XposedOrNot MCP Server Live

776 data breaches and more than 11.5 billion exposed records indexed, as of August 2026.

Give your AI assistant live access to data breach intelligence. Query the XposedOrNot breach database directly from Claude, Cursor, or any MCP-compatible client. Free, open source, no API key required.

New to MCP? The Model Context Protocol is an open standard that lets AI assistants call external tools. Connect this server once, and your assistant can answer breach questions with live data instead of guesses.

Get started

Quick start

Claude Code

One command in your terminal:

claude mcp add --transport http xposedornot https://api.xposedornot.com/mcp

Claude Desktop

Go to Settings, then Connectors, then Add custom connector and enter:

Name: XposedOrNot URL: https://api.xposedornot.com/mcp

Cursor

Add the server to ~/.cursor/mcp.json (or via Settings, then MCP, then Add new server):

{ "mcpServers": { "xposedornot": { "url": "https://api.xposedornot.com/mcp" } } }

Any MCP client

  • Server endpoint: https://api.xposedornot.com/mcp
  • Transport: streamable HTTP (JSON-RPC 2.0 over HTTPS POST)
  • Protocol version: 2024-11-05
  • Authentication: none required

To confirm the connection, ask your assistant: "What XposedOrNot tools do you have available?" It should list the six tools below.

Available tools

The server exposes six tools covering emails, domains, the breach catalog, and live statistics.

check_email_breaches

Check whether an email address appears in any known data breach. Returns breach names, dates, and exposed data types.

"Has john@example.com appeared in any data breaches?"

get_breach_analytics

Detailed exposure analytics for an email: risk score, breach timeline, exposed data categories, and password risk.

"Give me a full breach risk analysis for john@example.com."

list_breaches

Browse or filter the full breach catalog by domain or breach ID, with records, data classes, and verification status.

"List the breaches XposedOrNot has indexed for example.com."

domain_breach_summary

Aggregate breach summary for a domain: breach count, affected accounts, pastes, and the most recent breach date. Returns counts only, never individual addresses.

"How exposed is example.com across known breaches?"

get_breach_metrics

System-wide statistics: total breaches and records indexed, breaches per year and industry, and the largest and most recent breaches.

"How many breaches were indexed per industry this year?"

get_recent_breaches

The latest data breach news and the breaches most recently added to the XposedOrNot database.

"What are the newest data breaches tracked by XposedOrNot?"

See it in action

Ask your assistant:

Check if john@example.com has been in any data breaches, and summarize what was exposed.

Your AI assistant calls check_email_breaches, receives live results from the XposedOrNot database, and answers with the actual breaches, dates, and exposed data types, not guesses from training data. An answer typically looks like this (illustrative):

john@example.com appears in 3 known breaches: 1. ExampleCorp (2023): email addresses, passwords (bcrypt), names 2. SampleShop (2021): email addresses, phone numbers 3. DemoForum (2019): email addresses, plaintext passwords Highest risk: DemoForum exposed plaintext passwords. If that password is reused anywhere, change it now and enable two-factor authentication.

Follow-up questions like "which of those exposed passwords?" reuse the same live data.

Rate limits and access

The MCP server is free for personal and development use and shares the community API's per-IP limits. When a limit is reached, the server returns a clear message rather than failing silently.

Free tier rate limits per IP address for MCP tools
Tools Burst Per hour Per day
check_email_breaches, get_breach_analytics 2 per second 25 100
list_breaches, get_recent_breaches 2 per second 50 100
domain_breach_summary 2 per second 25 50
get_breach_metrics 5 per minute 50 100

Need higher volume? xonAPI+ offers paid plans with rate limits up to 25,000 requests per minute, API-key access, and commercial support. Full details in the API documentation.

Privacy

Only the queried email address or domain is sent, over TLS, to api.xposedornot.com. XposedOrNot does not store user passwords or personally identifiable information from searches, and domain_breach_summary returns only counts, never individual addresses. The server is open source: verify how queries are handled in the source code or read the privacy policy.

Discovery for agents

Agents and registries can discover the server and its tools automatically through two published machine-readable descriptors:

Frequently asked questions

Is it really free?

Yes. The MCP server uses the free, keyless XposedOrNot community API. If you need higher throughput for a product or a busy team, xonAPI+ offers paid plans with much higher limits, and that is what keeps the free tier free.

Do I need an API key?

No. Point your MCP client at https://api.xposedornot.com/mcp and it works. No account, no key, no registration.

Which clients work?

Any MCP client that supports streamable HTTP transport, including Claude Desktop, Claude Code, and Cursor. The server speaks standard JSON-RPC over HTTPS with protocol version 2024-11-05 and requires no authentication.

Are the email addresses I query stored?

Only the queried email address or domain is sent over TLS, and it is used to answer the lookup. XposedOrNot does not store user passwords or personally identifiable information from searches. See the privacy policy for details.

How is this different from the REST API?

Same data, different consumer. The REST API is for code you write; the MCP server wraps the same breach database in tools an AI assistant can call directly, so your assistant answers breach questions with live data.

How current is the data?

The MCP server queries the live XposedOrNot database: 776 breaches and more than 11.5 billion exposed records as of August 2026, updated as new breaches are verified and indexed. See live repository statistics.

Go deeper