Llama 4 Maverick MCP Server
by YobieBen
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| SEED | No | Random seed for reproducible results | 42 |
| DEBUG | No | Enable debug mode | false |
| TOP_K | No | Top-k sampling parameter (1-100) | 40 |
| TOP_P | No | Top-p sampling parameter (0.0-1.0) | 0.9 |
| CACHE_TTL | No | Cache time-to-live in seconds | 3600 |
| PYTHONPATH | No | Python path for module imports | |
| TEMPERATURE | No | Model temperature setting (0.0-2.0) | 0.7 |
| ENABLE_VISION | No | Enable vision processing capabilities | false |
| LLAMA_API_KEY | No | Optional API key for Ollama authentication | |
| LLAMA_API_URL | No | URL for the Ollama API server | http://localhost:11434 |
| MCP_LOG_LEVEL | No | Logging level for the MCP server | INFO |
| CACHE_MAX_SIZE | No | Maximum cache size | 1000 |
| REPEAT_PENALTY | No | Repetition penalty for text generation | 1.1 |
| MCP_SERVER_HOST | No | Host address for the MCP server | localhost |
| MCP_SERVER_PORT | No | Port number for the MCP server | 3000 |
| VERBOSE_LOGGING | No | Enable verbose logging | false |
| ENABLE_STREAMING | No | Enable streaming support for real-time token generation | true |
| LLAMA_MODEL_NAME | No | Name of the Llama model to use | llama3:latest |
| ALLOW_FILE_WRITES | No | Allow file write operations | true |
| ENABLE_WEB_SEARCH | No | Enable web search functionality | true |
| MAX_CONTEXT_LENGTH | No | Maximum context length for the model | 128000 |
| REQUEST_TIMEOUT_MS | No | Request timeout in milliseconds | 30000 |
| ENABLE_CODE_EXECUTION | No | Enable code execution (security risk) | false |
| FILE_SYSTEM_BASE_PATH | No | Base path for file system operations | |
| ENABLE_FUNCTION_CALLING | No | Enable function calling capabilities | true |
| MAX_CONCURRENT_REQUESTS | No | Maximum number of concurrent requests | 10 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
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 | |
This server cannot be deployed
Maintenance
ActivityInactive
ResponsivenessNo issues