Skip to main content
Glama
123Ergo

unphurl-mcp

show_defaults

View the 25 default scoring signals with weights and descriptions to understand baseline URL risk assessment before customizing profiles.

Instructions

Show all 25 scoring signals with their default weights and descriptions. This is the baseline scoring that applies when no custom profile is specified.

Use this to understand what each signal means and how much it contributes to the score before creating custom profiles. Profiles are sparse overrides on top of these defaults.

This tool does not require an API key. The defaults are hardcoded and always available.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Implementation Reference

  • The show_defaults tool handler. Registers the tool with no input schema, and returns the hardcoded DEFAULT_SIGNALS array and DEFAULTS_NOTE string. No auth or API call required.
      // --- show_defaults ---
      // Fully hardcoded, no API call, no auth required
      server.registerTool(
        "show_defaults",
        {
          description: `Show all 25 scoring signals with their default weights and descriptions. This is the baseline scoring that applies when no custom profile is specified.
    
    Use this to understand what each signal means and how much it contributes to the score before creating custom profiles. Profiles are sparse overrides on top of these defaults.
    
    This tool does not require an API key. The defaults are hardcoded and always available.`,
          inputSchema: {},
        },
        async () => {
          return successResult({
            signals: DEFAULT_SIGNALS,
            note: DEFAULTS_NOTE,
          });
        }
      );
  • The tool is registered via server.registerTool('show_defaults', ...) within the registerProfileTools function.
      // --- show_defaults ---
      // Fully hardcoded, no API call, no auth required
      server.registerTool(
        "show_defaults",
        {
          description: `Show all 25 scoring signals with their default weights and descriptions. This is the baseline scoring that applies when no custom profile is specified.
    
    Use this to understand what each signal means and how much it contributes to the score before creating custom profiles. Profiles are sparse overrides on top of these defaults.
    
    This tool does not require an API key. The defaults are hardcoded and always available.`,
          inputSchema: {},
        },
        async () => {
          return successResult({
            signals: DEFAULT_SIGNALS,
            note: DEFAULTS_NOTE,
          });
        }
      );
  • DEFAULT_SIGNALS and DEFAULTS_NOTE constants: hardcoded array of all 25 signals with their default_weight and description, plus a note explaining profile behavior.
    // Hardcoded default scoring weights and signal descriptions
    // Used by show_defaults tool — no API call needed
    
