Codex Vision MCP
MCPReferenceby darkamenosa
Indexed by Glama. No runnable package is published via Glama's API — open the repository for install instructions.
MCP configuration
Environment
CODEX_VISION_MODELResponses model to use for vision analysis. Default: gpt-5.5
CODEX_VISION_BASE_URLBase URL for the Codex Responses backend. Default: https://chatgpt.com/backend-api/codex
CODEX_VISION_AUTH_JSONExplicit path to a JSON file containing OAuth credentials. If not set, the server attempts to discover auth from other sources.
CODEX_VISION_TIMEOUT_MSTimeout in milliseconds for API requests. Default: 300000
CODEX_VISION_IMAGE_DETAILImage detail level: auto, low, high, or original. Default: auto
CODEX_VISION_MAX_IMAGE_MBMaximum image file size in MB. Default: 10
CODEX_VISION_MAX_VIDEO_MBMaximum video file size in MB. Default: 50
CODEX_VISION_MCP_LOG_PATHOptional path to a log file for the MCP server.
CODEX_VISION_VIDEO_FRAMESNumber of frames to extract from video. Default: 4
Install in one click with Zurek
Browse here, install from the native macOS app — pick targets, fill env vars, and write configs safely.