広告掲載
MCP.so
ログイン

Deepseek Thinker MCP Server

@ruixingshi

リポジトリ

基本情報

カテゴリ

AI とエージェント

トランスポート

stdio

作者

ruixingshi

Deepseek Thinker MCP Server について

A MCP provider Deepseek reasoning content to MCP-enabled AI Clients, like Claude Desktop. Supports access to Deepseek's CoT from the Deepseek API service or a local Ollama server.

Deepseek Thinker MCP Server の設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "deepseek-thinker-mcp": {
      "command": "node",
      "args": [
        "build/index.js"
      ]
    }
  }
}

Deepseek Thinker MCP Server のツール

ツール一覧はまだありません

この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is Deepseek Thinker MCP Server?

Deepseek Thinker MCP Server is an MCP (Model Context Protocol) provider that delivers Deepseek reasoning content (including thought processes) to MCP-enabled AI clients, such as Claude Desktop. It supports access either through the Deepseek API service or via a local Ollama server.

How to use Deepseek Thinker MCP Server?

Install and run the server via npx -y deepseek-thinker-mcp or build locally with npm install && npm run build then run node build/index.js. Configure it in your client’s MCP settings, e.g., claude_desktop_config.json, setting environment variables for either OpenAI API mode (API_KEY, BASE_URL) or Ollama mode (USE_OLLAMA=true). Invoke the get-deepseek-thinker tool, providing an originPrompt string, to receive structured reasoning output.

Key features of Deepseek Thinker MCP Server

  • Dual mode support: OpenAI API and Ollama local
  • Captures Deepseek’s thinking process for reasoning output
  • Provides a single get-deepseek-thinker tool for reasoning queries
  • Built with TypeScript, @modelcontextprotocol/sdk, and Zod validation
  • Licensed under MIT

Use cases of Deepseek Thinker MCP Server

  • Integrating Deepseek reasoning directly into Claude Desktop conversations
  • Accessing Deepseek’s thought processes without sending data to the cloud (Ollama mode)
  • Adding reasoning capabilities to any MCP‑enabled AI assistant
  • Experimenting with Deepseek’s reasoning chain for analysis or debugging

よくある質問

1

I see “MCP error -32001: Request timed out”. What does that mean?

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

2

What modes does Deepseek Thinker MCP Server support?

It supports two modes: OpenAI API mode (requires API_KEY and BASE_URL) and Ollama local mode (set USE_OLLAMA=true).

3

How do I switch between modes?

Set the appropriate environment variables in your MCP server configuration. Use `API_KEY` and `BASE_URL` for OpenAI API mode, or set `USE_OLLAMA=true` for Ollama mode.

4

What are the runtime requirements?

Node.js and npm are needed to install dependencies and build the project. The server is a Node.js application built with TypeScript.

5

Where can I find the source and license?

The project is open source under the MIT License; the repository includes the full license file.

コメント

「AI とエージェント」の他のコンテンツ

Gamedev Tavern

Gamedev Tavern

Gamedev Tavern is MCP for the game industry: studios, people, games and open quests. Have a goal — your AI agent writes a quest in your words and Tavern agents look for people and studios that fit. No goal — your agent i

KissCode

NickSF189

KissCode is the world's first relationship network where AI agents and people meet. Connect your agent over MCP: it gets a profile, meets other agents and real people, chats, sends virtual gifts, goes on dinner and movie

OpenZiti MCP Gateway

openziti

NetFoundry MCP Gateway enables secure, isolated access to Model Context Protocol (MCP) tools across distributed systems without exposing public endpoints. Zero trust gateway for MCP servers. Aggregate, filter, and secure

48

TruVerifAI Panel-review

TruVerifAI

TruVerifAI's Panel Review is the guardian agent for AI's highest-stakes coding decisions: four frontier models argue over an AI coding agent's riskiest designs, diffs, and commits before they execute, with local review g

1

scvd.store

seancrecord

scvd.store is an evidence observatory for agentic commerce. Independent signed observation of what other people's endpoints, artifacts and payments actually did among other things. USDC on Base, Arbitrum One, World Chain

2
広告掲載