mcp-server-deepseek

@tizee

About mcp-server-deepseek

A MCP server provides access to DeepSeek-R1's reasoning capabilities for LLMs

#mcp-server #deepseek #reasoning #llm #api

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "mcp-server-deepseek-tizee": {
      "command": "python",
      "args": [
        "-m",
        "venv",
        "venv"
      ]
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is mcp-server-deepseek?

mcp-server-deepseek is a Model Context Protocol (MCP) server that provides access to DeepSeek-R1’s reasoning capabilities, allowing non-reasoning models to generate better responses with enhanced thinking. It acts as a bridge between LLM applications and DeepSeek’s reasoning model.

How to use mcp-server-deepseek?

Install with Python 3.13+ and a DeepSeek API key: clone the repo, create a virtual environment, run pip install -e ., and set environment variables in a .env file. Start the server with mcp-server-deepseek (or make dev for development mode). The server exposes a single tool think_with_deepseek_r1 that accepts a prompt string and returns DeepSeek-R1’s reasoning wrapped in <thinking> tags.

Key features of mcp-server-deepseek

Access to DeepSeek-R1’s reasoning model via API
Returns structured thinking in <thinking> format
Fully compatible with the Model Context Protocol
Robust error handling with detailed logging
Simple setup with environment variable configuration

Use cases of mcp-server-deepseek

Enhancing responses from models without native reasoning capabilities
Accessing DeepSeek-R1’s thinking process for complex problem solving
Adding structured reasoning to Claude or other MCP-supporting LLMs
Offloading deep reasoning to a specialized model while keeping a main assistant

FAQ from mcp-server-deepseek

How do I install and configure mcp-server-deepseek?

Clone the repository, create a Python 3.13+ virtual environment, install with pip install -e ., copy .env.example to .env, and set your DeepSeek API key, model name, and API base URL (default https://api.deepseek.com).

What tool does the server expose?

It exposes a single tool think_with_deepseek_r1 that takes a prompt (string) and returns DeepSeek-R1’s reasoning content enclosed in <thinking> tags.

What are common issues and how do I resolve them?

Common issues include an incorrect DeepSeek API key (check your .env file), timeout errors on complex prompts (try simplifying the prompt), and missing reasoning content (try rephrasing the query). Detailed error logs are stored at ~/.cache/mcp-server-deepseek/server.log and the log level can be set via the LOG_LEVEL environment variable.

Frequently asked questions

How do I install and configure mcp-server-deepseek?

Clone the repository, create a Python 3.13+ virtual environment, install with `pip install -e .`, copy `.env.example` to `.env`, and set your DeepSeek API key, model name, and API base URL (default `https://api.deepseek.com`).

What tool does the server expose?

It exposes a single tool `think_with_deepseek_r1` that takes a `prompt` (string) and returns DeepSeek-R1’s reasoning content enclosed in `<thinking>` tags.

What are common issues and how do I resolve them?

Common issues include an incorrect DeepSeek API key (check your `.env` file), timeout errors on complex prompts (try simplifying the prompt), and missing reasoning content (try rephrasing the query). Detailed error logs are stored at `~/.cache/mcp-server-deepseek/server.log` and the log level can be set via the `LOG_LEVEL` environment variable.