Gemini Mcp
by RLabs-Inccommunityv0.7.1
195
38
This MCP server integrates Google's Gemini 3 models with Claude Code, facilitating collaboration between the two AI systems.
From the registry: Gemini 3 MCP server with 30+ tools: images, video, research, TTS, code exec & CLI
Install & configure
Prerequisites
- required
Install in your client
Paste into the AI you're chatting with — it will figure out the rest
Please install the `gemini-mcp` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Gemini API key** — Free from Google AI Studio (https://aistudio.google.com/apikey)
Canonical MCP server config (stdio transport):
- command: `npx`
- args: ["-y","@rlabs-inc/gemini-mcp"]
- required environment variables:
- `GEMINI_API_KEY`: Google Gemini API key (example: `<your-gemini-api-key>`)
- optional environment variables:
- `GEMINI_OUTPUT_DIR`: Where to save generated files (example: `./gemini-output`)
- `GEMINI_TOOL_PRESET`: Tool preset: minimal, text, image, research, media, full (example: `full`)
- `GEMINI_ENABLED_TOOLS`: Comma-separated tool groups to load (example: `query,search,image-gen`)
- `VERBOSE`: Enable verbose logging (example: `false`)
Note: 37 tools for Gemini 3 including deep research, video (Veo), image gen, TTS, document analysis, and more. Use GEMINI_TOOL_PRESET to reduce tool count.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.Note: 37 tools for Gemini 3 including deep research, video (Veo), image gen, TTS, document analysis, and more. Use GEMINI_TOOL_PRESET to reduce tool count.
Tools (19)
gemini-query
Direct queries to Gemini with thinking level control.
gemini-generate-image
Generate images with specified prompts and styles.
gemini-start-image-edit
Start a multi-turn image editing session.
gemini-continue-image-edit
Continue refining an image in an editing session.
gemini-end-image-edit
Close an editing session.
gemini-generate-video
Generate videos using specified prompts.
gemini-analyze-code
Analyze code for issues.
gemini-analyze-text
Analyze text content for various insights.
gemini-brainstorm
Collaborative brainstorming tool.
gemini-summarize
Summarize content based on specified length and format.
gemini-run-code
Let Gemini write and execute Python code.
gemini-search
Perform real-time web searches with citations.
gemini-structured
Get JSON responses matching a schema.
gemini-extract
Environment variables
GEMINI_API_KEYrequiredYour Google Gemini API key.Packages
@rlabs-inc/gemini-mcp
npmv0.7.1transport: stdio
Details
- Language
- TypeScript
- License
- MIT
- Released
- Jan 5, 2026
- Last commit
- Mar 13, 2026
- Registry name
- io.github.RLabs-Inc/gemini-mcp