LABSCO SUMMARY

A second model is one call away, and you decide how long and how adventurous its answer is.

The tool takes a prompt rather than a message array, so it suits a self-contained question — a proof, a translation, a rewrite — more than a continuing conversation. temperature and max_tokens are the two levers, and they are per call, which makes it practical to ask the same question twice under different settings and compare.

What it is

A single-tool bridge to the DeepSeek R1 model. deepseek_r1 takes a prompt, a temperature and a max_tokens, and returns generated text.

What you get

Text generated by DeepSeek R1 from a prompt you pass
Per-call control of randomness through temperature and of length through max_tokens

Requirements

A DeepSeek account with an API key in DEEPSEEK_API_KEY, and Node on your PATH.

Setup effort

Build from source — git clone https://github.com/66julienmartin/MCP-server-Deepseek_R1.git

See installation options

USE CASES

01

Getting a second model's read on a self-contained problem

A prompt goes across and generated text comes back, which suits a proof, a translation or a rewrite where the whole question fits in one message.

deepseek_r1

02

Comparing the same question at two temperatures

temperature and max_tokens are per-call, so the same prompt can be run twice under different settings and the two answers put side by side.

deepseek_r1

1 tool

Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.

`deepseek_r1`

Generate text using DeepSeek R1 model

BEFORE YOU INSTALL

What to know first

Tools you get

1 tool when we connected.

Requires

Node.js
DEEPSEEK_API_KEY in your environment

Where it runs

The documented client runs the server on your machine.

CONTEXT COST

Light Standing cost

Rated by the size of the one tool definition that rides along on every turn

INSTALLATION

Connect your client

You clone and build this one yourself.

Server setup

TERMINAL

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

# Set up environment
cp .env.example .env  # Then add your API key

# Build and run
npm run build

The clone above creates a directory named MCP-server-Deepseek_R1, and the next line enters deepseek-r1-mcp. Change into MCP-server-Deepseek_R1 instead, or the build steps run in the wrong place.

MCP Clients

Claude Desktop

CLAUDE DESKTOP · JSON

{
  "mcpServers": {
    "deepseek_r1": {
      "command": "node",
      "args": [
        "<YOUR_PATH_TO_DEEPSEEK_R1_MCP>/build/index.js"
      ],
      "env": {
        "DEEPSEEK_API_KEY": "<YOUR_DEEPSEEK_API_KEY>"
      }
    }
  }
}

Deepseek R1