three.ws Vision MCP
v0.1.1io.github.nirholas/vision-mcp
Image understanding for AI agents — analyze and describe any image via the three.ws pipeline.
transport:stdio
runtime:npm
Target client
run in your project directory
claude mcp add vision-mcp -e THREE_WS_BASE=<THREE_WS_BASE> -e THREE_WS_TIMEOUT_MS=<THREE_WS_TIMEOUT_MS> -e THREE_WS_API_KEY=<THREE_WS_API_KEY> -- npx -y @three-ws/vision-mcp
Adds it for this project only. Append --scope user to make it available everywhere. Claude Code docs
This listing does not declare its tools. Connect the server and your client will discover them on the handshake.