Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
OLLAMA_URLNoLocal Ollama URLhttp://localhost:11434
PLUGINS_DIRNoPlugin directories (comma-separated)
DATABASE_URLYesPostgres connection string (required)
REDACT_PII_MODENooff / cloud_only / alwaysoff
FEDERATION_PEERSNoComma-separated peer URLs
WATCHDOG_ENABLEDNoBridge watchdog auto-recovery0
AUTO_SPAWN_BRIDGESNoAuto-spawn detected CLI bridges at boot0
FEDERATION_ENABLEDNoCross-instance learning0
OUTPUT_DEFENSE_MODENooff / tag / cutoff
DASHBOARD_AUTH_TOKENNoBearer token for /api/dashboard/*
INJECTION_DEFENSE_MODENooff / warn / block / llm_judgeoff
LLM_GATEWAY_MIN_TOKENSNoMin prompt length before compression700
SEMANTIC_CACHE_ENABLEDNoEmbedding-similarity cache0
ADAPTIVE_ROUTING_ENABLEDNoCost-aware adaptive routing0

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/renefichtmueller/adaptive-llm-gateway'

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