Hibp

Check Account

check_account

Read-onlyIdempotent

Look up breaches an email account has been seen in. REQUIRES a paid HIBP subscription key (pass _apiKey). Returns the set of breach names; combine with get_breach for details.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`account`	Yes	Email address
`truncate`	No	Return only breach names (default true). Set false for full breach objects (counts as 1 query).

Output Schema

TableJSON Schema

Name	Required	Description
`pwned`	Yes	Whether account found in any breaches
`account`	Yes	Email address checked
`breaches`	No	Full breach objects (when truncate=false)
`breach_names`	No	Breach names (when truncate=true)

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedMay 22, 2026

addedInput schema / examples

Added value: +[
+  {
+    "_apiKey": "your-hibp-api-key",
+    "account": "user@example.com"
+  },
+  {
+    "_apiKey": "your-hibp-api-key",
+    "account": "john.doe@company.com",
+    "truncate": false
+  }
+]

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "account": {
+      "description": "Email address checked",
+      "type": "string"
+    },
+    "breach_names": {
+      "description": "Breach names (when truncate=true)",
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "breaches": {
+      "description": "Full breach objects (when truncate=false)",
+      "items": {
+        "properties": {
+          "added_date": {
+            "description": "Date added to HIBP",
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "breach_date": {
+            "description": "Date breach occurred",
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "data_classes": {
+            "description": "Types of data exposed",
+            "items": {
+              "type": "string"
+            },
+            "type": "array"
+          },
+          "description": {
+            "description": "Detailed breach description",
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "domain": {
+            "description": "Primary domain affected",
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "is_fabricated": {
+            "description": "Whether breach is fabricated",
+            "type": [
+              "boolean",
+              "null"
+            ]
+          },
+          "is_malware": {
+            "description": "Whether malware was involved",
+            "type": [
+              "boolean",
+              "null"
+            ]
+          },
+          "is_retired": {
+            "description": "Whether breach is retired",
+            "type": [
+              "boolean",
+              "null"
+            ]
+          },
+          "is_sensitive": {
+            "description": "Whether breach is sensitive",
+            "type": [
+              "boolean",
+              "null"
+            ]
+          },
+          "is_spam_list": {
+            "description": "Whether this is a spam list",
+            "type": [
+              "boolean",
+              "null"
+            ]
+          },
+          "is_verified": {
+            "description": "Whether breach is verified",
+            "type": [
+              "boolean",
+              "null"
+            ]
+          },
+          "logo_path": {
+            "description": "Path to breach logo image",
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "modified_date": {
+            "description": "Last modification date",
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "name": {
+            "description": "Unique breach name",
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "pwn_count": {
+            "description": "Number of affected accounts",
+            "type": [
+              "number",
+              "null"
+            ]
+          },
+          "title": {
+            "description": "Human-readable breach title",
+            "type": [
+              "string",
+              "null"
+            ]
+          }
+        },
+        "required": [
+          "name",
+          "title",
+          "domain",
+          "breach_date",
+          "added_date",
+          "modified_date",
+          "pwn_count",
+          "description",
+          "data_classes",
+          "is_verified",
+          "is_fabricated",
+          "is_sensitive",
+          "is_retired",
+          "is_spam_list",
+          "is_malware",
+          "logo_path"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "pwned": {
+      "description": "Whether account found in any breaches",
+      "type": "boolean"
+    }
+  },
+  "required": [
+    "account",
+    "pwned"
+  ],
+  "type": "object"
+}

First observedMay 11, 2026

TDQS

A4/5.0

Behavior3/5

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false. The description adds the requirement of an API key and the return format (breach names), but does not disclose potential rate limits or other behavioral traits. With annotations covering safety, a score of 3 is appropriate.

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?

The description is two sentences, front-loading the purpose and critical requirements. Every sentence adds value without redundancy.

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?

Given the presence of annotations and output schema (not shown but noted), the description provides adequate context about return value and usage. It could mention pagination or error cases, but overall it's sufficient.

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?

The input schema has 100% coverage with descriptions for both parameters. The description reiterates the API key requirement and mentions truncate behavior implicitly, but does not add significant new semantic meaning beyond the 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?

The description clearly states 'Look up breaches an email account has been seen in', which is a specific verb+resource. There are sibling tools like check_password and get_breach, and this definition effectively distinguishes itself by focusing on breaches for an email account.

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?

The description provides explicit guidance: 'REQUIRES a paid HIBP subscription key (pass _apiKey)' and recommends combining with get_breach for details. It does not explicitly state when not to use, but the context is clear enough for an agent to decide.

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

All Hibp tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.