広告掲載
MCP.so
ログイン

Gemini Context MCP Server

@ogoldberg

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

ogoldberg

Gemini Context MCP Server について

MCP server for Cursor that leverages Gemini's much larger context window to enhance the capabilities of the AI tools

Gemini Context 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": {
    "gemini-context-mcp-server": {
      "command": "node",
      "args": [
        "dist/mcp-server.js"
      ]
    }
  }
}

Gemini Context 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 Gemini Context MCP Server?

Gemini Context MCP Server is an MCP (Model Context Protocol) server that uses Gemini’s capabilities for context management and caching, supporting up to a 2M token context window. It enables session-based conversations, semantic search, and efficient reuse of large prompts to reduce costs.

How to use Gemini Context MCP Server?

Requires Node.js 18+, a Gemini API key, and cloning the repository. Install dependencies (npm install), copy .env.example to .env and add your key, then build (npm run build) and start (node dist/mcp-server.js). Quick client setup commands are available for Claude Desktop, Cursor, and VS Code (e.g., npm run install:claude). For custom usage, instantiate GeminiContextServer with optional configuration.

Key features of Gemini Context MCP Server

  • Up to 2M token context window support
  • Session-based conversations with state tracking
  • Semantic search for relevant context
  • Automatic context and cache expiration
  • Large prompt caching for cost optimization
  • TTL management for cached contexts

Use cases of Gemini Context MCP Server

  • Maintain conversational context across multiple interactions in a session
  • Improve response quality by reusing large system prompts via caching
  • Reduce API token costs by caching frequently used contexts
  • Find relevant past context using semantic similarity

よくある質問

1

What are the runtime requirements?

Node.js 18+ and a Gemini API key are required.

2

How do I get a Gemini API key?

Obtain one from [ai.google.dev](https://ai.google.dev).

3

Which MCP clients are supported?

It works with Claude Desktop, Cursor, and VS Code via MCP-compatible extensions.

4

What MCP tools are available?

Context tools include `generate_text`, `get_context`, `clear_context`, `add_context`, and `search_context`. Caching tools include `create_cache`, `generate_with_cache`, `list_caches`, `update_cache_ttl`, and `delete_cache`.

5

How is context stored and does it persist?

Context and caches are held in memory with automatic expiration; database persistence is a planned future improvement.

コメント

「AI とエージェント」の他のコンテンツ

Fotor MCP

fotor

Bring ideas to life with Fotor MCP: generate and edit images, enhance product photos, and create videos, voiceovers, and music.

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
早

早起鸟儿喊真人验真

shenshaoyin

早起鸟儿喊真人验真 is a remote MCP server available at http://121.40.18.232.

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

広告掲載