Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
VISION_MODELNoModel name to use for vision tasks.qwen3.7-plus
OPENAI_API_KEYNoOpenAI API key. Alternative to VISION_API_KEY.
VISION_API_KEYNoAPI key for your vision model provider. If not set, DASHSCOPE_API_KEY or OPENAI_API_KEY can be used.
VISION_TIMEOUTNoTimeout in milliseconds for API requests.120000
VISION_BASE_URLNoBase URL for an OpenAI-compatible vision endpoint.https://dashscope.aliyuncs.com/compatible-mode/v1
DASHSCOPE_API_KEYNoAlibaba Cloud DashScope API key. Alternative to VISION_API_KEY.
VISION_MAX_TOKENSNoMaximum number of tokens in the response.1024
VISION_ENABLE_THINKINGNoWhether to enable thinking mode for qwen3 models (true/false).false

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/sulghu/vision-mcp'

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