Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
HF_TOKENNoHuggingFace token
LOG_LEVELNoLog levelINFO
OLLAMA_URLNoLocal LLM (Ollama) endpointhttp://localhost:11434
QDRANT_HOSTNoQdrant hostlocalhost
QDRANT_PORTNoQdrant port6333
DATABASE_URLNoPostgreSQL connection string (required)
VAULT_OUTPUT_DIRNoContainer Vault output mount point/output
GPU_SCHEDULER_URLNoGPU scheduler endpointhttp://gpu-scheduler:9400
OPENAI_COMPAT_URLNoExternal OpenAI-compatible endpointhttp://localhost:8317
POSTGRES_PASSWORDNoPostgreSQL password for docker-compose setup
VAULT_OUTPUT_HOST_DIRNoHost path to Obsidian vault (for docker-compose)
LLAMA_SERVER_BATCH_URLNoBatch llama-server endpointhttp://localhost:11435
FOUNDATION_ALLOWED_EMAILSNoAllowed email addresses for OAuth (required in http 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/nekoPhysics/foundation-core'

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