Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
ARK_API_KEYNoAlternative to `VOLCANO_API_KEY` for the Volcano Ark Key.
ARK_BASE_URLNoVolcano Ark base URL, default `https://ark.cn-beijing.volces.com/api/v3`.
VISION_MODELSNoComma-separated candidate chain, can include provider prefixes: `ollama:qwen2.5vl:3b,ark:doubao-seed-2-0-pro-260215`. Default is this string.
VISION_API_KEYNoUse when connecting to any OpenAI-compatible service (provider name `openai`).
DSH_VISION_HOMENoSettings file directory, default `~/.dsh-vision`.
OLLAMA_BASE_URLNoOpenAI-compatible address of local Ollama, default `http://127.0.0.1:11434/v1`.
VISION_BASE_URLNoUse when connecting to any OpenAI-compatible service (provider name `openai`).
VISION_PROVIDERNoWhich provider unprefixed model ids belong to: `ollama` (default) / `ark` / `openai`.
VOLCANO_API_KEYNoVolcano Ark Key (can also use `ARK_API_KEY`). Only needed when the `ark:` candidate is configured.
VISION_TIMEOUT_MSNoSingle request timeout, default 60000.

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