data-breach-detector is a remote MCP server that gives an AI agent 7 tools, among them assess_threat, breach_history, breach_news. It answers at https://breach.seiche.info/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 6 of 6 times since 11 September 2026; the last check, on 21 October 2026, succeeded.
Read-only breach intel, full history 2007-today: reports THAT an org was breached, never the data.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
assess_threat | Classify a piece of security text you supply — an advisory, alert or forum post — into a threat level, matched categories, financial-target flags, a confidence score and a recommended action. Pure local analysis: it collects nothing, stores Inputs: text |
breach_history | Search the FULL historical breach archive — every incident this server knows about, back to 2007: HaveIBeenPwned's verified breach directory, the 2020-2025 ransomwatch leak-site archive (~16k victims), the RansomLook live tracker and SEC 8- Inputs: query, year_from, year_to, sector, data_type, min_accounts |
breach_news | Read recent breach and ransomware DISCLOSURES from public threat-intel feeds (HaveIBeenPwned, the RansomLook live leak-site tracker and SEC 8-K Item 1.05 filings), newest first. Every row is metadata only — entity, date, scale, exposed data Inputs: since_days, sector, source, limit, offset |
breach_stats | Aggregate the full breach archive into analyst-grade statistics: incidents and accounts exposed per year, per source, per exposed data type, per threat level, or per ransomware actor — plus the five largest incidents ever recorded. Use it t Inputs: group_by, sector, limit |
breach_timeline | Build the incident-by-incident CHRONOLOGY of one organization across every source and all history, with judgment on top: first and latest incident, incidents per year, whether the organization is a repeat victim, worst threat level and tota Inputs: entity, limit, offset |
check_exposure | Answer whether a domain, company or brand appears in public breach or ransomware DISCLOSURES across ALL history (2007 → today): yes/no with mention count, worst threat level, total accounts exposed across matches, the exposed data TYPES, an Inputs: query, since_days, limit, offset |
feed_sources | List the public disclosure feeds this server aggregates, how many disclosures are cached per source, each source's newest item and an honest staleness flag, plus cache ages. Takes no arguments. Also states the scope plainly: public feeds on |
Every block below points at https://breach.seiche.info/mcp. Pick your client and copy.
claude mcp add --transport http data-breach-detector https://breach.seiche.info/mcp
{
"mcpServers": {
"data-breach-detector": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://breach.seiche.info/mcp"]
}
}
}{
"mcpServers": {
"data-breach-detector": {
"url": "https://breach.seiche.info/mcp"
}
}
}{
"servers": {
"data-breach-detector": {
"type": "http",
"url": "https://breach.seiche.info/mcp"
}
}
}{
"context_servers": {
"data-breach-detector": {
"url": "https://breach.seiche.info/mcp"
}
}
}{
"mcpServers": {
"data-breach-detector": {
"serverUrl": "https://breach.seiche.info/mcp"
}
}
}{
"mcpServers": {
"data-breach-detector": {
"url": "https://breach.seiche.info/mcp"
}
}
}name: data-breach-detector
version: 0.0.1
schema: v1
mcpServers:
- name: data-breach-detector
type: streamable-http
url: https://breach.seiche.info/mcp{
"mcpServers": {
"data-breach-detector": {
"httpUrl": "https://breach.seiche.info/mcp"
}
}
}{
"mcpServers": {
"data-breach-detector": {
"type": "http",
"url": "https://breach.seiche.info/mcp"
}
}
}{
"mcpServers": {
"data-breach-detector": {
"url": "https://breach.seiche.info/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fbreach.seiche.info%2Fmcp&type=streamable_http&id=data-breach-detector&name=data-breach-detector
It answered our last check on 21 October 2026 in 67 ms. Over 6 checks since 11 September 2026 it answered 6. Status here comes from Neuronto's own probes, not from the publisher.
7, as returned by the server's own tools/list on 13 September 2026: assess_threat, breach_history, breach_news, breach_stats, breach_timeline, check_exposure, feed_sources.
It answered our last check on 21 October 2026 in 67 ms. Over 6 checks since 11 September 2026 it answered 6.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://breach.seiche.info/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: io.github.beepboop2025. Endpoint host: breach.seiche.info. ARD identifier: urn:air:io.github.beepboop2025:mcp:data-breach-detector.
First indexed 10 September 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.