Schema | gemini-mcp

gemini-mcp

Describes the environment variables required to run the server.

Name	Required	Description	Default
`QUIET`	No	Minimize logging (default: false)	false
`VERBOSE`	No	Enable verbose logging (default: false)	false
`HTTP_PROXY`	No	HTTP proxy URL (optional)
`HTTPS_PROXY`	No	HTTPS proxy URL (optional)
`GEMINI_MODEL`	No	Override model for init test
`GEMINI_API_KEY`	Yes	Your Google Gemini API key (required)
`GEMINI_PRO_MODEL`	No	Pro model (default: gemini-3-pro-preview)	gemini-3-pro-preview
`GEMINI_OUTPUT_DIR`	No	Directory to save generated files (default: ./gemini-output)	./gemini-output
`GEMINI_FLASH_MODEL`	No	Flash model (default: gemini-3-flash-preview)	gemini-3-flash-preview
`GEMINI_IMAGE_MODEL`	No	Image model (default: gemini-3-pro-image-preview)	gemini-3-pro-image-preview
`GEMINI_TOOL_PRESET`	No	Preset profile: minimal, text, image, research, media, full
`GEMINI_VIDEO_MODEL`	No	Video model (default: veo-2.0-generate-001)	veo-2.0-generate-001
`GEMINI_ENABLED_TOOLS`	No	Comma-separated list of tool groups to load
`GEMINI_IMAGE_THINKING_LEVEL`	No	Default thinking level for image generation (minimal, low, medium, high)	high

Server capabilities have not been inspected yet.

Functions exposed to the LLM to take actions

Name	Description
No tools

Interactive templates invoked by user choice

Name	Description
No prompts

Contextual data attached and managed by the client

Name	Description
No resources

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/RLabs-Inc/gemini-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server