Have I Been Pwned

Have I Been Pwned - Paste Account

hibp_get_paste_account

Read-onlyIdempotent

Search for public pastes containing a single email address. Requires an OAuth bearer token linked to an active HIBP API subscription; run this separately from breached-account lookup.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`limit`	No	Maximum number of items to include in the response. Defaults to 25.
`offset`	No	Number of items to skip before returning results. Defaults to 0.
`account`	Yes	The email address to search for pastes.
`response_format`	No	Format only the text content as markdown (default) or a JSON string. The same machine-readable data is always returned in structuredContent.	markdown

Output Schema

TableJSON Schema

Name	Required	Description
`limit`	No
`offset`	No
`pastes`	No
`account`	No
`hasMore`	No
`message`	No	Present when the tool returns an error.
`guidance`	No	Additional guidance for resolving the tool error.
`nextOffset`	No
`statusCode`	No	Present when the tool returns an error.
`totalCount`	No
`returnedCount`	No
`rateLimitResetAt`	No	UTC timestamp indicating when the current rate limit window should have reset.
`retryAfterHeaders`	No	Retry headers that mirror the standard HTTP rate-limit response when applicable.
`retryAfterSeconds`	No	How long to wait before retrying, when the tool is rate limited.

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedSep 2, 2026
- removedOutput schema / properties / pastes / items / properties / Date / anyOf
```
Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]
```
- addedOutput schema / properties / pastes / items / properties / Date / type
```
Added value: +[
+  "string",
+  "null"
+]
```
- removedOutput schema / properties / pastes / items / properties / Title / anyOf
```
Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]
```
- addedOutput schema / properties / pastes / items / properties / Title / type
```
Added value: +[
+  "string",
+  "null"
+]
```

Changed3 schema fields changedAug 27, 2026

changedInput schema / $schema

Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"

changedInput schema / properties / response_format / description

Previous value: -"Format the text response as markdown (default) or JSON. structuredContent is always returned."New value: +"Format only the text content as markdown (default) or a JSON string. The same machine-readable data is always returned in structuredContent."

changedOutput schema / $schema

Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"

First observedJul 23, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds value by disclosing the auth dependency on a bearer token and active subscription, and by warning to run this separately from breached-account lookup. It does not discuss rate limits or response quirks, but those are not heavily needed given the output schema.

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?

Two sentences with no filler. The first sentence front-loads the core action and resource; the second adds the critical auth prerequisite and a usage differentiator. Every phrase earns its place.

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 read-only search tool with a 100%-covered input schema, an output schema, and informative annotations, the description adds the one missing operational context: authentication requirements and the recommendation to keep this call separate from breached-account lookup. Nothing necessary for correct invocation is missing.

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 description coverage is 100%, so the schema already documents account, limit, offset, and response_format. The description's 'single email address' reinforces the account parameter but does not add meaningful detail beyond the schema. With full schema coverage, the baseline of 3 is appropriate.

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 states a specific verb ('Search'), a specific resource ('public pastes'), and a specific scope ('containing a single email address'). It also differentiates itself from the breached-account lookup sibling, so an agent can distinguish it from at least one closely related operation.

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 explicitly tells the agent to run this separately from breached-account lookup, which provides a clear exclusion. It also states the OAuth/subscription prerequisite. It does not mention when to choose this over stealer-logs-by-email or other email-related tools, but the paste-specific scope makes the intended context reasonably clear.

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

All Have I Been Pwned 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.

Resources

Need Help?