gemini-mcp-server
by mnthe
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GEMINI_MODEL | No | Model to use (default: gemini-3.5-flash). | |
| GEMINI_TOP_K | No | Top-k sampling parameter (default: 40). | |
| GEMINI_TOP_P | No | Top-p sampling parameter (default: 0.95). | |
| GEMINI_API_KEY | No | Your Google AI Studio API key. Required for AI Studio mode. | |
| GEMINI_LOG_DIR | No | Directory for log files (default: ./logs). | |
| GEMINI_MAX_TOKENS | No | Maximum output tokens (default: 8192). | |
| GEMINI_MAX_HISTORY | No | Maximum history entries per session (default: 10). | |
| GEMINI_MCP_SERVERS | No | JSON array of external MCP server configurations. | |
| GEMINI_TEMPERATURE | No | Temperature for generation (default: 1.0). | |
| GEMINI_LOG_TO_STDERR | No | Log to stderr instead of files (default: true). | |
| GEMINI_SYSTEM_PROMPT | No | Custom system prompt to set the AI's persona. | |
| GOOGLE_CLOUD_PROJECT | No | Your GCP project ID. Required for Vertex AI mode. | |
| GOOGLE_CLOUD_LOCATION | No | GCP location (e.g., us-central1). Required for Vertex AI mode. | |
| GEMINI_ALLOW_FILE_URIS | No | Allow file:// URIs (default: false, secure). | |
| GEMINI_DISABLE_LOGGING | No | Disable logging entirely (default: false). | |
| GEMINI_SESSION_TIMEOUT | No | Session timeout in seconds (default: 3600). | |
| GEMINI_IMAGE_OUTPUT_DIR | No | Directory for generated images (default: ~/Pictures/gemini-generated). | |
| GEMINI_MEDIA_RESOLUTION | No | Media resolution for Gemini 3 models: low, medium, high. | |
| GEMINI_MUSIC_OUTPUT_DIR | No | Directory for generated music (default: ~/Music/gemini-generated/music). | |
| GEMINI_VIDEO_OUTPUT_DIR | No | Directory for generated videos (default: ~/Movies/gemini-generated on macOS, ~/Videos/gemini-generated on Windows/Linux). | |
| GEMINI_SPEECH_OUTPUT_DIR | No | Directory for generated speech (default: ~/Music/gemini-generated/speech). | |
| GOOGLE_GENAI_USE_VERTEXAI | No | Set to 'false' to use Google AI Studio mode. Default is 'true' for Vertex AI mode. | |
| GEMINI_ENABLE_CONVERSATIONS | No | Enable multi-turn conversations (default: false). | |
| GOOGLE_APPLICATION_CREDENTIALS | No | Path to service account key JSON file for Vertex AI authentication (alternative to ADC). |
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/mnthe/gemini-mcp-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server