Skip to main content
Glama
Cesar514
by Cesar514

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
OLLAMA_HOSTNoOverride Ollama host
OLLAMA_API_KEYNoRequired only if your Ollama setup needs auth
OPENAI_API_KEYNoFallback alias for API key
OPENAI_BASE_URLNoFallback alias for base URLhttps://api.openai.com/v1
OLLAMA_CHAT_MODELNoChat model used in generated config examplesnemotron-3-nano:4b-128k
OLLAMA_EMBED_MODELNoOllama embedding model tagqwen3-embedding:0.6b-32k
OPENAI_EMBED_MODELNoFallback alias for embedding modeltext-embedding-3-small
SCPLUS_EMBED_NUM_CTXNoPass num_ctx into Ollama embed options
SCPLUS_EMBED_NUM_GPUNoPass num_gpu into Ollama embed options
SCPLUS_EMBED_LOW_VRAMNoPass low_vram into Ollama embed options
SCPLUS_EMBED_MAIN_GPUNoPass main_gpu into Ollama embed options
SCPLUS_EMBED_PROVIDERNoSelect embedding provider mode: 'ollama' or 'openai'ollama
SCPLUS_OPENAI_API_KEYNoPreferred OpenAI-compatible API key when provider is 'openai'
SCPLUS_PARENT_POLL_MSNoParent-process polling interval
SCPLUS_EMBED_NUM_BATCHNoPass num_batch into Ollama embed options
SCPLUS_IDLE_TIMEOUT_MSNoIdle shutdown timeout for MCP process
SCPLUS_OPENAI_BASE_URLNoPreferred OpenAI-compatible base URLhttps://api.openai.com/v1
SCPLUS_EMBED_BATCH_SIZENoEmbedding batch size, clamped in code8
SCPLUS_EMBED_NUM_THREADNoPass num_thread into Ollama embed options
SCPLUS_EMBED_CHUNK_CHARSNoChunk chars before vector merge, clamped in code2000
SCPLUS_OPENAI_EMBED_MODELNoPreferred OpenAI-compatible embedding modeltext-embedding-3-small
SCPLUS_MAX_EMBED_FILE_SIZENoMax file size for embed-aware search paths
SCPLUS_SCAN_MAX_MS_PER_TICKNoMax scanner milliseconds per tick100
SCPLUS_SCAN_STAT_CONCURRENCYNoMax concurrent file stat calls per scanner tick16
SCPLUS_SCAN_MAX_DIRS_PER_TICKNoMax directories scanned per bounded watcher tick32
SCPLUS_SCAN_MAX_FILES_PER_TICKNoMax files fingerprinted per bounded watcher tick256
SCPLUS_SCAN_RESCAN_INTERVAL_MSNoScanner tick interval cap used while watching1000
SCPLUS_WATCH_EVENT_PATH_SAMPLENoMax changed paths included in one streamed event payload100
SCPLUS_WATCH_MAX_PENDING_PATHSNoMax detailed pending paths before escalating to full rebuild5000

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/Cesar514/scplus-mcp'

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