Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
CHUTES_WARMUPNoWarm models up before invoking.true
CHUTES_API_KEYYesYour Chutes API key.
CHUTES_OUTPUT_DIRNoOutput directory relative to the agent's CWD.assets/chutes
CHUTES_AUTH_SCHEMENoHow the key is sent in Authorization: raw or bearer.raw
CHUTES_API_BASE_URLNoManagement API base URL.https://api.chutes.ai
CHUTES_COLD_START_RETRIESNoRetries when a cold model returns 503 no-instances.4
CHUTES_PROGRESS_INTERVAL_MSNoHow often progress heartbeats are emitted.5000
CHUTES_COLD_START_BACKOFF_MSNoBase backoff between cold-start retries.8000

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/TheStreamCode/chutes-media-mcp'

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