generate_imageLABSCO SUMMARY
One key, and the model gets eyes, ears and a sandbox.
The breadth is the draw: transcription, video analysis and image editing usually mean three servers and three configs. The preference layer is the part to judge for yourself — it rewrites your prompts before they reach Gemini, which helps when the context guess is right and is worth watching when it is not. Verbatim transcription is the standout: it keeps the fillers most transcription tools quietly delete.
What it is
An MCP server over Google's Gemini API offering seven tools, wrapped in a preference layer that detects the context of a request, enhances the prompt accordingly, and stores what worked for next time.
What you get
generate_image— images from a text prompt, with optionaltemperatureand astylechosen from realistic, artistic, minimalistic, vibrant, photographic or abstractgemini-edit-image— edit an existing image from a natural-language instructiongemini-chat— conversation with context-aware responsesgemini-transcribe-audio— MP3, WAV, FLAC, AAC, OGG, WEBM or M4A to text, with a verbatim mode that keeps fillers, repeated words and expressions such as [laughs], andpreserve_spelled_acronymsto keep U-R-L as spokengemini-code-execute— run Python in a sandboxgemini-analyze-video— summary, transcript, objects or a detailed pass over MP4, MOV, AVI, WEBM, MKV or FLVgemini-analyze-image— objects, text and descriptions from JPEG, PNG, WebP, HEIC, HEIF, BMP or GIF- Context types the server recognises:
consciousness,code,debugging,general, andverbatimfor transcription
Requirements
A Google Gemini API key in GEMINI_API_KEY. Clone the repo, npm install, then register node gemini-server.js with the key in the env block; OUTPUT_DIR and DEBUG are optional. Learned preferences are stored at ./data/tool-preferences.json. File size limits are 20MB for images, 20MB for audio and 100MB for video. Package version 2.2.0. MIT.
Setup effort
Build from source — git clone https://github.com/Garblesnarff/gemini-mcp-server.git
USE CASES
01
Getting an exact transcript, fillers included
Transcribe an interview in verbatim mode so "um", repeated words and [laughs] survive instead of being cleaned away.
02
Turning a recorded session into notes
Run a detailed pass over the video file and get a summary plus what happened on screen.
03
Making and then fixing an image
Generate a first image from a prompt, then edit it with an instruction rather than regenerating from scratch.
04
Checking a calculation without a local Python
Send the snippet to the sandbox and read the printed output back in the conversation.
7 tools
Listed in project docs. Your client may show a different list.
gemini-edit-imagegemini-chatgemini-transcribe-audiogemini-code-executegemini-analyze-videogemini-analyze-imageBEFORE YOU INSTALL
What to know first
Tools you get
7 tools named in the project's documentation.
Requires
- Node.js 16 or later
- GEMINI_API_KEY in your environment
Where it runs
The documented client runs the server on your machine.
INSTALLATION
Connect your client
You clone this one yourself.
Server setup
TERMINAL
git clone https://github.com/Garblesnarff/gemini-mcp-server.git
cd gemini-mcp-server
npm installMCP Clients
Claude Desktop
CLAUDE DESKTOP · JSON
{
"mcpServers": {
"gemini": {
"command": "node",
"args": [
"<YOUR_PATH_TO_GEMINI_MCP_SERVER>/gemini-server.js"
],
"env": {
"GEMINI_API_KEY": "<YOUR_GEMINI_API_KEY>"
}
}
}
}<YOUR_PATH_TO_GEMINI_MCP_SERVER> is the full path of the folder you cloned.
