Skip to main content
Glama

crumple_site

Read-only

Grades a deployed web app A to F for what a stranger can exploit — leaked keys, exposed source maps, missing CSP — and returns plain-English reasons plus code fixes to apply.

Instructions

Grade a deployed web app (built with Lovable, Bolt, v0, Replit, Emergent or by hand) A to F for what a stranger can use against it: secret keys shipped in its JavaScript, a Supabase service_role key in the browser, public source maps, no Content-Security-Policy. Each finding has a plain-English reason, what the owner must do by hand (like revoking a key), and a fix prompt to apply in the app's code. Call it again after fixing: change lists what got fixed. Reads only what the site serves to every visitor. Database checks (which Supabase tables or Firebase data anyone can read) need the owner, so tell them to run npx crumplelab site <url> --mine themselves.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "url": "<url>"
    },
    "name": "crumple_site"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYesThe app's address, for example myapp.lovable.app

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already declare readOnlyHint and openWorldHint, and the description adds substantive context beyond them: it reads only publicly served content, requires no owner credentials, and describes the shape of results (grade, plain-English reason, manual action, fix prompt, and a `change` diff on re-runs). No rate limits or pagination mentioned, but for a one-shot auditor that is minor.

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

Conciseness4/5

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

The purpose and scope lead the text, followed by result shape, re-run behavior, and the database exclusion. It is dense but nearly every clause carries information an agent needs; the framework list (Lovable, Bolt, v0, Replit, Emergent) is the one mildly expendable element.

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

Completeness4/5

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

With no output schema and a single trivial input, the description bears the burden of explaining returns and does so: findings carry a grade, a reason, a manual action, and a fix prompt, plus a `change` field on re-runs. It also clarifies the credential-free, public-surface-only nature of the read. Only minor gaps like finding ordering or count remain.

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?

There is only one parameter and the schema already documents it fully, including an example address, so coverage is 100% and the baseline of 3 applies. The description adds no syntax or format details beyond the schema's example; the `<url>` reference appears only in the CLI instruction.

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?

Names a specific verb and resource ('Grade a deployed web app ... A to F') and enumerates the concrete checks (shipped secret keys, service_role key in the browser, public source maps, missing CSP). It also delineates scope by excluding database checks, which implicitly separates it from broader scanning siblings, though no sibling is named explicitly.

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?

Gives clear when-to-use context (grading a deployed app after a build) and a re-run policy ('Call it again after fixing'). It also states an explicit when-not boundary: database table/Firebase exposure checks require the owner and must be run via the CLI, not this tool. Lacks direct routing to named sibling tools.

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