Skip to main content
Glama
Sign In
Penthera: Cyber Security Agent

Penthera: Cyber Security Agent

by danoszz
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Local

Scan a running app (passive)

scan_url
Read-onlyIdempotent

Runs a passive black-box security scan of an authorized web app, checking TLS, headers, cookies, CORS, exposed files, OpenAPI, and auth without sending attack payloads.

Instructions

Passive black-box scan of a running web app the user is authorized to test: TLS, security headers, cookies, CORS, exposed files and docs, OpenAPI and auth checks. Sends no attack payloads: profile quick sends no login request, standard sends one POST /api/login with invalid credentials. Only loopback targets, or hosts the user listed with --allow-host when configuring this server, can be scanned, and a redirect off them is refused.

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": "scan_url"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYeshttp(s) URL of the app, e.g. http://localhost:3000
profileNoquick skips Retire.js and parameter discovery; standard is the full passive scan (default).
max_findingsNoHow many findings to return, most severe first (default 50).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.6/5.0
Behavior5/5

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

Goes well past the annotations by disclosing that no attack payloads are sent, that standard issues exactly one POST /api/login with invalid credentials while quick issues none, and that redirects off the allow-list are refused. The scope constraint (loopback only, or hosts listed via --allow-host) is precisely the kind of environment/auth context annotations cannot express.

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?

Front-loaded with the purpose, then side effects, then scope — a sensible order with no filler sentences. The scope sentence is long and clause-stacked, slightly taxing on a single read, but every clause carries operative information.

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 three-parameter, no-output-schema tool, the description covers purpose, side effects per profile, authorization, target allow-listing, and redirect behavior — everything needed to call it safely. Return-value shape is handled by the schema's max_findings ordering note, so nothing material is missing.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3, but the description adds real meaning the schema does not: it explains the behavioral consequence of the profile choice (login request sent or not), not just the feature delta. max_findings ordering and default are left to the schema, which is acceptable.

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

Purpose5/5

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

Names a specific verb and resource ('Passive black-box scan of a running web app') and enumerates the exact check families covered (TLS, headers, cookies, CORS, exposed files, OpenAPI, auth). The 'running web app' framing clearly separates it from a repository-oriented sibling like scan_repo without needing to name it.

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 a strong precondition (user must be authorized to test the target) and explains the quick-vs-standard choice by what each actually sends, which is exactly the decision an agent needs to make. It does not explicitly name an alternative tool or state when to reach for a different scan type, so it stops short of a full routing statement.

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