A
securityA
licenseA
qualityEnables AI agents to break down complex tasks into manageable pieces using a structured JSON format with task tracking, context preservation, and progress monitoring capabilities.
Last updated -
15
49
6
MIT License
Provides tracking and verification of Express.js middleware implementations, including features like rate limiting for API endpoints
Mentioned as a planned roadmap feature for commit verification integration
Provides issue tracking, documentation and community discussion functionality through GitHub repositories
Offers verification capabilities for React component implementations, including tracking of responsive design and styling changes
🎯 SlopWatch - AI Accountability MCP Server
Stop AI from lying about what it implemented! Track what AI claims vs what it actually does.
🚀 What's New in v2.7.0
✨ Ultra-Minimal Responses - 90% less verbose output
🔄 Combined Tool - Single call instead of 2 separate tools
⚡ Seamless Workflow - Perfect for AI pair programming
🎯 Cursor MCP Compatible - Works seamlessly with Cursor IDE
🤔 Why SlopWatch?
Ever had AI say "I've added error handling to your function" but it actually didn't? Or claim it "implemented user authentication" when it just added a comment?
SlopWatch catches AI lies in real-time.
⚡ Quick Start
🎯 Option 1: Smithery (Easiest - 1 click install)
Click "Install to Cursor" or "Install to Claude"
Done! ✨
Smithery handles hosting, authentication, and updates automatically
🔧 Option 2: NPM Direct (Manual Setup)
For Cursor IDE:
{
"mcpServers": {
"slopwatch": {
"command": "npx",
"args": ["slopwatch-mcp-server"]
}
}
}
Manual Cursor Setup:
Open Cursor Settings (
Cmd+Shift+Jon Mac,Ctrl+Shift+Jon Windows)Go to Features → Model Context Protocol
Click "Add New MCP Server"
Configure:
Name: SlopWatch
Type: stdio
Command:
npx slopwatch-mcp-server
For Claude Desktop:
Add to your claude_desktop_config.json:
{
"mcpServers": {
"slopwatch": {
"command": "npx",
"args": ["slopwatch-mcp-server"]
}
}
}
Global NPM Install:
npm install -g slopwatch-mcp-server
🎮 How to Use
Method 1: Combined Tool (Recommended ⭐)
Perfect for when AI implements something and you want to verify it:
// AI implements code, then verifies in ONE call:
slopwatch_claim_and_verify({
claim: "Add input validation to calculateSum function",
originalFileContents: {
"utils/math.js": "function calculateSum(a, b) { return a + b; }"
},
updatedFileContents: {
"utils/math.js": "function calculateSum(a, b) {\n if (typeof a !== 'number' || typeof b !== 'number') {\n throw new Error('Invalid input');\n }\n return a + b;\n}"
}
});
// Response: "✅ PASSED (87%)"
Method 2: Traditional 2-Step Process
For when you want to claim before implementing:
// Step 1: Register claim
slopwatch_claim({
claim: "Add error handling to user login",
fileContents: {
"auth.js": "function login(user) { return authenticate(user); }"
}
});
// Response: "Claim ID: abc123"
// Step 2: Verify after implementation
slopwatch_verify({
claimId: "abc123",
updatedFileContents: {
"auth.js": "function login(user) {\n try {\n return authenticate(user);\n } catch (error) {\n throw new Error('Login failed');\n }\n}"
}
});
// Response: "✅ PASSED (92%)"
🛠️ Available Tools
Tool | Description | Response |
| ⭐ Recommended - Claim and verify in one call |
|
| Get your accountability stats |
|
| Generate .cursorrules for automatic enforcement | Minimal rules content |
🎯 Cursor IDE Integration
SlopWatch is designed specifically for Cursor IDE and AI pair programming:
Automatic Detection
Detects when AI claims to implement features
Automatically suggests verification
Integrates seamlessly with Cursor's Composer
Smart Workflow
1. AI: "I'll add error handling to your function"
2. SlopWatch: Automatically tracks the claim
3. AI: Implements the code
4. SlopWatch: Verifies implementation matches claim
5. Result: ✅ PASSED (92%) or ❌ FAILED (23%)
Perfect for:
Code reviews - Verify AI actually implemented what it claimed
Pair programming - Real-time accountability during development
Learning - Understand what AI actually does vs what it says
Quality assurance - Catch implementation gaps before they become bugs
💡 Real-World Examples
Example 1: API Endpoint Enhancement
// AI says: "I'll add rate limiting to your API endpoint"
slopwatch_claim_and_verify({
claim: "Add rate limiting middleware to /api/users endpoint",
originalFileContents: {
