zgz518/vision-bridge-mcp

Give models that do not support multimodality, such as DeepSeek and text-only models, a pair of eyes.

0Stars on the repository
1Mods indexed here, across every type
1mo agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

vision-bridge-mcp

01

zgz518/vision-bridge-mcp

MCP server Claude CodeCodexCursor +2

A local MCP server that uses a MiniMax vision model to turn images into written descriptions for text-only models.

not rated 0 1mo ago A tokens not measured original MIT