Skip to main content
Glama

breach_catalog

Search the public Have I Been Pwned breach catalogue by company, domain, or keyword to retrieve breach names, dates, record counts, data classes, and descriptions without individual email lookup.

Instructions

Search the public Have I Been Pwned breach catalogue by company, domain or keyword.

Keyless and safe for general research: returns breach names, dates, record counts, data classes and descriptions. It does not look up an individual email address. Use domain_only=True to match only the breached site's domain. limit is capped at 100. Results are cached for 24 hours.

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": "breach_catalog"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNo
queryNo
domain_onlyNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv2.0.0

TDQS

A4.3/5.0
Behavior4/5

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

With no annotations provided, the description carries the full burden and does well: it discloses that the tool is keyless (no auth required), that results are cached for 24 hours, and that the limit is capped at 100 — all non-obvious operational traits. It doesn't describe error behavior or what happens when the limit is exceeded, which keeps it from a 5.

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 purpose and scope, then layered with the exclusion, parameter hints, and caching note — each sentence adds distinct information. Slightly list-like in the back half, but nothing is redundant.

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 three-parameter read tool with no output schema, the description usefully enumerates what comes back (breach names, dates, record counts, data classes, descriptions), so the agent knows what to expect. Missing only edge-case behavior such as empty results or limit overflow.

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 description coverage is 0%, so the description must compensate and largely does: it explains 'domain_only' as restricting matches to the breached site's domain, explains 'limit' as capped at 100, and characterizes the query as a company, domain or keyword. Only 'query' lacks format or matching-rule detail (substring vs exact, case sensitivity).

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?

States a specific verb and resource ('Search the public Have I Been Pwned breach catalogue') plus the three axes of search (company, domain, keyword). It also draws the boundary against the email-lookup sibling by saying it does not look up an individual email address, which lets an agent route correctly without opening a schema.

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 context for use ('keyless and safe for general research') and an explicit exclusion ('does not look up an individual email address'), which implicitly routes email lookups to breach_check. It stops short of naming that alternative tool outright, so the guidance is strong but not fully self-contained.

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