Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
HF_ENDPOINTNo透传 huggingface_hub,国内设 https://hf-mirror.com
MODEL_CACHENo模型快照本地目录(Docker 镜像内置 /models 预下载);设置后优先读本地,配 HF_HUB_OFFLINE=1 可纯离线
KRONOS_MODELNo预测模型(另有 Kronos-mini 4.1M / Kronos-base 102.3M,均 MIT)NeoQuasar/Kronos-small
KRONOS_DEVICENoauto = cuda > mps > cpu;也可显式 cpu/cuda/mpsauto
HF_HUB_OFFLINENo设置 1 以在配置 MODEL_CACHE 后纯离线运行
KRONOS_TOKENIZERNoK 线分词器NeoQuasar/Kronos-Tokenizer-base
MCP_LICENSE_FILENolicenses.json 文件路径;设置后强制 license key 鉴权

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

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/JingxuanC/kronos-mcp'

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