Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
MCP_EYES_LANGNoLanguage: auto, en, zh. Default auto.auto
MCP_EYES_MODELYesVision model identifier (e.g., doubao-seed-2.0-pro, gpt-4o-mini).
MCP_EYES_API_KEYYesProvider API key.
MCP_EYES_TIMEOUTNoHTTP timeout in seconds. Default 90.90
MCP_EYES_BASE_URLYesAPI endpoint URL, no trailing slash, no /chat/completions or /messages suffix.
MCP_EYES_PROTOCOLYesProtocol to use: 'openai' or 'anthropic'.
MCP_EYES_CACHE_DIRNoCache location. Default ~/.cache/mcp-eyes.~/.cache/mcp-eyes
MCP_EYES_MAX_TOKENSNoVision model max_tokens. Default 1536.1536
MCP_EYES_TEMPERATURENoSampling temperature. Lower = more deterministic. Default 0.2.0.2
MCP_EYES_CACHE_ENABLEDNoDisk cache for (image-hash + prompt + model). Default true.true
MCP_EYES_MAX_IMAGE_DIMNoAuto-resize longest edge to this many px (Pillow required). 0 disables. Default 2048.2048
MCP_EYES_ANTHROPIC_VERSIONNoAnthropic protocol only. The anthropic-version header value. Default 2023-06-01.2023-06-01

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/loudMore/vision-extension'

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