Gemini MCP Server by aliargun

What it is

A stdio bridge to the Google Gemini API. Six tools cover generation, vision, embeddings, token counting, model discovery and built-in help, with the model named per call.

What you get

• generate_text with the parameters exposed as arguments: model, temperature, topK, topP, maxTokens, systemInstruction and safetySettings
• jsonMode with a jsonSchema, so a call can return a structured object instead of prose you then have to parse
• Grounding turns on Google Search grounding for questions where current material matters
• conversationId keeps a thread going across calls rather than restarting the context each time
• analyze_image takes a prompt plus an image URL or base64 data
• embed_text produces embeddings from Gemini's embedding models
• count_tokens measures text against a specific model before you send it
• list_models returns the available models and their capabilities, with an optional filter
• get_help answers usage questions about the server itself, by topic

Requirements

A Gemini API key from Google AI Studio, passed as GEMINI_API_KEY in the client's env block — it is read from the environment only, never an argument. It runs over stdio as npx -y github:aliargun/mcp-server-gemini, so Node and network access are all that is needed locally. Usage is billed by Google against that key. MIT.

Setup effort

One command plus a key — npx -y github:aliargun/mcp-server-gemini, then supply credentials

Tools you get

6 tools when we connected. The documentation never prints tool names. Ignore the PORT and localhost:3005 instructions in the docs folder; the server communicates over stdio.

Requires

• npx on PATH
• GEMINI_API_KEY in your environment

Where it runs

All 4 documented setups run the server on your machine.