MCP.so
Sign In

Gemini MCP Server Enhanced v2.5

@ivangrynenko

Repository

About Gemini MCP Server Enhanced v2.5

Enhanced MCP server for Google Gemini 2.5 Pro Preview with 16 powerful tools. Compatible with Claude Desktop.

#mcp#gemini#google-gemini#claude-desktop

Config

No standard config provided

This server doesn't expose a parseable MCP config block in its README. See the repository for install instructions.

Repository

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is Gemini MCP Server Enhanced v2.5?

Gemini MCP Server Enhanced v2.5 is a Model Context Protocol (MCP) server that provides comprehensive access to Google's Gemini 2.5 Pro Preview AI capabilities. It enables text generation, image analysis, code generation, chat conversations, content creation, and safety moderation through Claude Desktop or custom WebSocket integrations.

How to use Gemini MCP Server Enhanced v2.5?

Clone the repository, install dependencies with npm install, build with npm run build, obtain a Gemini API key from Google AI Studio, configure Claude Desktop (in claude_desktop_config.json with the GEMINI_API_KEY environment variable pointing to dist/stdio.js), and restart Claude Desktop. Then use the provided tools (e.g., generate_text, analyze_image) in your conversations.

Key features of Gemini MCP Server Enhanced v2.5

  • Full MCP protocol support with stdio transport for Claude Desktop
  • WebSocket support for custom integrations
  • Real-time response streaming
  • Secure API key handling via environment variables
  • Tools for text generation, image analysis, and code generation
  • Chat conversations with context memory and session management
  • Content creation and safety/moderation capabilities

Use cases of Gemini MCP Server Enhanced v2.5

  • Generate creative text with customizable temperature and token limits
  • Analyze images, extract text (OCR), and compare multiple images
  • Generate, explain, refactor, and convert code between programming languages
  • Conduct chat conversations with session management and summarization
  • Translate, summarize, rewrite text, and generate structured data (JSON, YAML, CSV, XML, TOML)

FAQ from Gemini MCP Server Enhanced v2.5

What runtime does it require?

Node.js and npm are required. The project is a TypeScript implementation with ES modules.

How do I get a Gemini API key?

Visit Google AI Studio (makersuite.google.com/app/apikey) and create a new API key.

Where are API keys stored?

API keys are handled exclusively via the GEMINI_API_KEY environment variable in the Claude Desktop configuration. No sensitive data is logged or stored by the server.

What are the context window limits?

The current model supports a 1M token context window, with a 2M token window coming soon.

What transports are available?

The server supports stdio transport for Claude Desktop and WebSocket transport for custom integrations.

Frequently asked questions

What runtime does it require?

Node.js and npm are required. The project is a TypeScript implementation with ES modules.

How do I get a Gemini API key?

Visit Google AI Studio (makersuite.google.com/app/apikey) and create a new API key.

Where are API keys stored?

API keys are handled exclusively via the `GEMINI_API_KEY` environment variable in the Claude Desktop configuration. No sensitive data is logged or stored by the server.

What are the context window limits?

The current model supports a 1M token context window, with a 2M token window coming soon.

What transports are available?

The server supports stdio transport for Claude Desktop and WebSocket transport for custom integrations.

Comments

Basic information

Category

AI & Agents

License

MIT license

Transports

stdio

Author

ivangrynenko

More AI & Agents MCP servers

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

Sequential Thinking Multi-Agent System (MAS)

FradSer

An advanced sequential thinking process using a Multi-Agent System (MAS) built with the Agno framework and served via MCP.

306

21st.dev Magic AI Agent

21st-dev

It's like v0 but in your Cursor/WindSurf/Cline. 21st dev Magic MCP server for working with your frontend like Magic

5.3K

bsv.cx

Andy Rowe

Timestamp and verify evidence on-chain. Let your agent prove what it saw and when. bsv.cx gives an AI agent verifiable memory. Timestamp a hash of any output, archive a web page as it looked, or fetch a URL with a recei

MCP-NixOS - Because Your AI Assistant Shouldn't Hallucinate About Packages

utensils

MCP-NixOS - Model Context Protocol Server for NixOS resources

739