Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
LLAMA_CPP_PATHNoOptional llama.cpp path hint
RUVLTRA_CONFIGNoOptional JSON config file path
RUVLTRA_THREADSNollama.cpp thread count (0=auto)0
RUVLTRA_LOG_LEVELNodebug/info/warn/errorinfo
RUVLTRA_GPU_LAYERSNollama.cpp GPU layers (-1 for auto)-1
RUVLTRA_HTTP_MODELNoHTTP model nameruvltra-claude-code
RUVLTRA_MAX_TOKENSNoDefault max generation tokens512
RUVLTRA_MODEL_PATHNoLocal GGUF model file path (auto-search if not set)
RUVLTRA_HTTP_FORMATNoopenai or llamaauto
RUVLTRA_MAX_WORKERSNoMaximum worker count8
RUVLTRA_MIN_WORKERSNoMinimum worker count2
RUVLTRA_TEMPERATURENoDefault temperature0.2
RUVLTRA_HTTP_API_KEYNoHTTP API key
RUVLTRA_RUVLLM_MODELNoRuvLLM auto-download model IDruvltra-claude-code
RUVLTRA_SONA_ENABLEDNoEnable SONA self-improvementtrue
RUVLTRA_HTTP_ENDPOINTNoHTTP inference endpoint (OpenAI-compatible or llama.cpp HTTP)
RUVLTRA_CONTEXT_LENGTHNoContext token length4096
RUVLTRA_SONA_STATE_DIRNoSONA state directory./.ruvltra-state/sona
RUVLTRA_HTTP_TIMEOUT_MSNoHTTP timeout in milliseconds15000
RUVLTRA_INITIAL_WORKERSNoInitial worker count2
RUVLTRA_MOCK_LATENCY_MSNoMock backend latency in milliseconds120
RUVLTRA_TASK_TIMEOUT_MSNoDefault per-task timeout in milliseconds60000
RUVLTRA_HTTP_MAX_RETRIESNoHTTP retry count2
RUVLTRA_QUEUE_MAX_LENGTHNoMax queued tasks before backpressure256
RUVLTRA_HTTP_RETRY_BASE_MSNoRetry backoff base in milliseconds250
RUVLTRA_SONA_PERSIST_INTERVALNoPersist every N interactions10
RUVLTRA_HTTP_CIRCUIT_COOLDOWN_MSNoCircuit cooldown in milliseconds30000
RUVLTRA_HTTP_CIRCUIT_FAILURE_THRESHOLDNoFailures before opening circuit5

Capabilities

Server capabilities have not been inspected yet.

Tools

Functions exposed to the LLM to take actions

NameDescription

No tools

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Latest Blog Posts

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/coco4atJP/ruvltra-mcp-server'

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