mcpnuke-checks

mcpnuke-checks is a cursor rule for Cursor from babywyrm/mcpnuke. It costs 0 tokens per session (544 once invoked), scanned A, original, MIT.

Rules for writing check modules and pattern files for mcpnuke, a tool that scans MCP server tools for specified patterns. They include templates for text-based and behavior-based checks.

In plain words
What is it for?
Use them when adding checks that inspect tool names or descriptions, detect patterns, test server behavior, record findings, or handle different connection types.
Why use it?
They keep new checks consistent and ensure they use the supported result and session interfaces.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/.

Good fit Use them when adding checks that inspect tool names or descriptions, detect patterns, test server behavior, record findings, or handle different connection types.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/babywyrm/mcpnuke/mcpnuke-checks
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/babywyrm/mcpnuke

Made for: Cursor.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for mcpnuke-checks

README.md
[![agentmods](https://agentmods.dev/badge/rules/babywyrm/mcpnuke/mcpnuke-checks.svg)](https://agentmods.dev/rules/babywyrm/mcpnuke/mcpnuke-checks)
Your own site
<a href="https://agentmods.dev/rules/babywyrm/mcpnuke/mcpnuke-checks"><img src="https://agentmods.dev/badge/rules/babywyrm/mcpnuke/mcpnuke-checks.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 544 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.00544
Opus 5 $0.00000 $0.00272
Sonnet 5 $0.00000 $0.00109
Haiku 4.5 $0.00000 $0.00054

Measured 8d ago against content hash 3c31871e9507, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

mcpnuke-checks scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.cursor/rules/mcpnuke-checks.mdc · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Check Module Conventions

Static Check Template

"""One-line description of what this check detects."""

import re
from mcpnuke.core.models import TargetResult
from mcpnuke.checks.base import time_check
from mcpnuke.patterns.rules import YOUR_PATTERNS


def check_your_check(result: TargetResult) -> None:
    with time_check("your_check", result):
        for tool in result.tools:
            name: str = tool.get("name", "")
            desc: str = tool.get("description", "")
            combined: str = f"{name} {desc} {tool.get('inputSchema', {})}"
            for pat in YOUR_PATTERNS:
                if re.search(pat, combined, re.IGNORECASE):
                    result.add("your_check", "SEVERITY", f"Title '{name}'", f"Detail: {pat}", evidence=combined[:300])
                    break

Behavioral Check Template

session is typed with MCPSessionProtocol from mcpnuke.core.transports.base. Rely only on what it declares — call, notify, close, wait_ready, protocol_mode. For anything HTTP-specific (post_raw), gate on hasattr(session, "post_raw"), because stdio has no header layer.

def check_your_check(
    session: MCPSessionProtocol,
    result: TargetResult,
    probe_opts: dict | None = None,
) -> None:
    opts: dict = probe_opts or {}
    _log = opts.get("_log", lambda msg: None)
    cache: dict = opts.get("_response_cache", {})
    with time_check("your_check", result):
        for tool in result.tools:
            name: str = tool.get("name", "")
            text: str | None = cache.get(name)
            if text is None:
                args = _build_safe_args(tool)
                resp = _call_tool(session, name, args)
                text = _response_text(resp)
            if text:
                # Analyze response
                pass

Wiring Checklist

  1. Import in checks/__init__.py
  2. Call in correct phase (static / behavioral / deep probe)
  3. Add attack chains to core/constants.py if applicable
  4. Add to README scan phases table
  5. Add to CHANGELOG

Read the full file on GitHub · 69 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 8d ago First seen · 69 lines · 0 tokens per session scan A 3c31871e9507

Subscribe to this mod's changes

mcpnuke-checks is a cursor rule published in the GitHub repository babywyrm/mcpnuke (2 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 544 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.