Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
PORTNoHTTP server port (when TRANSPORT=http)3000
TRANSPORTNoTransport mode: stdio or httpstdio
XCOMET_DEBUGNoEnable verbose debug logging (v0.3.1+)false
XCOMET_MODELNoxCOMET model to use (e.g., Unbabel/XCOMET-XL, Unbabel/XCOMET-XXL, or Unbabel/wmt22-comet-da)Unbabel/XCOMET-XL
XCOMET_PRELOADNoPre-load model at startup (v0.3.1+). Enabling this makes all requests fast (~500ms), including the first one.false
XCOMET_PYTHON_PATHNoPython executable path. If not set, the server automatically detects a Python environment with unbabel-comet installed.

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/shuji-bonji/xcomet-mcp-server'

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