"routes/users.js": "app.get('/api/users', (req, res) => { ... })"
},
updatedFileContents: {
"routes/users.js": "const rateLimit = require('express-rate-limit');\nconst limiter = rateLimit({ windowMs: 15*60*1000, max: 100 });\napp.get('/api/users', limiter, (req, res) => { ... })"
}
});
// Result: ✅ PASSED (94%)
Example 2: React Component Update
// AI claims: "Added responsive design with CSS Grid"
slopwatch_claim_and_verify({
claim: "Make UserCard component responsive using CSS Grid",
originalFileContents: {
"components/UserCard.jsx": "const UserCard = () => <div className=\"user-card\">...</div>"
},
updatedFileContents: {
"components/UserCard.jsx": "const UserCard = () => <div className=\"user-card grid-responsive\">...</div>",
"styles/UserCard.css": ".grid-responsive { display: grid; grid-template-columns: repeat(auto-fit, minmax(300px, 1fr)); gap: 1rem; }"
}
});
// Result: ✅ PASSED (89%)
📊 Accountability Stats
Track your AI's honesty over time:
slopwatch_status();
// Returns: "Accuracy: 95% (19/20)"
Accuracy Score: Percentage of claims that were actually implemented
Claim Count: Total number of implementation claims tracked
Success Rate: How often AI delivers what it promises
🔧 Advanced Configuration
Auto-Enforcement with .cursorrules
Generate automatic accountability rules:
slopwatch_setup_rules();
This creates a .cursorrules file that automatically enforces SlopWatch verification for all AI implementations.
Custom Verification
SlopWatch analyzes:
File changes - Did the files actually get modified?
Code content - Does the new code match the claim?
Implementation patterns - Are the right patterns/libraries used?
Keyword matching - Does the code contain relevant keywords?
🚀 Why Choose SlopWatch?
For Developers:
Catch AI lies before they become bugs
Learn faster by seeing what AI actually does
Improve code quality through automatic verification
Save time with streamlined accountability
For Teams:
Standardize AI interactions across team members
Track AI reliability over time
Reduce debugging from AI implementation gaps
Build trust in AI-assisted development
For Cursor Users:
Native integration with Cursor's Composer
Seamless workflow - no context switching
Real-time feedback during development
Ultra-minimal responses - no verbose output
🎯 Getting Started with Cursor
Install SlopWatch using one of the methods above
Open Cursor and start a new chat with Composer
Ask AI to implement something: "Add input validation to my function"
Watch SlopWatch work: It automatically tracks and verifies the claim
Get instant feedback: ✅ PASSED (87%) or ❌ FAILED (23%)
🔍 Troubleshooting
Common Issues:
Tools not showing: Restart Cursor after installation
Verification failed: Check if files were actually modified
NPM errors: Try
npm cache clean --forceand reinstall
Debug Mode:
Enable detailed logging by setting DEBUG=true in your environment.
📈 Roadmap
Visual dashboard for accountability metrics
Integration with Git for commit verification
Team analytics for multi-developer projects
Custom verification rules for specific frameworks
IDE extensions for other editors
🤝 Contributing
We welcome contributions! Please see our Contributing Guide for details.
📝 License
MIT License - see LICENSE for details.
🌟 Support
GitHub Issues: Report bugs or request features
Documentation: Full docs and examples
Community: Join the discussion
Made with ❤️ for the Cursor community
Stop AI from lying about what it implemented. Start using SlopWatch today!
An AI accountability system that tracks what AI systems claim they will implement versus what they actually deliver, helping to reduce the gap between promises and reality.
Related MCP Servers
- AsecurityFlicenseAqualityAn AI-powered goal management system that transforms traditional goal tracking into storytelling, helping users focus on one goal at a time with personalized narratives and insights that increase motivation and achievement.Last updated -25117
- -securityFlicense-qualityA task tracking and backlog management tool that enables AI assistants to create, organize, and track issues and tasks with status workflow through MCP protocol.Last updated -1
- -securityAlicense-qualityA comprehensive AI-powered fitness tracking application that enables AI tools to interact intelligently with user fitness data, providing personalized workout plans, nutrition tracking, and progress analysis through natural language.Last updated -2MIT License