MCP

Access Deepseek Reasoning via API or Ollama

MCP server that exposes Deepseek's reasoning process and thought chains to Claude Desktop and other MCP clients via OpenAI API or local Ollama.

Works with ollamaopenai
⚠️ This tool looks unmaintained — no upstream commits in 12+ months.

19
Spark score
out of 100
Updated Mar 2025
Version 1.0.0
Models

Add to Favorites

Why it matters

Integrate Deepseek's advanced reasoning and thinking capabilities into your applications. This connector supports both OpenAI API and local Ollama server modes for flexible deployment.

Outcomes

What it gets done

01

Connect to Deepseek's reasoning engine using OpenAI API.

02

Integrate with local Ollama server for Deepseek model access.

03

Capture and utilize structured reasoning processes from Deepseek.

04

Enable focused reasoning tasks within your existing workflows.

Install

Add it to your toolbox

Run in your project directory:

curl -fsSL https://spark.entire.vc/get/vb-deepseek-thinker-mcp | bash

Capabilities

Tools your agent gets

get-deepseek-thinker

Performs reasoning using the Deepseek model with structured text response containing the reasoning process.

Overview

deepseek-thinker-mcp server

What it does

An MCP server that captures and exposes Deepseek model reasoning processes to MCP-enabled AI clients through either OpenAI API or local Ollama integration.

How it connects

Use when you need to inspect Deepseek's step-by-step thinking and reasoning chains within Claude Desktop or other MCP clients, either via cloud API or local deployment.

Source README

Deepseek Thinker MCP Server

smithery badge

A MCP (Model Context Protocol) provider Deepseek reasoning content to MCP-enabled AI Clients, like Claude Desktop. Supports access to Deepseek's thought processes from the Deepseek API service or from a local Ollama server.

Deepseek Thinker Server MCP server

Core Features

  • 🤖 Dual Mode Support

    • OpenAI API mode support
    • Ollama local mode support
  • 🎯 Focused Reasoning

    • Captures Deepseek's thinking process
    • Provides reasoning output

Available Tools

get-deepseek-thinker

  • Description: Perform reasoning using the Deepseek model
  • Input Parameters:
    • originPrompt (string): User's original prompt
  • Returns: Structured text response containing the reasoning process

Environment Configuration

OpenAI API Mode

Set the following environment variables:

API_KEY=<Your OpenAI API Key>
BASE_URL=<API Base URL>

Ollama Mode

Set the following environment variable:

USE_OLLAMA=true

Usage

Integration with AI Client, like Claude Desktop

Add the following configuration to your claude_desktop_config.json:

{
  "mcpServers": {
    "deepseek-thinker": {
      "command": "npx",
      "args": [
        "-y",
        "deepseek-thinker-mcp"
      ],
      "env": {
        "API_KEY": "<Your API Key>",
        "BASE_URL": "<Your Base URL>"
      }
    }
  }
}

Using Ollama Mode

{
  "mcpServers": {
    "deepseek-thinker": {
      "command": "npx",
      "args": [
        "-y",
        "deepseek-thinker-mcp"
      ],
      "env": {
        "USE_OLLAMA": "true"
      }
    }
  }
}

Local Server Configuration

{
  "mcpServers": {
    "deepseek-thinker": {
      "command": "node",
      "args": [
        "/your-path/deepseek-thinker-mcp/build/index.js"
      ],
      "env": {
        "API_KEY": "<Your API Key>",
        "BASE_URL": "<Your Base URL>"
      }
    }
  }
}

Development Setup

# Install dependencies
npm install

# Build project
npm run build

# Run service
node build/index.js

FAQ

Response like this: "MCP error -32001: Request timed out"

This error occurs when the Deepseek API response is too slow or when the reasoning content output is too long, causing the MCP server to timeout.

Tech Stack

  • TypeScript
  • @modelcontextprotocol/sdk
  • OpenAI API
  • Ollama
  • Zod (parameter validation)

Discussion

Questions & comments · 0

Sign In Sign in to leave a comment.