Gemini Context MCP Server

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

FAQ from Gemini Context MCP Server

What are the runtime requirements?

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

How do I get a Gemini API key?

Obtain one from ai.google.dev.

Which MCP clients are supported?

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

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.

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.