MCP.Market

Hibp MCP server

by darrenjrobinson·io.github.darrenjrobinson/hibp·v1.1.0·5 stars

A Model Context Protocol (MCP) server for the Have I Been Pwned (HIBP) API

B83/100grade B
What users say
No reviews yet
Be the first
Safety scan
B83/100

full report

Adoption
Growing

5 stars34 downloads/wk

Reviews

Write one

Nobody has reviewed Hibp yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Hibp tools (3)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • HIBP-Breaches

    Tool to query breached accounts and breaches from the Have I Been Pwned API

  • HIBP-Pastes

    Tool to query pastes containing account data from the Have I Been Pwned API

  • HIBP-PwnedPasswords

    Tool to check if a password has been exposed in data breaches using the Pwned Passwords API

Public scan report

scanner v0.1.10 · 2026-10-15 · same rubric, same numbers if you re-run it

no findings
  • Code scan4 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitystatic API keys via environment variables6/15
  • Maintenancelast push 2 days ago15/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 83/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Hibp compares

Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
83/100
higher than 68% of 4,461 AI and agents servers
Tools
3
the typical AI and agents server has 6
Tools that change things
0%
typical: 0%. Fewer write tools means less an agent can break
GitHub stars
5
more than 78% of 2,713 AI and agents servers
Downloads a week
34
more than 22% of 1,554 AI and agents servers with a package

What its tools let an agent do: 3 read

Release history: 2 versions in the registry since 2026-09-07, latest 2026-10-14, typically one every 37 days.

Install Hibp in Claude Code, Cursor or VS Code

Runs npx -y @darrenjrobinson/hibp-mcp on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add hibp -- npx -y @darrenjrobinson/hibp-mcp
Add to Cursor

What the publisher says

From the Hibp repository's README, as published. We do not edit it. Read it on GitHub

Have I Been Pwned MCP Server

A Model Context Protocol (MCP) server for the Have I Been Pwned (HIBP) API that allows you to query breach data using natural language.

Overview

This MCP server provides tools to interact with the Have I Been Pwned API, allowing you to:

  • Check if an email address has been in a data breach
  • Get details about specific breaches
  • Check if a password has been exposed in known data breaches
  • Check if an email address appears in pastes

GitHub Repo

NPM Package

Blog

Your browser does not support the video tag.

Installation & Configuration

Option 1: NPM Installation (Recommended)

  1. Install Node.js (v22.10.0 or higher recommended)
  2. Get your HIBP API key from https://haveibeenpwned.com/API/Key
  3. Configure your MCP client (e.g., Claude Desktop ) with:
{
  "mcpServers": {
    "HIBP-MCP": {
      "command": "npx",
      "args": ["-y", "@darrenjrobinson/hibp-mcp"],
      "env": {
        "HIBP_API_KEY": "<your-hibp-api-key>",
        "HIBP_SUBSCRIPTION_PLAN": "Pwned 1"
      }
    }
  }
}

Option 2: Local Development

  1. Clone this repository:
git clone https://github.com/darrenjrobinson/HIBP-MCP-Server.git
  1. Install dependencies:
cd HIBP-MCP-Server
npm install
  1. Build the project:
npm run build
  1. Configure your MCP client with:
{
  "mcpServers": {
    "HIBP-MCP": {
      "command": "node",
      "args": ["path/to/hibp-mcp/build/main.js"],
      "env": {
        "HIBP_API_KEY": "<your-hibp-api-key>",
        "HIBP_SUBSCRIPTION_PLAN": "Pwned 1"
      }
    }
  }
}

Environment Variables

Usage Examples

Once configured, you can ask Claude natural language questions about data breaches. Here are some examples:

Checking Email Breaches

  • "Has email address test@example.com appeared in any data breaches?"
  • "What breaches contain the email address test@example.com?"
  • "Show me all breaches for test@example.com"

Checking Specific Breaches

  • "Tell me about the LinkedIn data breach"
  • "What data was exposed in the Adobe breach?"
  • "List all known data breaches"

Checking Passwords

  • "Has the password 'Password123' been exposed in any breaches?"
  • "Is my password 'MySecurePass2024' safe to use?"
  • "Check if this password has been compromised: 'TestPass1234'"

Checking Pastes

  • "Has test@example.com appeared in any pastes?"
  • "Show me paste data for test@example.com"

Tools

HIBP-Breaches

Query breached accounts and breaches from the Have I Been Pwned API.

Parameters:

  • operation: The HIBP operation to perform (getAllBreachesForAccount, getAllBreachedSites, getBreachByName, getDataClasses)
  • account: Email address to check for breaches (required for getAllBreachesForAccount)
  • domain: Domain to filter breaches by (optional)
  • name: Breach name to get details for (required for getBreachByName)
  • includeUnverified: Whether to include unverified breaches (optional)
  • truncateResponse: Whether to truncate the response (optional)

HIBP-Pastes

Query pastes containing account data from the Have I Been Pwned API.

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Hibp: common questions

Is Hibp MCP server safe?
Mostly: it is graded B (83/100). Read the Hibp safety report
How do I install Hibp?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Hibp need an API key?
Yes. The registry entry asks for HIBP_API_KEY.
Is Hibp maintained?
The last commit was 23 days ago (2026-10-14). The latest release is v1.1.0.
How does Hibp compare with other AI and agents MCP servers?
safety score 83/100 (higher than 68% of 4,461 AI and agents servers); tools 3 (the typical AI and agents server has 6); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

More from darrenjrobinson →