Deepseek R1 Reasoner MCP server

Leverages Deepseek r1 for local reasoning and task planning, enabling autonomous decision-making while maintaining data privacy.
Back to servers
Setup instructions
Provider
Michael Neale
Release date
Feb 03, 2025
Language
TypeScript
Package
Stats
322 downloads
2 stars

This MCP server provides a local technical agent system by leveraging Deepseek r1 as a reasoning model that can be combined with tool-calling models. This approach allows you to run capable AI agents entirely on your local machine without depending on remote models.

Installation

To use the Deepseek Reasoner MCP server, you need to have Node.js installed on your system. The server can be easily run using npx without requiring a separate installation step:

npx -y deepseek-reasoner-mcp

This command will automatically download and run the MCP server.

Prerequisites

Before running the server, ensure you have Ollama installed and running on your system. Ollama is used to serve the local models that the MCP server will work with.

Usage

The Deepseek Reasoner MCP server follows the Model Context Protocol, making it compatible with various agent systems. It acts as a bridge between your agent system and the local models being served by Ollama.

Basic Usage

To start the server, simply run:

npx -y deepseek-reasoner-mcp

Once running, the server will be available for your agent system to connect to.

Integration with Agent Systems

This MCP server can be integrated with any agent system that supports the Model Context Protocol. A common usage is to pair it with systems like "Project Goose" where:

  1. Deepseek r1 handles complex reasoning tasks
  2. A separate tool-calling model handles interactions with external tools
  3. All processing happens locally on your machine

Architecture Overview

In a typical setup:

  • Deepseek r1 model provides advanced reasoning capabilities
  • Tool-calling models handle specific interactions with external systems
  • The MCP server coordinates between these components

This architecture allows you to create powerful AI agents that run entirely on your local system without requiring connection to cloud-based models.

Troubleshooting

If you encounter issues with the server:

  • Ensure Ollama is running properly
  • Check that you have the required models downloaded in Ollama
  • Verify that your agent system is correctly configured to use the MCP server

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "deepseek-reasoner-mcp" '{"command":"npx","args":["-y","deepseek-reasoner-mcp"]}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "deepseek-reasoner-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "deepseek-reasoner-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json
  • Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "deepseek-reasoner-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "deepseek-reasoner-mcp"
            ]
        }
    }
}

3. Restart Claude Desktop for the changes to take effect

Want to 10x your AI skills?

Get a free account and learn to code + market your apps using AI (with or without vibes!).

Nah, maybe later