Skip to main content
Glama
Sign In
enesjakozh
Gemini MCP Server

Gemini MCP Server

by georgejeffers
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

gemini-mcp-server

A TypeScript implementation of a Model Context Protocol (MCP) server that integrates with Google's Gemini Pro model.

MCP Tools

generate_text

From server: gemini

Related MCP server: MCP Gemini Server

Prerequisites

  • Node.js 18 or higher

  • Google Gemini API key

  • TypeScript

  • Claude Desktop app

Installation

Installing via Smithery

To install Gemini MCP Server for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install @georgejeffers/gemini-mcp-server --client claude

Manual Installation

  1. Clone the repository:

git clone https://github.com/GeorgeJeffers/gemini-mcp-server.git
cd gemini-mcp-server

  1. Install dependencies:

npm install

  1. Build:

npm run build

Claude Desktop Integration

To use this server with Claude Desktop:

  1. Open Claude Desktop

  2. Go to Settings > Developer

  3. Click "Edit Config"

  4. Add the following configuration:

{
  "name": "gemini",
  "command": "node",
  "args": ["dist/gemini_mcp_server.js"],
  "env": {
    "GEMINI_API_KEY": "your_api_key_here"
  },
  "cwd": "/path/to/mcp-gemini-server"
}

Replace:

  • /path/to/mcp-gemini-server with the absolute path to where you cloned this repository

  • your_api_key_here with your actual Google Gemini API key

The server will now be available in Claude Desktop's MCP server list.

License

MIT

Author

GeorgeJeffers

Available Tools

7 tools
chatChatA

Multi-turn conversation with session management. Omit sessionId to start a new session; include it to continue an existing one.

Inputs: message (required), sessionId, model, systemInstruction. Returns: response, sessionId, turnCount

code_executionCode ExecutionA
Read-only

Execute Python code in a sandboxed environment. Gemini generates and runs code, returning both the code and results.

Inputs: prompt (required), model, temperature, maxOutputTokens.

edit_imageEdit ImageA
Read-only

Edit an image using a text prompt. Send a base64-encoded image and describe the desired changes.

Inputs: prompt (required), image (required), mimeType, model, +2 more.

edit_image_multiEdit Image (Multi-Reference)B
Read-only

Edit or compose images using multiple reference images (up to 14). Uses gemini-3-pro-image-preview (Nano Banana Pro).

Inputs: prompt (required), images (required), aspectRatio, imageSize.

generate_imageGenerate ImageB
Read-only

Generate an image from a text prompt using Gemini image models (Nano Banana Pro by default).

Inputs: prompt (required), model, aspectRatio, imageSize.

generate_textGenerate TextB
Read-only

Generate text using Google Gemini models with configurable model, temperature, and system instructions.

Inputs: prompt (required), model, temperature, maxOutputTokens, +1 more.

generate_with_searchGenerate with SearchA
Read-only

Generate text with Google Search grounding for up-to-date, cited responses.

Inputs: prompt (required), model, temperature, maxOutputTokens.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Deploy Server
    One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

    TDQS

    A3.9/5.0

    Scored across 7 tools

    Disambiguation5/5

    Each tool has a clearly distinct purpose with no overlap: chat handles conversations, code_execution runs Python, edit_image modifies single images, edit_image_multi handles multiple images, generate_image creates images, generate_text produces text, and generate_with_search adds search grounding. The descriptions clearly differentiate their functions, making misselection unlikely.

    Naming Consistency5/5

    All tools follow a consistent verb_noun pattern (e.g., chat, code_execution, edit_image, generate_image, generate_text, generate_with_search). The naming is uniform and predictable across all seven tools, with no deviations in style or convention.

    Tool Count5/5

    With 7 tools, the count is well-scoped for a Gemini MCP server, covering core AI functionalities like text generation, image handling, code execution, and chat. Each tool earns its place without feeling excessive or insufficient for the server's purpose.

    Completeness4/5

    The tool surface is nearly complete for a Gemini AI server, covering text generation (with and without search), image generation and editing, code execution, and chat. A minor gap exists in lacking explicit tools for model management or configuration, but core workflows are well-covered and agents can work around this.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Resources

    Related MCP Connectors

    Related MCP Servers

    • MCP Gemini Server

      amitsh06
      F
      license
      Not graded
      quality
      D
      maintenance
      A server implementing the Model Context Protocol that enables AI assistants like Claude to interact with Google's Gemini API for text generation, text analysis, and chat conversations.
      -

    • Gemini MCP Server

      dakrin
      A
      license
      B
      quality
      D
      maintenance
      A Model Context Protocol server that enables Claude Desktop to interact with Google's Gemini 2.5 Pro Experimental AI model, with features like Google Search integration and token usage reporting.
      2
      75 npm
      4
      Apache 2.0

    • Gemini MCP Server

      IA-Entertainment-git-organization
      A
      license
      D
      quality
      D
      maintenance
      A TypeScript implementation of a Model Context Protocol server that integrates with Google's Gemini 2.0 Flash model, enabling Claude Desktop users to interact with Gemini through natural language conversations.
      1
      210 npm
      3
      MIT

    Appeared in Searches