QV

quangthai/vision-bridge-mcp

Developer tools

このページは AI により自動翻訳されています。技術的な詳細は原文をご確認ください。 原文を見る

11 stars 2 forks 品質 72 トレンド 26MIT

MCP vision bridge for . Atlas reads local images, calls a dedicated vision provider, and returns markdown plus structured JSON evidence so agents can work from screenshots, diagrams, and UI mockups...

概要

MCP vision bridge for . Atlas reads local images, calls a dedicated vision provider, and returns markdown plus structured JSON evidence so agents can work from screenshots, diagrams, and UI mockups without native vision support. Many coding agents use text-only or weak-vision models. Developers still reference image paths, screenshots, mockups, and error captures — but the main model cannot see them reliably. Atlas uses a to decide whether a model needs vision bridge: replace hardcoded model lists — no updates needed when new models release: (cursor/, opencode-go/, opencode/*) route to arbitrary upstream models. Atlas resolves capabilities via: 1. Runtime signal from hooks (supports_vision, input_modalities) or pi (ctx.model.input) 2. Known proxy-native patterns (composer*, auto* → vision) — env overrides 3. Hook model field — wins over MAIN_MODEL_REF when the agent sends it 4. MAIN_MODEL_REF — fallback when hook model is unknown (avoid global export; use per-agent config) 5.

README

以下は原文 README の抜粋です。原文を見る。

Atlas Vision MCP

MCP vision bridge for text-only coding agents. Atlas reads local images, calls a dedicated vision provider, and returns markdown plus structured JSON evidence so agents can work from screenshots, diagrams, and UI mockups without native vision support.

Problem

Many coding agents use text-only or weak-vision models. Developers still reference image paths, screenshots, mockups, and error captures — but the main model cannot see them reliably.

How Atlas decides when to intercept

Atlas uses a multi-layer capability chain to decide whether a model needs vision bridge:

1. ctx.model.input (pi runtime)        → certain vision → skip
2. Hook supports_vision / input_modalities → runtime signal → skip or intercept
3. ATLAS_MODEL_CAPABILITIES_FILE       → user overrides
4. Proxy resolution (composer* patterns, hook model, MAIN_MODEL_REF fallback, upstream inference)
5. Provider heuristics (v0.4.0)        → openai/* = vision, deepseek/* = text-only
6. models.dev catalog                  → remote lookup
7. ATLAS_INTERCEPT_MODE                → policy fallback

Provider heuristics replace hardcoded model lists — no updates needed when new models release:

Provider ALL models have vision ALL models text-only
OpenAI (openai/*) ✅ GPT-4o, GPT-5, o3, … —
Anthropic (anthropic/*) ✅ Claude Sonnet, Opus, … —
Google (google/*) ✅ Gemini Pro, Flash, … —
DeepSeek (deepseek/*) — ✅ V4 Flash, V4 Pro, V3, R1
Z.ai / ZhipuAI (zai/*, alias zhipuai/*, glm/*) — ✅ GLM-5.1, 5.2, 4.x

Proxy providers (cursor/*, opencode-go/*, opencode/*) route to arbitrary upstream models. Atlas resolves capabilities via:

  1. Runtime signal from hooks (supports_vision, input_modalities) or pi (ctx.model.input)
  2. Known proxy-native patterns (composer*, auto* → vision) — before env overrides
  3. Hook model field — wins over MAIN_MODEL_REF when the agent sends it
  4. MAIN_MODEL_REF — fallback when hook model is unknown (avoid global export; use per-agent config)
  5. CURSOR_UNDERLYING_MODEL — alternative upstream override
  6. Upstream inference from model id prefix (gpt-* → openai, deepseek-* → deepseek, …)
  7. Safe default: intercept when unknown

Do not set MAIN_MODEL_REF globally if you switch between text-only models (Pi + DeepSeek) and vision models (Cursor Composer). Use per-agent config (~/.config/atlas-vision/env for Codex, project .env for Pi) or let hooks send the active model.

GitHub で README 全文を見る

インストール

npx atlas-vision-mcp config init
MCP 初心者?mcpskill.org のガイドから始めましょう →