SkillAgentSearch skills...

mcp-vision-bridge

MCP server that gives text-only LLM coding agents vision — analyze images via any multimodal model (mimo, Claude, Gemini, OpenAI-compatible). Works with Claude Code, Codex, Kimi, opencode, PI.

Install / Use

claude mcp add KuaaMU -- npx -y github:KuaaMU/mcp-vision-bridge

If the server publishes to npm under a different name, use that package instead — check the repo README.

About this skill
🔌

MCP Server

Model Context Protocol server

Quality Score

18/100

Supported Platforms

Claude Code
Claude Desktop
Gemini CLI
OpenAI Codex

Related Skills

View on GitHub
GitHub Stars9
CategoryAI
Updated12h ago
Forks1

Languages

TypeScript

Security Score

92/100

Audited on Aug 7, 2026

1 low