SlopWatch is a Model Context Protocol (MCP) server that provides AI accountability tools.
{
"mcpServers": {
"slopwatch": {
"args": [
"slopwatch-mcp-server"
],
"command": "npx"
}
}
}Are you the author?
Add this badge to your README to show your security score and help users find safe servers.
Stop AI from lying about what it implemented! Track what AI claims vs what it actually does.
Is it safe?
No known CVEs for slopwatch-mcp-server.
No authentication — any process on your machine can connect.
License not specified.
Is it maintained?
Last commit 270 days ago. 6 stars. 6 weekly downloads.
Will it work with my client?
Transport: stdio, sse, http. Works with Claude Desktop, Cursor, Claude Code, and most MCP clients.
Context cost
5 tools. ~500 tokens (0.3% of 200K).
This server supports HTTP transport. Be the first to test it — help the community know if it works.
No known vulnerabilities.
slopwatch_claim_and_verifyClaim and verify an AI implementation in one call. Compares original and updated file contents against the claim to verify implementation.
slopwatch_claimRegister a claim before implementation. Returns a claim ID for later verification.
slopwatch_verifyVerify an implementation against a previously registered claim using the claim ID.
slopwatch_statusGet accountability statistics including accuracy score, claim count, and success rate.
slopwatch_setup_rulesGenerate a .cursorrules file for automatic SlopWatch enforcement across AI implementations.
Have you used this server?
Share your experience — it helps other developers decide.
Sign in to write a review.
Dynamic problem-solving through sequential thought chains
A Model Context Protocol server for searching and analyzing arXiv papers
An open-source AI agent that brings the power of Gemini directly into your terminal.
The official Python SDK for Model Context Protocol servers and clients
MCP Security Weekly
Get CVE alerts and security updates for SlopWatch and similar servers.
Start a conversation
Ask a question, share a tip, or report an issue.
Sign in to join the discussion.
Stop AI from lying about what it implemented! Track what AI claims vs what it actually does.
✨ 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
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.
Smithery handles hosting, authentication, and updates automatically
For Cursor IDE:
{
"mcpServers": {
"slopwatch": {
"command": "npx",
"args": ["slopwatch-mcp-server"]
}
}
}
Manual Cursor Setup:
Cmd+Shift+J on Mac, Ctrl+Shift+J on Windows)npx slopwatch-mcp-serverFor 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
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%)"
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%)"
| Tool | Description | Response |
|------|-------------|----------|
| slopwatch_claim_and_verify | ⭐ Recommended - Claim and verify in one call | ✅ PASSED (87%) |
| slopwatch_status | Get your accountability stats | Accuracy: 95% (19/20) |
| slopwatch_setup_rules | Ge