Schema

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

Interactive templates invoked by user choice

Name	Description
No prompts

Contextual data attached and managed by the client

Name	Description
No resources

Functions exposed to the LLM to take actions

Name	Description
No tools