Deepseek R1 MCP Server

What does “Deepseek R1” MCP Server do?

The Deepseek R1 MCP Server is a Model Context Protocol (MCP) server implementation designed to connect Claude Desktop with DeepSeek’s advanced language models, such as Deepseek R1 and DeepSeek V3. By acting as a bridge between AI assistants and DeepSeek’s powerful reasoning-optimized models (featuring an 8192-token context window), this server enables AI agents to perform enhanced natural language understanding and generation tasks. Developers can leverage the Deepseek R1 MCP Server to integrate these models seamlessly into their workflows, facilitating advanced text generation, reasoning, and interaction with external data sources or APIs within supported platforms. The implementation focuses on providing stable, reliable, and efficient integration using Node.js/TypeScript for optimal compatibility and type safety.

List of Prompts

No prompt templates are documented in the repository.

Ready to grow your business?

Start your free trial today and see results within days.

Request demo Log in

List of Resources

No explicit MCP resources are documented in the repository.

List of Tools

• Advanced text generation tool
  • Enables LLMs to generate text using Deepseek R1 (or V3), leveraging the model’s large context window and reasoning abilities.

Join our newsletter

Get latest tips, trends, and deals for free.

Email address

Subscribe

Use Cases of this MCP Server

• Advanced Text Generation
  Benefit from DeepSeek R1’s large context window (8192 tokens) to compose lengthy and complex outputs for documentation, storytelling, or technical writing.
• Enhanced Reasoning Tasks
  Use the Deepseek R1 model’s optimized capabilities for logic-heavy or multi-step reasoning, ideal for problem-solving and analysis tasks.
• Seamless Claude Desktop Integration
  Integrate state-of-the-art language models directly into Claude Desktop environments, enhancing the AI assistant’s capabilities for everyday workflows.
• Flexible Model Selection
  Switch between Deepseek R1 and DeepSeek V3 models by altering configuration, adapting to various project requirements.
• API-Based Automation
  Enable AI-driven automation in environments where DeepSeek’s API is available, streamlining content creation or knowledge base management.

How to set it up

Windsurf

1. Ensure Node.js (v18+) and npm are installed.
2. Clone the repository and install dependencies:

   git clone https://github.com/66julienmartin/MCP-server-Deepseek_R1.git
   cd deepseek-r1-mcp
   npm install
   

3. Copy .env.exemple to .env and set your DeepSeek API key.
4. Edit Windsurf’s configuration to add the MCP server:

   {
     "mcpServers": {
       "deepseek_r1": {
         "command": "node",
         "args": ["/path/to/deepseek-r1-mcp/build/index.js"],
         "env": {
           "DEEPSEEK_API_KEY": "your-api-key"
         }
       }
     }
   }
   

5. Save, restart Windsurf, and verify the server is running.

Claude

1. Install Node.js (v18+) and npm.
2. Clone and set up the Deepseek R1 MCP Server as above.
3. In Claude’s configuration, add:

   {
     "mcpServers": {
       "deepseek_r1": {
         "command": "node",
         "args": ["/path/to/deepseek-r1-mcp/build/index.js"],
         "env": {
           "DEEPSEEK_API_KEY": "your-api-key"
         }
       }
     }
   }
   

4. Restart Claude and verify MCP server availability.

Cursor

1. Install prerequisites (Node.js, npm).
2. Set up the server and environment variables.
3. Add the server to Cursor’s config:

   {
     "mcpServers": {
       "deepseek_r1": {
         "command": "node",
         "args": ["/path/to/deepseek-r1-mcp/build/index.js"],
         "env": {
           "DEEPSEEK_API_KEY": "your-api-key"
         }
       }
     }
   }
   

4. Save, restart Cursor, and test the server integration.

Cline

1. Ensure Node.js and npm are installed.
2. Clone and build the Deepseek R1 MCP Server.
3. Add the server to Cline’s configuration:

   {
     "mcpServers": {
       "deepseek_r1": {
         "command": "node",
         "args": ["/path/to/deepseek-r1-mcp/build/index.js"],
         "env": {
           "DEEPSEEK_API_KEY": "your-api-key"
         }
       }
     }
   }
   

4. Restart Cline and confirm the MCP server is connected.

Securing API Keys

Use environment variables in your configuration to keep API keys secure:

{
  "mcpServers": {
    "deepseek_r1": {
      "command": "node",
      "args": ["/path/to/deepseek-r1-mcp/build/index.js"],
      "env": {
        "DEEPSEEK_API_KEY": "your-api-key"
      }
    }
  }
}

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "deepseek_r1": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change “deepseek_r1” to whatever the actual name of your MCP server is and replace the URL with your own MCP server URL.

Overview

| Supports Roots | ⛔ | Not documented |

Based on the available documentation, the Deepseek R1 MCP Server provides a clean, focused implementation that is easy to configure and use, but lacks documentation for prompts, resources, or advanced MCP features like roots and sampling. This makes it highly practical for text generation, but less feature-rich for complex workflows.

MCP Score