@triedotdev/mcp 1.0.37 → 1.0.39

package/dist/workers/agent-worker.js

@@ -1,6 +1,6 @@
 import {
   getAgentRegistry
-} from "../chunk-QFTSX2BX.js";
+} from "../chunk-B3MBKB2U.js";
 import "../chunk-3CS6Z2SL.js";
 import "../chunk-OB45V2QC.js";
 import "../chunk-IMFD4SJC.js";

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@triedotdev/mcp",
-  "version": "1.0.37",
+  "version": "1.0.39",
   "description": "Intelligent Agent Orchestration for AI Coding Tools",
   "main": "dist/index.js",
   "type": "module",
@@ -73,7 +73,6 @@
   "homepage": "https://trie.dev",
   "files": [
     "dist",
-    "README.md",
-    "QUICK_START.md"
+    "README.md"
   ]
 }

package/QUICK_START.md

@@ -1,228 +0,0 @@
-# Quick Start Guide
-
-Get Trie Agent up and running in minutes to start scanning and reviewing AI-generated code.
-
-## Prerequisites
-
-- **Node.js 18+** installed ([download](https://nodejs.org/))
-- **AI coding tool** (Cursor, Claude Code, or VS Code with MCP support)
-
-## Installation
-
-### Step 1: Install Trie Agent
-
-```bash
-npm install -g @triedotdev/mcp
-```
-
-### Step 2: Configure Your AI Tool
-
-No API key required! Trie uses your AI tool's built-in Claude to do the analysis.
-
-## Configuration
-
-### For Claude Code
-
-Use the `claude` CLI to add the MCP server:
-
-```bash
-claude mcp add Trie -- npx @triedotdev/mcp
-```
-
-Or add to `~/.claude/settings.json`:
-
-```json
-{
-  "mcpServers": {
-    "Trie": {
-      "command": "node",
-      "args": ["/usr/local/lib/node_modules/@triedotdev/mcp/dist/index.js"]
-    }
-  }
-}
-```
-
-### For Cursor
-
-1. Open Cursor Settings → MCP Servers
-2. Add this configuration:
-
-```json
-{
-  "mcpServers": {
-    "Trie": {
-      "command": "node",
-      "args": ["/usr/local/lib/node_modules/@triedotdev/mcp/dist/index.js"]
-    }
-  }
-}
-```
-
-**Note:** If installed globally, the path might be different. Find it with:
-```bash
-npm list -g @triedotdev/mcp
-```
-
-### For VS Code
-
-Add to your VS Code settings (`.vscode/settings.json` or user settings):
-
-```json
-{
-  "mcp.servers": {
-    "Trie": {
-      "command": "node",
-      "args": ["/usr/local/lib/node_modules/@triedotdev/mcp/dist/index.js"]
-    }
-  }
-}
-```
-
-## Usage
-
-### Scan Your Code
-
-Once configured, use Trie Agent in your AI coding tool:
-
-**In Cursor/Claude Code:**
-```
-Scan this code with Trie Agent
-```
-
-**Or use the MCP tool directly:**
-```
-Use trie_scan to analyze the current file
-```
-
-### Example Workflow
-
-1. **Generate code** with your AI assistant
-2. **Scan for issues:**
-   ```
-   Scan this with Trie Agent
-   ```
-3. **Review results** - Trie will show:
-   - Risk level and activated agents
-   - Critical issues requiring review
-   - Suggested fix prompts for AI
-   - Plain-language explanations
-4. **Fix issues:**
-   ```
-   Apply the suggested fixes for the critical issues
-   ```
-5. **Generate tests:**
-   ```
-   Generate tests for this code
-   ```
-
-## Available Tools
-
-- **`trie_scan`** - Scan code with intelligent agent selection
-- **`trie_fix`** - Generate high-confidence fix prompts
-- **`trie_explain`** - Get plain-language explanations of code/issues
-- **`trie_test`** - Generate tests or check coverage
-- **`trie_watch`** - Monitor files for changes and report issues
-- **`trie_register_agent`** - Add custom agents
-
-## Example Output
-
-```
-🔍 TRIE AGENT SCAN
-━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
-
-Smart Triaging:
-✓ Risk Level: high
-✓ Reason: High-risk authentication feature
-✓ Agents activated: security, privacy, legal, architecture, typecheck
-✓ Execution time: 8.2s
-
-Results:
-Score: 72/100 (needs work)
-
-🔴 2 Critical Issues (require your review)
-🟡 3 Serious Issues
-🔵 2 Moderate Issues
-
-Critical Issues Preview:
-1. Password stored without hashing (auth/signup.ts:23)
-   Agent: Security | Confidence: 100%
-2. PII stored in plain text (models/user.ts:15)
-   Agent: Privacy | Confidence: 95%
-```
-
-## Configuration (Optional)
-
-Create `.trie/config.json` in your project root to customize behavior:
-
-```json
-{
-  "version": "1.0",
-  "triaging": {
-    "enabled": true,
-    "riskThresholds": {
-      "critical": 70,
-      "high": 40,
-      "medium": 20
-    }
-  },
-  "agents": {
-    "builtin": {
-      "security": { "enabled": true },
-      "privacy": { "enabled": true },
-      "legal": { "enabled": true },
-      "accessibility": { "enabled": true }
-    }
-  }
-}
-```
-
-## Troubleshooting
-
-### Agent not found
-
-**Problem:** Can't find the Trie Agent executable
-
-**Solution:** Find the installation path:
-```bash
-npm list -g @triedotdev/mcp
-# Or
-npx @triedotdev/mcp --help
-```
-
-Update your MCP config with the correct path.
-
-### No agents activating
-
-**Problem:** Scan runs but no agents are triggered
-
-**Solution:**
-- Check that your code matches patterns (auth, payments, UI, etc.)
-- Review the triaging logic in `.trie/config.json`
-- Try scanning a file with known issues (auth, payments, etc.)
-
-### MCP connection fails
-
-**Problem:** Can't connect to Trie Agent server
-
-**Solution:**
-1. Verify Node.js is installed: `node --version` (should be 18+)
-2. Check the path in MCP config is correct
-3. Restart your AI coding tool
-4. Check console/logs for error messages
-
-## Next Steps
-
-- **Try different code patterns** - Test with auth, payments, UI components
-- **Explore agents** - See which agents activate for different code types
-- **Generate tests** - Create comprehensive test suites
-- **Add custom agents** - Extend Trie with your own review logic
-
-## Support
-
-- 📚 **Documentation**: [trie.dev/docs](https://trie.dev/docs)
-- 🐛 **Issues**: [GitHub Issues](https://github.com/Trie-OS/Trie-Agent/issues)
-- 💬 **Community**: [Discord](https://discord.gg/trie-ai)
-
----
-
-**Ready to ship safer code?** Start scanning your AI-generated code now! 🚀