Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
BIND_ADDRNoAddress to bind application ports. Set to 0.0.0.0 to expose on a LAN/private network or behind a TLS reverse proxy.127.0.0.1
AUTH_ENABLEDNoEnable authentication for MCP and REST routes. When true, protected routes require an X-API-Key.true
DREAM_ENABLEDNoEnable automated memory consolidation and person profiles. Off by default.false
EMBEDDING_DIMNoDimension of the embedding model. For low-RAM (8GB) deployments, set to 384.
EMBEDDING_MODELNoEmbedding model to use. For low-RAM (8GB) deployments, set to granite-embedding:30m.
PROCEDURE_ENABLEDNoEnable living procedures observation. Off by default.false
SKILL_SYNTHESIS_ENABLEDNoEnable server-side auto-synthesis of skills. Off by default.false
SYMDEX_ANALYTICS_ENABLEDNoEnable the 8 hidden Symdex analytics tools. Off by default.false
PATTERN_VALIDATION_ENABLEDNoEnable automated pattern validation. Off by default.false
PATTERN_EXPERIMENTS_ENABLEDNoEnable experiment framework for pattern tips. Off by default.false

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/kapella-hub/FirekeepHQ'

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