Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
BRAIN_DIRNoWhere the second brain is stored.D:/mcp/second_brain
MAX_AGENTSNoAuto-spawn safety limit.6
ADAPTER_DIRNoWhere gateway_generate_adapter writes generated servers.<state dir>/adapters
GATEWAY_FILENoHub registry/routes/audit (kept out of team state and resets).<state dir>/gateway.json
GATEWAY_MAX_OPSNoMax operations generated from one OpenAPI spec.150
TEAM_STATE_FILENoPath to the shared state file. Use the same value for every client.D:/mcp/shared_state.json (Windows) / ~/.claude_team_state.json
LOG_ROTATE_LIMITNoActivity-log size cap.2000
MSG_ROTATE_LIMITNoChannel size before old messages are archived out.2000
GATEWAY_VAULT_FILENoSecret vault (written chmod 600).<state dir>/gateway_vault.json
AGENT_STALE_SECONDSNoIdle time before an agent is marked offline.300
GATEWAY_AUDIT_LIMITNoGateway audit-trail size cap.2000
GATEWAY_CALL_TIMEOUTNoTimeout (s) for proxied REST calls.30
GATEWAY_RATE_PER_MINNoDefault per-agent, per-target call limit.60

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/Lakshan12367/MCP'

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