Skip to main content
Glama
ygq-future

openai-vision-mcp-server

by ygq-future

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
VISION_MODELYesVision model name (e.g., gpt-4o, qwen-vl-max, claude-3-5-sonnet).
VISION_API_KEYYesAPI key for authentication.
VISION_BASE_URLYesBase URL of the OpenAI-compatible API (e.g., https://api.openai.com/v1).
VISION_MAX_REDIRECTSNoMaximum HTTP redirect count. Default: 3.3
VISION_HTTP_TIMEOUT_MSNoHTTP request timeout in milliseconds. Default: 15000.15000
VISION_MAX_CONCURRENCYNoMax concurrent tile processing calls. Default: 2.2
VISION_MAX_INPUT_BYTESNoMax raw image download size in bytes. Default: 20971520.20971520
VISION_DEFAULT_MAX_TILESNoDefault hard ceiling for detail tiles (1 to 64). Default: 24.24
VISION_ALLOWED_FILE_ROOTSNoDelimiter-separated absolute paths allowed for file:// URIs. Default: "".
VISION_MAX_DECODED_PIXELSNoMax allowed total decoded image pixels. Default: 40000000.40000000
VISION_ALLOW_PRIVATE_NETWORKNoSet to 'true' to allow http(s):// fetches targeting private/internal IPs. Default: 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/ygq-future/openai-vision-mcp-server'

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