DeepSeek MCP Server

1

Add it to Claude Code

Run this in a terminal.

Run in terminal
claude mcp add --transport http -H "Authorization: Bearer ${DEEPSEEK_API_KEY}" deepseek-mcp-server https://deepseek-mcp.tahirl.com/mcp
Required:DEEPSEEK_API_KEY+ 2 optional
README.md

MCP server for DeepSeek AI with chat, reasoning, and function calling.

DeepSeek MCP Server

MCP server for DeepSeek AI with chat, reasoning, multi-turn sessions, function calling, thinking mode, and cost tracking.

Compatible with Claude Code, Gemini CLI, Cursor, Windsurf, and any MCP-compatible client. Officially listed on the MCP Registry, Smithery, Glama, and LobeHub.

Quick Start

Remote (No Install)

Use the hosted endpoint directly — no npm install, no Node.js required. Bring your own DeepSeek API key:

Claude Code:

claude mcp add --transport http deepseek \
  https://deepseek-mcp.tahirl.com/mcp \
  --header "Authorization: Bearer YOUR_DEEPSEEK_API_KEY"

Cursor / Windsurf / VS Code:

{
  "mcpServers": {
    "deepseek": {
      "url": "https://deepseek-mcp.tahirl.com/mcp",
      "headers": {
        "Authorization": "Bearer ${DEEPSEEK_API_KEY}"
      }
    }
  }
}

Local (stdio)

Claude Code:

claude mcp add -s user deepseek npx @arikusi/deepseek-mcp-server -e DEEPSEEK_API_KEY=your-key-here

Gemini CLI:

gemini mcp add deepseek npx @arikusi/deepseek-mcp-server -e DEEPSEEK_API_KEY=your-key-here

Scope options (Claude Code):

  • -s user: Available in all your projects (recommended)
  • -s local: Only in current project (default)
  • -s project: Project-specific .mcp.json file

Get your API key: https://platform.deepseek.com


Features

  • DeepSeek V3.2: Both models now run DeepSeek-V3.2 (since Sept 2025)
  • Multi-Turn Sessions: Conversation context preserved across requests via session_id parameter
  • Model Fallback & Circuit Breaker: Automatic fallback between models with circuit breaker protection against cascading failures
  • MCP Resources: deepseek://models, deepseek://config, deepseek://usage — query model info, config, and usage stats
  • Thinking Mode: Enable thinking on deepseek-chat with thinking: {type: "enabled"}
  • JSON Output Mode: Structured JSON responses with json_mode: true
  • Function Calling: OpenAI-compatible tool use with up to 128 tool definitions
  • Cache-Aware Cost Tracking: Automatic cost calculation with cache hit/miss breakdown
  • Session Management Tool: List, delete, and clear sessions via deepseek_sessions tool
  • Configurable: Environment-based configuration with validation
  • 12 Prompt Templates: Templates for debugging, code review, function calling, and more
  • Streaming Support: Real-time response generation
  • Multimodal Ready: Content part types for text + image input (enable with ENABLE_MULTIMODAL=true)
  • Remote Endpoint: Hosted at deepseek-mcp.tahirl.com/mcp — BYOK (Bring Your Own Key), no install needed
  • HTTP Transport: Self-hosted remote access via Streamable HTTP with TRANSPORT=http
  • Docker Ready: Multi-stage Dockerfi

Tools (1)

deepseek_sessionsManage conversation sessions including listing, deleting, and clearing history.

Environment Variables

DEEPSEEK_API_KEYrequiredAPI key for authenticating with DeepSeek services
ENABLE_MULTIMODALEnable support for image input processing
TRANSPORTSet to http for self-hosted remote access

Configuration

claude_desktop_config.json
{"mcpServers": {"deepseek": {"url": "https://deepseek-mcp.tahirl.com/mcp", "headers": {"Authorization": "Bearer ${DEEPSEEK_API_KEY}"}}}}

Try it

Use DeepSeek to analyze this code snippet and suggest optimizations.
Start a new reasoning session with DeepSeek to solve this complex logic problem.
List my current DeepSeek conversation sessions and clear the old ones.
Enable thinking mode and explain the step-by-step reasoning for this query.

Frequently Asked Questions

What are the key features of DeepSeek MCP Server?

Support for DeepSeek-V3.2 models with reasoning capabilities. Multi-turn session management with context preservation. Automatic model fallback and circuit breaker protection. Built-in cost tracking with cache hit/miss breakdown. Structured JSON output mode and multimodal input support.

What can I use DeepSeek MCP Server for?

Integrating DeepSeek's reasoning models into Claude Desktop for complex problem solving. Managing long-running AI conversations across multiple sessions. Monitoring API usage and costs directly within the MCP client. Utilizing function calling capabilities for automated task execution.

How do I install DeepSeek MCP Server?

Install DeepSeek MCP Server by running: claude mcp add --transport http deepseek https://deepseek-mcp.tahirl.com/mcp --header "Authorization: Bearer YOUR_DEEPSEEK_API_KEY"

What MCP clients work with DeepSeek MCP Server?

DeepSeek MCP Server works with any MCP-compatible client including Claude Desktop, Claude Code, Cursor, and other editors with MCP support.

Turn this server into reusable context

Keep DeepSeek MCP Server docs, env vars, and workflow notes in Conare so your agent carries them across sessions.

Need the old visual installer? Open Conare IDE.
Open Conare