广告合作
MCP.so
登录

DeepSeek-Claude MCP Server

@HarshJ23

代码仓库

基本信息

分类

AI 与智能体

传输方式

stdio

作者

HarshJ23

关于 DeepSeek-Claude MCP Server

a MCP server which integrates reasoning capabilities of DeepSeek R1 model into claude desktop app.

#deepseek#claude#mcp-server

DeepSeek-Claude MCP Server 配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "deepseek-claude-MCP-server": {
      "command": "npx",
      "args": [
        "-y",
        "@smithery/cli",
        "install",
        "@HarshJ23/deepseek-claude-MCP-server",
        "--client",
        "claude"
      ]
    }
  }
}

DeepSeek-Claude MCP Server 工具

工具列表暂未提供

当前收录暂时没有可展示的工具列表，不代表服务没有工具。请查阅项目文档了解支持的能力。

点击上方按钮,在临时沙箱中运行此服务器并实时获取工具列表。

概览

What is DeepSeek-Claude MCP Server?

DeepSeek-Claude MCP Server enhances Claude's reasoning capabilities by integrating DeepSeek R1's advanced reasoning engine. It enables Claude to tackle complex, multi-step reasoning tasks by forwarding queries to DeepSeek R1 and incorporating its structured reasoning into Claude's responses. The server is designed for users who need precision and efficiency in thoughtful response generation.

How to use DeepSeek-Claude MCP Server?

Install via Smithery with npx -y @smithery/cli install @HarshJ23/deepseek-claude-MCP-server --client claude or manually by cloning the repository, setting up a Python 3.12+ environment with uv, installing dependencies (mcp[cli] and httpx), obtaining a DeepSeek API key, and configuring the claude_desktop_config.json file. The server runs automatically when used with Claude Desktop. When Claude receives a complex query, it forwards it to DeepSeek R1, which returns structured reasoning inside <ant_thinking> tags, and Claude integrates that reasoning into its final response.

Key features of DeepSeek-Claude MCP Server

  • Integrates DeepSeek R1 reasoning with Claude.
  • Supports intricate multi-step reasoning tasks.
  • Designed for precision and efficiency in responses.
  • Works automatically with Claude Desktop via MCP.

Use cases of DeepSeek-Claude MCP Server

  • Solving complex logic or math problems with step-by-step reasoning.
  • Handling multi-step analysis where deeper inference is needed.
  • Generating structured, thought-out answers for research or analysis tasks.

常见问题

1

What is DeepSeek-Claude MCP Server?

It is an MCP server that lets Claude leverage DeepSeek R1's reasoning engine for advanced, multi-step reasoning tasks.

2

What are the prerequisites for using DeepSeek-Claude MCP Server?

Python 3.12 or higher, the `uv` package manager, and a DeepSeek API key (obtainable from platform.deepseek.com).

3

How do I set up DeepSeek-Claude MCP Server?

Clone the repo, create a virtual environment with `uv`, install dependencies, configure your DeepSeek API key, add the server configuration to `claude_desktop_config.json`, then run `uv run server.py`. Restart Claude Desktop to use it.

4

How does the integration between Claude and DeepSeek R1 work?

Claude forwards a query to DeepSeek R1, which returns structured reasoning wrapped in `<ant_thinking>` tags. Claude then incorporates that reasoning into its final response.

5

Does DeepSeek-Claude MCP Server require any external transport or authentication?

The server communicates via the MCP protocol with Claude Desktop. Authentication is handled by your DeepSeek API key, set during configuration.

评论

AI 与智能体 分类下的更多 MCP 服务器

Transform MCP

Unstructured

The Unstructured Transform MCP Server connects your ADK agent to Unstructured, a document processing platform that turns raw files into structured, AI-ready data. This integration gives your agent the ability to parse PD

Melaya

Melaya Labs

**Melaya gives an AI assistant hands.** It is a remote MCP server, so there is nothing to install and no API key to configure — one URL works in Claude, ChatGPT, Le Chat, Cursor and any MCP client. ### Your Android phon

YouSpot MCP

YouSpot

Give an agent access to your YouSpot CRM: contacts, companies, notes, files, and your connected Gmail, Calendar, HubSpot, LinkedIn, Slack and X.

treg.to

Jason Zhou

OpenRouter for tools & data — 3,028 APIs for your agent, one token, pay per call. treg.to is a remote MCP server at https://treg.to/mcp/ that gives an agent 3,028 ready-to-call API endpoints across 82 platforms: SEO and

L

Legion MCP

faulkj

MCP-native LLM councils for debates, juries, blind panels, voting, refinement, and custom multi-model deliberation.

1
广告合作