Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
DB_HOSTNoPostgreSQL hostlocalhost
DB_NAMENoDatabase namehc_ai
DB_PORTNoPostgreSQL port5432
LLM_MODELNoLLM model for ollama/bedrock (e.g., llama3, haiku, sonnet, opus)haiku
AWS_REGIONNoAWS region (required if LLM_PROVIDER=bedrock or EMBEDDING_PROVIDER=bedrock)
DB_PASSWORDYesDatabase password (required)
HC_AI_DEBUGNoEnable debug logging (set to 'true')
LLM_PROVIDERNoLLM provider: ollama, openai, anthropic, bedrockollama
OPENAI_MODELNoOpenAI modelgpt-4o-mini
AGENT_TIMEOUTNoAgent timeout in seconds60
OPENAI_API_KEYNoOpenAI API key (required if LLM_PROVIDER=openai)
RERANK_TIMEOUTNoRerank timeout in seconds30
ANTHROPIC_MODELNoAnthropic modelclaude-3-5-sonnet-20241022
ANTHROPIC_API_KEYNoAnthropic API key (required if LLM_PROVIDER=anthropic)
EMBEDDING_PROVIDERNoEmbedding provider: ollama or bedrockollama

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/rsanandres/atlas_mcp'

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