    export const DEFAULT_SIGNALS = [
      {
        key: "brand_impersonation",
        default_weight: 40,
        description: "Domain name resembles a major brand (Levenshtein distance + homoglyph analysis against 150+ brands)",
      },
      {
        key: "domain_age_3",
        default_weight: 35,
        description: "Domain registered within the last 3 days",
      },
      {
        key: "domain_age_7",
        default_weight: 25,
        description: "Domain registered within the last 7 days",
      },
      {
        key: "domain_age_30",
        default_weight: 15,
        description: "Domain registered within the last 30 days",
      },
      {
        key: "domain_age_90",
        default_weight: 5,
        description: "Domain registered within the last 90 days",
      },
      {
        key: "ssl_invalid",
        default_weight: 10,
        description: "SSL/TLS certificate is missing, expired, or invalid",
      },
      {
        key: "http_only",
        default_weight: 5,
        description: "Site has no SSL/TLS at all (HTTP only)",
      },
      {
        key: "redirects_3",
        default_weight: 10,
        description: "URL has 3-4 redirects in the chain",
      },
      {
        key: "redirects_5",
        default_weight: 25,
        description: "URL has 5 or more redirects in the chain",
      },
      {
        key: "chain_incomplete",
        default_weight: 15,
        description: "Redirect chain could not be fully followed (timeout, blocked, or loop)",
      },
      {
        key: "parked",
        default_weight: 10,
        description: "Domain is parked (registrar placeholder, 'for sale' page, or parking service)",
      },
      {
        key: "compound",
        default_weight: 10,
        description: "3 or more signals detected together with at least one high-severity anchor (domain ≤30 days, 5+ redirects, invalid certificate, parked, or incomplete chain). The score breakdown names which signals contributed.",
      },
      {
        key: "brand_impersonation_floor",
        default_weight: 80,
        description: "Minimum score applied when brand impersonation is confirmed alongside a meaningful secondary signal. Structural signals like url_long or subdomain_excessive alone do not qualify.",
      },
      {
        key: "url_long",
        default_weight: 3,
        description: "URL is longer than 200 characters",
      },
      {
        key: "path_deep",
        default_weight: 3,
        description: "URL path has more than 4 segments",
      },
      {
        key: "subdomain_deep",
        default_weight: 3,
        description: "Domain has 2 subdomains",
      },
      {
        key: "subdomain_excessive",
        default_weight: 5,
        description: "Domain has 3 or more subdomains",
      },
      {
        key: "domain_entropy_high",
        default_weight: 5,
        description: "Domain name has high character entropy (random-looking)",
      },
      {
        key: "url_contains_ip",
        default_weight: 10,
        description: "URL uses an IP address instead of a domain name",
      },
      {
        key: "encoded_hostname",
        default_weight: 5,
        description: "Hostname contains percent-encoded characters",
      },
      {
        key: "tld_redirect_change",
        default_weight: 5,
        description: "TLD changed on redirect to a suspicious final TLD (e.g. .com→.xyz fires; .com→.ca does not)",
      },
      {
        key: "js_fragment_redirect",
        default_weight: 25,
        description: "HTML page on object storage (S3, GCS, Azure Blob) reads the URL fragment client-side and redirects the visitor to the decoded destination — a common phishing delivery technique",
      },
      {
        key: "expiring_soon",
        default_weight: 10,
        description: "Domain registration expires within 30 days",
      },
      {
        key: "domain_status_bad",
        default_weight: 15,
        description: "Domain has a bad status code (pendingDelete, serverHold, etc.)",
      },
      {
        key: "no_mx_record",
        default_weight: 5,
        description: "Domain has no MX record (cannot receive email)",
      },
    ] as const;
    
    export const DEFAULTS_NOTE =
      "Profiles override specific weights. Signals not in a profile use these defaults. 25 configurable signals plus suspicious_tld (+3 points) which is internal only and not configurable.";
  • Imports DEFAULT_SIGNALS and DEFAULTS_NOTE from src/defaults.ts, and imports successResult helper for formatting the response.
    // Profile tools — list, create, delete, and show defaults
    // Profiles are named weight sets that change how Unphurl scores URLs
    
    import type { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js";
    import { z } from "zod";
    import type { UnphurlAPI } from "../api.js";
    import { ApiRequestError } from "../api.js";
    import { DEFAULT_SIGNALS, DEFAULTS_NOTE } from "../defaults.js";
    import {
      successResult,
      authError,
      apiErrorToResult,
      errorResult,
    } from "./helpers.js";
  • src/index.ts:37-37 (registration)
    Top-level registration: registerProfileTools(server, api) is called from the main entry point, which wires up show_defaults among other profile tools.
    registerProfileTools(server, api); // list_profiles, create_profile, delete_profile, show_defaults
Behavior4/5

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

Discloses no API key required, hardcoded defaults always available, which is good for a read-only tool. No annotations provided, so description carries full burden.

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?

Three short, front-loaded sentences with no redundancy; every sentence adds value.

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?

Adequately covers purpose, usage context, and constraints for a parameterless tool; no output schema, but explanation of returned data suffices.

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?

No parameters; schema coverage 100%. Description adds meaning by specifying output content (25 signals, weights, descriptions) beyond schema.

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?

Description explicitly states 'Show all 25 scoring signals with their default weights and descriptions', clearly distinguishing from sibling tools like create_profile or check_url.

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?

Advises using before creating custom profiles and explains profiles are sparse overrides, but lacks explicit when-not-to-use or alternative tool names.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/123Ergo/unphurl-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server