Skip to main content
Glama
CyberSafe MCP

CyberSafe MCP

by kshitij9896

check_url_safety

Inspect a suspicious web link for phishing or malware indicators using local heuristics and live URLhaus lookups without visiting the URL.

Instructions

Check whether a suspicious web link looks like a phishing or malware URL.

Combines local heuristic checks with live abuse.ch URLhaus lookups (when URLHAUS_AUTH_KEY is set). Never visits or opens the submitted link.

Args: url: The web link to inspect (for example, 'https://example.com/login').

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": "check_url_safety"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYes

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.0

TDQS

A3.7/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does well: it discloses the two-tier approach (local heuristics plus live abuse.ch URLhaus lookups), the conditional dependency on URLHAUS_AUTH_KEY, and the critical safety property that the link is never visited or opened. It stops short of mentioning rate limits, latency, or what happens when the auth key is absent.

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 core behavior and the key safety guarantee are front-loaded in the first two sentences, and the Args block is compact. The parenthetical about URLHAUS_AUTH_KEY is well placed rather than buried, with little wasted wording.

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?

For a one-parameter tool with an output schema, the description supplies the behavioral context an agent needs: what it inspects, how, and that it never fetches the target. The only real gap is the absence of any hint about verdict semantics or behavior when the optional lookup key is unset.

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 coverage is 0%, so the description must compensate for the single 'url' parameter. The inline example ('https://example.com/login') establishes the expected full-URL format, but there is no guidance on scheme requirements, length limits, or whether non-HTTP schemes are accepted.

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 opens with a specific verb and resource ('Check whether a suspicious web link...') and narrows the scope to phishing/malware URLs. It is clearly distinct from the email, password, and message-oriented siblings, though it never explicitly contrasts itself with them.

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

Usage Guidelines3/5

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

Calling it on a 'suspicious web link' implies the triggering condition, so the when-to-use case is inferable. There is no explicit when-not guidance, no statement about what to do for non-URL artifacts, and no reference to alternatives such as the message-analysis sibling.

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