@triedotdev/mcp 1.0.16 → 1.0.17

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (2) hide show
  1. package/README.md +9 -8
  2. package/package.json +1 -1
package/README.md CHANGED
@@ -138,7 +138,7 @@ VIOLATIONS DETECTED: 47 instances across 6 categories
138
138
 
139
139
  ## Visual QA Browser
140
140
 
141
- **Screenshot-based visual testing** - Captures your app at 3 viewports and uses Claude Vision to analyze for visual bugs.
141
+ **Screenshot-based visual testing** - Captures your app at 3 viewports and returns images for your AI model to analyze.
142
142
 
143
143
  ```
144
144
  Use trie_visual_qa_browser
@@ -149,9 +149,9 @@ Use trie_visual_qa_browser url:"http://localhost:3000"
149
149
  1. Auto-detects running dev server (checks ports 3000, 5173, 8080, etc.)
150
150
  2. Launches headless Playwright browser
151
151
  3. Captures screenshots at mobile (375px), tablet (768px), and desktop (1440px)
152
- 4. Returns images for Claude Vision to analyze
152
+ 4. Returns images for your AI model to analyze
153
153
 
154
- **What Claude Vision checks:**
154
+ **What gets analyzed:**
155
155
  - Broken layouts, overlapping elements
156
156
  - Responsive design issues
157
157
  - Color contrast and accessibility
@@ -168,12 +168,13 @@ Use trie_visual_qa_browser url:"http://localhost:3000"
168
168
 
169
169
  **First run:** If Playwright browsers aren't installed, run: `npx playwright install chromium`
170
170
 
171
- **Vision model required:** This tool returns screenshots for the LLM to analyze. Works best with:
172
- - Cursor (Claude has vision)
173
- - Claude Code (native vision support)
174
- - OpenCode with Claude/GPT-4V
171
+ **Vision model required:** This tool returns screenshots as images. Your AI model must support vision to analyze them:
172
+ - **Claude** (Opus, Sonnet, Haiku 3.5+) - Full vision support
173
+ - **GPT-4o, GPT-4V** - Full vision support
174
+ - **Gemini Pro/Ultra** - Full vision support
175
+ - **Models without vision** - Will receive images but cannot analyze them
175
176
 
176
- No API key needed - Trie runs locally and the AI tool's built-in model does the analysis.
177
+ Works in Cursor, Claude Code, and OpenCode - whichever model you have configured. No API key needed; Trie runs locally.
177
178
 
178
179
  ## YOLO Mode
179
180
 
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@triedotdev/mcp",
3
- "version": "1.0.16",
3
+ "version": "1.0.17",
4
4
  "description": "Intelligent Agent Orchestration for AI Coding Tools",
5
5
  "main": "dist/index.js",
6
6
  "type": "module",