DIV7NE

DIV7NE/deepseek-vision-mcp

Skill Claude CodeCodex

Structured UI report from a screenshot via vision MCP: ASCII wireframe + element inventory (label/role/position/state) + visual notes.

DIV7NE/deepseek-vision-mcp

MCP server Claude CodeCodexCursor

MCP Server that gives DeepSeek (and other text-only LLMs) vision capability via third-party OpenAI-compatible vision APIs. Runs locally from the deepseek-vision-mcp Python package.