MCP.so
ログイン

Gemini Thinking Mcp

@falahgs

リポジトリ

Gemini Thinking Mcp について

概要はまだありません

#mathgpt#math-solver#math-assistant

基本情報

カテゴリ

AI とエージェント

ライセンス

MIT

ランタイム

node

トランスポート

stdio

公開者

falahgs

投稿者

Falah Gatea

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": {
    "gemini-thinking": {
      "command": "node",
      "args": [
        "/path/to/gemini-thinking-mcp/build/index.js"
      ],
      "env": {
        "GEMINI_API_KEY": ""
      }
    }
  }
}

ツール

ツールは検出されませんでした

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 Gemini Thinking Mcp?

Gemini Thinking Mcp is a Model Context Protocol (MCP) server that integrates Google’s Gemini-2.0-flash-thinking-exp-01-21 model with Claude Desktop. It enables Claude users to leverage Gemini’s fast, high‑quality reasoning for tasks such as mathematical problem solving, logical deduction, and step‑by‑step analysis.

How to use Gemini Thinking Mcp?

Install Node.js v18+, clone the repository, run npm install, create a .env file with your GEMINI_API_KEY, build with npm run build, then add a gemini-thinking entry to Claude Desktop’s mcpServers configuration. In conversations, invoke the model with @gemini-thinking followed by your prompt.

Key features of Gemini Thinking Mcp

  • Exposes Gemini‑2.0‑flash‑thinking‑exp‑01‑21 to Claude Desktop
  • Optimized for fast, high‑quality reasoning
  • Supports mathematical reasoning and logical deduction
  • Enables step‑by‑step structured thinking
  • Configurable parameters: prompt, max_tokens, temperature
  • Local setup with a single API key

Use cases of Gemini Thinking Mcp

  • Solving mathematical equations step by step
  • Performing logical deduction and analytical tasks
  • Generating structured, reasoned explanations in Claude conversations

FAQ from Gemini Thinking Mcp

What are the prerequisites for using Gemini Thinking Mcp?

Node.js v18 or higher, npm, Claude Desktop, and a valid Google Gemini API key.

How do I configure Claude Desktop to use this server?

Add a JSON object to the mcpServers section of Claude Desktop’s config file, specifying the node command, the path to the built server (build/index.js), and the GEMINI_API_KEY environment variable.

What parameters can I adjust when calling Gemini Thinking Mcp?

You can set prompt (required), max_tokens (default 8192), and temperature (default 0.2) to control the model’s output.

コメント

「AI とエージェント」の他のコンテンツ

Shell and Coding agent for Claude and other mcp clients

rusiaaman

Shell and coding agent on mcp clients

666

Solon Ai

opensolon

Java AI application development framework (supports LLM-tool,skill; RAG; MCP; Agent-ReAct,Team-Agent). Compatible with java8 ~ java25. It can also be embedded in SpringBoot, jFinal, Vert.x, Quarkus, and other frameworks.

416

Gemini MCP Server

aliargun

MCP server implementation for Google's Gemini API

259

🛡️ A.I.G（AI-Infra-Guard）

Tencent

A full-stack AI Red Teaming platform securing AI ecosystems via OpenClaw Security Scan, Agent Scan, Skills Scan, MCP scan, AI Infra scan and LLM jailbreak evaluation.

4.1K

MCP Server - Remote MacOs Use

baryhuang

The only general AI agent that does NOT requires extra API key, giving you full control on your local and remote MacOs from Claude Desktop App

487