Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
CODESIFT_DATA_DIRNoStorage directory for indexes~/.codesift
CODESIFT_OLLAMA_URLNoOllama URL for local embeddings (optional)
CODESIFT_LOCAL_MODELNoOverride local embedding model (e.g., 'Xenova/bge-small-en-v1.5')
CODESIFT_SECRET_SCANNoEnable/disable secret scanning (set 'false' to disable)true
CODESIFT_DEFAULT_TOP_KNoDefault max results for search50
CODESIFT_OPENAI_API_KEYNoOpenAI API key for semantic search (optional)
CODESIFT_VOYAGE_API_KEYNoVoyage AI API key for semantic search (optional)
CODESIFT_WATCH_DEBOUNCE_MSNoFile watcher debounce interval500
CODESIFT_DEFAULT_TOKEN_BUDGETNoDefault token budget for retrieval8000
CODESIFT_EMBEDDING_BATCH_SIZENoSymbols per embedding API call128
CODESIFT_MAX_EMBEDDING_MEM_MBNoCap resident embedding RAM in MB1024
CODESIFT_DISABLE_LOCAL_EMBEDDINGSNoSet to 'true' to disable local embeddings (Lite mode)

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/greglas75/codesift'

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