A local MCP server that adds computer-vision tools to coding agents and models that do not support native image input, using Codex OAuth credentials and the ChatGPT/Codex Responses backend.
Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find.
Install from
M8ven verifies MCPs across every public registry — install directly from whichever one you prefer.
process.env. You'll be asked to provide them before it can run.CODEX_AUTH_JSONCODEX_HOME— 4. /auth.jsonCODEX_IMAGEN_AUTH_JSONCODEX_REFRESH_TOKEN_URL_OVERRIDECODEX_VISION_AUTH_JSON— explicit auth JSON pathCODEX_VISION_BASE_URL— default https://chatgpt.com/backend-api/codexCODEX_VISION_CODEX_VERSIONCODEX_VISION_FORCE_REFRESHCODEX_VISION_IMAGE_DETAIL— auto, low, high, or originalCODEX_VISION_MAX_IMAGE_MB— default 10CODEX_VISION_MAX_VIDEO_MB— default 50CODEX_VISION_MCP_LOG_PATH— optional log file pathCODEX_VISION_MODEL— Responses model, default gpt-5.5CODEX_VISION_NO_REFRESHCODEX_VISION_VIDEO_FRAMESTERMTERM_PROGRAMTERM_PROGRAM_VERSION[](https://m8ven.ai/mcp/darkamenosa-codex-vision-mcp-1ujeyb)