Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
PORTNoThe port the server listens on.8787
DB_FILENoPath to the SQLite database file.data/agentlayer.db
CRAWL_RENDERNoWhen to render pages: auto|never|always.auto
LLM_PROVIDERNoLLM provider: auto|anthropic|deepseek|heuristic.auto
API_KEY_PEPPERNoSecret used for hashing API keys; must be set in production.dev value
ANTHROPIC_MODELNoModel name to use for Anthropic.claude-sonnet-5
CRAWL_MAX_PAGESNoMaximum pages to crawl per site.60
DEEPSEEK_API_KEYNoAPI key for DeepSeek (alternative provider).
ANTHROPIC_API_KEYNoAPI key for Anthropic (enables model extraction pass).
EMBEDDING_API_KEYNoAPI key for hosted embedding provider.
EMBEDDING_PROVIDERNoEmbedding provider: local|voyage|openai.local
AGENTLAYER_MCP_TIERNoMCP tool tier: public or restricted.restricted
MONITOR_INTERVAL_MSNoRecrawl cadence in milliseconds.6h
CONTEXT_TOKEN_BUDGETNoSoft token budget for context.json.6000
CRAWL_RESPECT_ROBOTSNoWhether to respect robots.txt.true

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/mhsh77/ai-agent-layer'

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