Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
DISCORD_TOKENYesThe bot token from the Discord Developer Portal.
DISCORD_SAMPLING_MODELNoModel name to use for local agentic sampling.
DISCORD_SAMPLING_BASE_URLNoBase URL for local agentic sampling (e.g., Ollama or OpenAI-compatible API).
DISCORD_MAX_MESSAGE_LENGTHNoOverride for maximum message length (Discord default/max is 2000).
DISCORD_SAMPLING_USE_CLIENT_LLMNoSet to 1 if you want the host LLM to handle sampling and the server handler only as a fallback.
DISCORD_MIN_MESSAGE_INTERVAL_SECONDSNoMinimum seconds to wait between sending messages.
DISCORD_RATE_LIMIT_INVITES_PER_MINUTENoMaximum invites created per minute (anti-spam).
DISCORD_RATE_LIMIT_CHANNELS_PER_MINUTENoMaximum channels created per minute (anti-spam).
DISCORD_RATE_LIMIT_MESSAGES_PER_MINUTENoGlobal maximum messages allowed per minute (anti-spam).
DISCORD_RATE_LIMIT_MESSAGES_PER_CHANNEL_PER_MINUTENoMaximum messages allowed per minute per channel (anti-spam).

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/sandraschi/discord-mcp'

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