πŸ”¨ Tools icon in Claude Desktop's interface.

πŸš€ Usage

  1. Start the Server The server will automatically start when you use Claude Desktop with the proper configuration.

  2. Basic Workflow

    • Claude receives a query requiring reasoning

                - Query is sent to DeepSeek R1 for advanced reasoning
      
    • Reasoning is returned to Claude wrapped in `` tags

    • Claude incorporates the reasoning into its response

  3. Example Queries

    • Mathematical comparisons: "Is 9.9 greater than 9.11?"
    • Logic puzzles: "If all A are B, and some B are C, what can we conclude?"
    • Complex analysis: "Compare and contrast quantum computing with classical computing"

🧠 Technical Details

Reasoning Pipeline

  1. Query Processing

    • Accepts context and question in structured format
    • Combines inputs for comprehensive reasoning
  2. DeepSeek R1 Integration

    • Model: deepseek-reasoner
    • Stream: Enabled for real-time processing
    • Max Tokens: 1 (optimized for reasoning extraction)
    • Output: Structured reasoning content

Error Handling

  • API Errors

    • Graceful error wrapping in `` tags
    • Clear error messages for debugging
    • Proper exception propagation
  • Connection Issues

    • Timeout handling (30s default)
    • Automatic stream cleanup
    • Resource management

πŸ›  Troubleshooting

Common Issues

# Server not found in Claude Desktop
ERROR: MCP server not detected

# Solution
Check claude_desktop_config.json path and format

Performance Tips

  • Keep queries focused and specific
  • Provide relevant context when available
  • Use structured input format for complex queries

πŸ“„ License

MIT License - See LICENSE for details

πŸ™ Acknowledgments

  • DeepSeek R1 - For their groundbreaking work in reasoning capabilities
  • Claude - For the advanced AI assistant platform
  • MCP Protocol - For enabling seamless AI tool integration
Last updated: 2/26/2025

Publisher info

martinbowling's avatar

Martin Bowling

54
followers
16
following
138
repos

More MCP servers built with Python

composer-trade-mcp

Create, backtest, and execute trades directly in one chat box. The Composer MCP Server gives LLMs the power to backtest investment ideas and execute automated trading strategies. Trade across stocks, ETFs, and crypto directly in Claude.

By https://github.com/ronnyli
slidespeak-mcp

An MCP to generate presentations with AI. Create and edit PowerPoint presentations with AI.

By https://github.com/SlideSpeak
PaddleOCR

The PaddleOCR MCP server brings enterprise-grade OCR and document parsing capabilities to AI applications. Built on PaddleOCR β€” a proven solution with 50,000+ GitHub stars, deeply integrated by leading projects like MinerU, RAGFlow, and OmniParserβ€” with targeted optimizations based on the MCP concept.

By PaddlePaddle