Deepseek-Thinking-Claude-3.5-Sonnet-CLINE-MCP
@newideas99
About Deepseek-Thinking-Claude-3.5-Sonnet-CLINE-MCP
🧠MCP server implementing RAT (Retrieval Augmented Thinking) - combines DeepSeek's reasoning with GPT-4/Claude/Mistral responses, maintaining conversation context between interactions.
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"Deepseek-Thinking-Claude-3.5-Sonnet-CLINE-MCP": {
"command": "npx",
"args": [
"-y",
"@smithery/cli",
"install",
"@newideas99/Deepseek-Thinking-Claude-3.5-Sonnet-CLINE-MCP",
"--client",
"claude"
]
}
}
}Tools
No tools detected
Fetch the live tool list by running this server in a temporary sandbox using the button above.
Overview
What is Deepseek-Thinking-Claude-3.5-Sonnet-CLINE-MCP?
A Model Context Protocol (MCP) server that combines DeepSeek R1's reasoning capabilities with Claude 3.5 Sonnet's response generation through OpenRouter's unified API. It uses a two-stage process where DeepSeek provides structured reasoning which is then incorporated into Claude's response generation. Designed for users of Cline (Claude Dev) who want enhanced reasoning for complex tasks.
How to use Deepseek-Thinking-Claude-3.5-Sonnet-CLINE-MCP?
Install via Smithery or manually, clone the repository, install dependencies, and set your OpenRouter API key in a .env file. Build the server and add it to your Cline MCP settings. Two tools are available: generate_response (sends a prompt with optional reasoning display) and check_response_status (polls for task completion, which may take up to 60 seconds).
Key features of Deepseek-Thinking-Claude-3.5-Sonnet-CLINE-MCP
- Two-stage processing: DeepSeek R1 reasoning then Claude 3.5 Sonnet response.
- Smart conversation management: detects active conversations and handles multiple.
- Model-specific context limits (50k for DeepSeek, 600k for Claude).
- Polling mechanism for long-running requests (up to 60 seconds).
- Configurable environment variables for model selection.
Use cases of Deepseek-Thinking-Claude-3.5-Sonnet-CLINE-MCP
- Enhancing AI responses with structured reasoning for complex questions.
- Coding tasks requiring deep analysis followed by clear explanations.
- Multi-turn conversations with context retention and reasoning visibility.
- Problem-solving where reasoning steps should be inspectable.
FAQ from Deepseek-Thinking-Claude-3.5-Sonnet-CLINE-MCP
What is the two-stage processing?
DeepSeek R1 first generates reasoning tokens, then Claude 3.5 Sonnet uses those as context to produce the final response.
Do I need an OpenRouter API key?
Yes, both models are accessed through OpenRouter's unified API. Set OPENROUTER_API_KEY in your .env file.
What are the context limits?
DeepSeek uses 50,000 characters for focused reasoning; Claude uses 600,000 characters for comprehensive responses.
How do I check the status of a response?
Use the check_response_status tool with the taskId returned by generate_response. Poll until the status is "complete".
Can I see the reasoning process?
Yes, set showReasoning to true in generate_response to include DeepSeek's reasoning in the output.
Frequently asked questions
What is the two-stage processing?
DeepSeek R1 first generates reasoning tokens, then Claude 3.5 Sonnet uses those as context to produce the final response.
Do I need an OpenRouter API key?
Yes, both models are accessed through OpenRouter's unified API. Set `OPENROUTER_API_KEY` in your `.env` file.
What are the context limits?
DeepSeek uses 50,000 characters for focused reasoning; Claude uses 600,000 characters for comprehensive responses.
How do I check the status of a response?
Use the `check_response_status` tool with the `taskId` returned by `generate_response`. Poll until the status is "complete".
Can I see the reasoning process?
Yes, set `showReasoning` to `true` in `generate_response` to include DeepSeek's reasoning in the output.
Basic information
More AI & Agents MCP servers
fhirHydrant
faulkjOpen-source Node.js FHIR MCP server with SMART Backend Services, metadata-aware search/CRUD tools, compact responses, FHIRPath filtering, safe pagination, audit events, and terminology lookup.
Hypnothera
La-SalidaAgent skill: turn what your AI assistant knows about you into a personalized hypnosis session on hypnothera.ai
🔎 GPT Researcher
assafelovicAn autonomous agent that conducts deep research on any data using any LLM providers
Nero AI Image Processing
nero-comWe provide AI-powered tools for image enhancement, upscaling, background removal, photo restoration, colorization, denoising, and compression. All features are available through our API documentation.
Transform MCP
UnstructuredThe Unstructured Transform MCP Server connects your ADK agent to Unstructured, a document processing platform that turns raw files into structured, AI-ready data. This integration gives your agent the ability to parse PD
Comments