Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
NO_PROXYNoComma-separated list of hosts that should bypass the proxy, e.g., 'localhost,127.0.0.1' for local servers.
VISION_MODELYesThe vision model to use, e.g., 'glm-4v-flash', 'qwen2.5-vl'. Can include comma-separated fallback models, e.g., 'primary-vision-model,backup-vision-model'.
VISION_API_KEYNoAPI key for cloud services. Leave empty for local servers (Ollama, vLLM, LM Studio). It is sent as Authorization header only for remote endpoints.
VISION_API_BASEYesBase URL of the vision API endpoint. Must point to the root of an OpenAI Chat Completions compatible endpoint (e.g., https://open.bigmodel.cn/api/paas/v4) or a local Ollama/vLLM/LM Studio endpoint (e.g., http://localhost:11434/v1).
VISION_API_STYLENoAPI style: 'openai' (default) for OpenAI-compatible endpoints, or 'gemini' for Google Gemini native endpoint.openai
VISION_FALLBACKSNoComma-separated list of fallback models from other providers to try if the primary model fails. Used with VISION_API_STYLE and VISION_API_BASE per provider? (optional)
VISION_MAX_TOKENSNoMaximum number of tokens for the API response. Default is 4096.4096
VISION_ALLOWED_DIRSNoColon-separated (or semicolon on Windows) list of directories that the server is allowed to read images from. Restricts local file access for security.

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/Hel10o/vision-bridge-mcp'

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