Skip to content
New: AI verdicts in plain language.
Scampilot
For developers & AI integrators

Is-this-real? as an API & MCP.

JSON in, JSON out - shaped like the Safe Browsing you already call. Plus an MCP server so your AI agent can answer the same question. Stable contracts, no lawyer for the contract.

Open the API docs MCP server
v1 stablep95 4,8 s10 req/day per userOpenAPI 3.1
# Token aus Dashboard holen
export SCAMPILOT_TOKEN="sk_live_…"

# Nachricht analysieren
curl https://scampilot.de/api/v1/scan \
  -H "Authorization: Bearer $SCAMPILOT_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "content": "Ihr Konto wird in 24 Std…",
    "locale": "de"
  }'

# Strukturierte Antwort
{
  "verdict": "danger",
  "confidence": 94,
  "summary_plain": "Phishing-Versuch …",
  "actions": [...],
  "signals": [...],
  "model_used": "gpt-5-mini"
}
01
Four integration paths

Pick the one that fits.

Whether backend service, AI agent, browser user, or chat bot - one pipeline, four adapters.

REST API

Recommended

Bearer token, per-user-bucket rate limit, JSON body, auto-generated OpenAPI 3.1 spec.

POST /api/v1/scanGET /api/v1/reports

MCP server

For AI agents

Model Context Protocol - your Claude, Cursor, or Continue.dev sees Scampilot as a tool. HTTP transport.

scan_textscan_urlscan_email

Browser extension

Chrome MV3

Right-click on selected text, a link, or an image → check in the side panel. Answer without leaving the page, including QR-code detection on the page.

Telegram bot

Webhook-based

Building your own bot? Go via the REST API. Or link your users to @scampilot_bot with a /link code.

02
The REST API

One endpoint, one verdict.

Bearer token with abilities, OpenAPI 3.1, per-user bucket rate limit. We version via URL, not headers. The verdict enum is fixed at three values.

Request

POST /api/v1/scan HTTP/1.1
Authorization: Bearer sk_live_…
Content-Type: application/json
X-Request-ID: 9f2c1b3a-…

{
  "kind":    "email",
  "content": "From: support@spk-verify.io…",
  "locale":  "de",
  "hints": {
    "source_app": "my-extension"
  }
}

Response

HTTP/1.1 200 OK
X-Request-ID: 9f2c1b3a-…
X-RateLimit-Remaining: 117

{
  "id": "rpt_8f2a1c…",
  "verdict": "danger",
  "confidence": 94,
  "summary_plain": "Phishing-Versuch …",
  "actions": [
    { "icon": "❌", "text": "Klicke auf keinen Link." }
  ],
  "signals": [
    {
      "key": "credential_request",
      "severity": "high",
      "evidence": "„bestätigen Sie umgehend Ihr Passwort"
    }
  ],
  "model_used": "gpt-5-mini",
  "input_tokens": 1842,
  "output_tokens": 412
}
03
The MCP server

Phishing protection for your AI agent.

One of the first consumer-protection MCP servers. Tools for Claude, Cursor & co. - over HTTP. The agent decides on its own when to check a link.

Tool
scan_text - Check plain-text content.
Tool
scan_url - Check a single URL against reputation feeds.
Tool
scan_email - Full email including headers.
Tool
scan_image - Analyse a screenshot or image (OCR + vision).
Tool
list_my_recent_reports - Recent checks.
Prompt
explain_report_to_my_parent - Translate a report into plain language.
Resource
signals_glossary - What every signal key means.

Claude Desktop config

{
  "mcpServers": {
    "scampilot": {
      "transport": "http",
      "url": "https://scampilot.de/mcp/scampilot",
      "headers": {
        "Authorization": "Bearer sk_live_…"
      }
    }
  }
}
Quotas & limits

Predictable. Never surprising.

AuthenticationBearer token with per-token abilities (scan:create, reports:read).
Rate limit10 requests per day per user bucket. Multiple tokens share the bucket.
PayloadMax 64 KB per request. PDF / DOCX attachments via multipart, OCR before analysis.
WebhooksAsync for long analyses. Secret is a path suffix - rotatable.
OpenAPI 3.1

Spec live - always current.

The spec is generated from PHP annotations. No drift between docs and code. Clients can be generated in any language.

scampilot.de/docs/api
live
POST/api/v1/scan
GET/api/v1/reports
GET/api/v1/reports/{public_id}
DELETE/api/v1/reports/{public_id}
GET/health
openapi.json
04
Contracts

Built to be relied on.

Promises that live in the docs - not just on this marketing page.

OpenAPI 3.1

Live spec at /docs/api, generated from PHP annotations. No drift between docs and code - generate your own client in any language.

Stable versions

Versioned via the URL, not headers. The verdict enum is fixed at three values, signal keys are stable slugs. Deprecations are announced.

DPA without drama

EU hosting (Frankfurt & Falkenstein), a named subprocessor list, no model training on your content, no data resale.

X-Request-ID

Every request gets one. If you send one, we echo it. Logs, telemetry events, response headers - all correlated.

Structured errors

No stack traces in the body. {type, title, status, detail} per Problem Details (RFC 7807).

Heuristic fallback

If the AI provider is down, the heuristic answers. model_used = "heuristic-fallback". The client notices.

Token accounting

Per report: input_tokens, output_tokens, model_used. Costs per request precisely attributable.

24h URL cache

Google Safe Browsing and PhishTank are aggressively cached. You don't pay for identical URL checks.

Evidence fields

Every signal points to the exact spot in the input. You can show the end user the why.

05
Pricing

Pay only for what you check.

Personal use stays free. For production volume we bill per checked message - no seat licences, no minimums.

€5/ 1,000 checks

Beta anchor price. REST + MCP, the same engine as the app. Volume tiers on request.

Request access

Frequently asked questions

How do I call the Scampilot API?

JSON in, JSON out, authenticated with bearer tokens. There is an OpenAPI 3.1 spec; the API shares the daily quota with the web interface.

Is there an MCP server for AI agents?

Yes. The Model Context Protocol server offers tools such as scan_text, scan_url, scan_email, scan_qr and scan_links for agents like Claude - over HTTP or stdio.

What rate limits apply?

Anonymous calls are capped at 3 checks per day, registered at 10; for higher volumes there is the business tier.