mcp-vision-bridge
updated this yearGive text-only LLM coding agents (DeepSeek V4 Flash/Pro, Qwen, Kimi) vision via any multimodal model. One analyze_image tool — paste or drag in one or many images, analyzed in a single call, scoped to the current session. Works with Claude Code, opencode,
Code-only MCP server: no hosted endpoint, so you install and run it yourself. It is not probed, graded or counted in our reachability statistics.
Get it
- Package
- npm: mcp-vision-bridge
- Run (stdio)
npx -y mcp-vision-bridgeThe usual command for this package registry; check the repository README for required settings.- License
- MIT
- Last update
- 2026-08-08
Adoption signals
Public signals from outside this directory, shown for context. They do not change search order or grades.
Listed in
- npm · source
Run this server as a hosted endpoint? Submit the endpoint and it moves to the remote directory, where it is probed and graded.