Enables auditing of backend code that targets ClickHouse: scans files for anti-patterns like SELECT *, interpolated SQL, missing LIMITs, and N+1 queries in loops, returning deterministic PASS/FAIL with findings.
Enables auditing of backend code that targets PostgreSQL: scans files for anti-patterns like SELECT *, interpolated SQL, missing LIMITs, and N+1 queries in loops, returning deterministic PASS/FAIL with findings.
Enables auditing of backend code that targets Redis: scans files for anti-patterns like N+1 Redis calls in loops, missing timeouts, and other backend slop, returning deterministic PASS/FAIL with findings.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@backend-unslop-mcp audit src/api/users.ts for backend slop and fix any violations"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Stop AI-generated APIs and SQL from shipping as naive slop: skill + MCP verifier for PostgreSQL, ClickHouse, Redis and workers.
An agent skill plus an MCP server in one package. The skill tells your coding agent what Backend slop to avoid; the MCP tools then deterministically verify the result, so the agent can't just claim it's done.
Works with Claude Code, Claude Desktop, Codex and Antigravity.
Rule | Severity | Catches |
| ERROR |
|
| ERROR |
|
| ERROR | DB, Redis or HTTP calls awaited inside |
| ERROR | empty or |
| ERROR |
|
| ERROR |
|
| ERROR | unfinished |
The skill additionally requires input validation at every boundary, explicit LIMITs, timeouts and idempotent retries, and offloading work over ~2s to a queue.
Rules marked ERROR make the audit return status: "FAIL"; WARN is reported but does not fail.
Related MCP server: ui-assert
# Claude Code
claude mcp add backend-unslop -s user -- npx -y backend-unslop-mcp
# Codex
codex mcp add backend-unslop -- npx -y backend-unslop-mcpClaude Desktop (~/Library/Application Support/Claude/claude_desktop_config.json) and Antigravity (~/.gemini/antigravity/mcp_config.json):
{
"mcpServers": {
"backend-unslop": {
"command": "npx",
"args": ["-y", "backend-unslop-mcp"]
}
}
}Restart the app afterwards.
npx -y backend-unslop-mcp install-skillsCopies backend-unslop into:
Client | Location |
Claude Code |
|
Codex |
|
Antigravity |
|
Claude Desktop has no skills folder, so it receives the rules through the MCP prompt and the load_*_rules tool described below. Or install straight from this repo's skills/ directory.
Kind | Name | Purpose |
Prompt |
| The full skill text, for GUI clients |
Tool |
| Returns the skill text (for clients without prompt support) |
Tool |
| Scans |
Tool |
| Runs |
Audit output:
{
"status": "FAIL",
"totalViolations": 1,
"findings": [
{ "file": "src/a.ts", "line": 12, "rule": "NO_TYPE_ESCAPE", "severity": "ERROR", "message": "…", "snippet": "…" }
],
"instruction": "Refactor every ERROR finding and re-run the audit before completing the task."
}File paths are resolved against the server's working directory and cannot escape it.
The agent loads the skill and writes code under its constraints.
Before finishing, the skill requires a call to audit_backend_slop and verify_typescript_compile.
On FAIL, the agent fixes every finding and re-runs until PASS.
The checks are regex based: fast, offline and predictable, but heuristic. Expect the occasional false positive and treat them as a safety net, not a substitute for review.
frontend-unslop-mcp: the same idea for React, Next.js and Tailwind.
git clone https://github.com/fikrifirmanf/backend-unslop-mcp
cd backend-unslop-mcp && npm install
node src/server.mjs # speaks MCP over stdioMIT © Fikri Firman Fadilah
This server cannot be deployed
Enforces architectural invariants and code quality rules inside your AI agent's edit loop.
Statically audits MCP tool surfaces for token cost, schema quality, and design issues.
Stateless TS/JS compiler facts for agents: references, imports, impact. No repo index or OAuth.
Lets coding agents check their own code for leaked secrets, risky dependencies and AI-code mistakes
