Skip to main content
Glama

crumple_scan

Read-only

Audit AI coding agent setups locally to find exposed secrets, risky configs, hooks, and vulnerable MCP packages, returning a 0-100 Safe Setup score with fixes.

Instructions

Audit an AI coding agent setup (Claude Code, Codex, Gemini CLI, Cursor, MCP config, hooks, CLAUDE.md/AGENTS.md, .env exposure) the way an attacker would. Local and instant: no key, no Docker, nothing leaves the machine. Returns a 0-100 Safe Setup score and findings, each with why it matters and the fix. With cves: true it also checks the MCP servers it finds (npx/uvx packages) against published vulnerabilities on osv.dev, sending only package names and versions.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "crumple_scan"
  }
}

Input Schema

NameRequiredDescriptionDefault
cvesNoAlso check MCP server packages against osv.dev (goes online; sends only package names and versions).
pathNoProject folder to scan. Defaults to the server's working directory.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.3/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the readOnlyHint annotation, the description explains that nothing leaves the machine by default, that a 0-100 Safe Setup score and findings are returned, and that enabling cves goes online while sending only package names and versions. This adds substantial behavioral context about privacy, network behavior, and output.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with the core purpose, followed by key guarantees and the optional cves behavior. It is dense but every sentence adds useful information, with no redundant or filler wording.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a security audit tool with no output schema, the description covers what is scanned, local privacy guarantees, the optional online vulnerability check and its data exposure, and the returned score and findings. This is sufficient for an agent to invoke the tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so both cves and path are already documented. The description reinforces the cves behavior and privacy implications, but does not add much meaning beyond the schema, and it does not mention the path parameter.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource: auditing an AI coding agent setup covering Claude Code, Codex, Gemini CLI, Cursor, MCP config, hooks, CLAUDE.md/AGENTS.md, and .env exposure. It is clear what the tool does, though it does not explicitly differentiate itself from the sibling tools crumple_site and crumple_traps.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives clear usage context by describing the audit target and noting that the scan is local and instant with no key or Docker. It does not explicitly state when not to use it or name alternatives, but the intended use case is well defined.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools