Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
OLLAMA_HOSTNoOllama 服务地址。默认 http://127.0.0.1:11434。http://127.0.0.1:11434
OLLAMA_MODELNo本地模型。默认 deepseek-coder。deepseek-coder
OPENAI_MODELNo云端模型(DeepSeek 官方在列:deepseek-flash / deepseek-v4-pro)。默认 deepseek-flash。deepseek-flash
OPENAI_API_KEYNo云端密钥,仅从环境变量读取,永不写进代码。REFACTOR_BACKEND=openai 时必填。
OPENAI_BASE_URLNo云端接口地址(REFACTOR_BACKEND=openai 时生效)。默认 https://api.deepseek.com/v1。https://api.deepseek.com/v1
REFACTOR_BACKENDNo推理后端:ollama(本地)或 openai(任意 OpenAI 兼容接口)。默认 ollama。ollama
REFACTOR_TIMEOUTNo超时秒数(Python)。默认 180。180
REFACTOR_TIMEOUT_MSNo超时毫秒数(Node.js)。默认 180000。180000

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