hebrew-scam-shield-mcp
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
Hebrew Scam Shield ๐ก๏ธ
Explainable scam and phishing detection for Hebrew messages (SMS, WhatsApp, e-mail). Zero dependencies, a command-line tool, a Python library, and an MCP server so AI assistants can check messages for you.
Fake "your parcel is held" texts, fake government and bank alerts, fake emergency-app links: these messages reach everyone, but they hurt most the people who are least likely to have help at hand: elderly people, new internet users, and communities that are under-served by mainstream security tools. Most scam filters are built for English. Hebrew Scam Shield is built for Hebrew, and every verdict comes with a plain-language reason, so the person (or the assistant) can understand why a message looks dangerous.
Quick start
pip install "hebrew-scam-shield[mcp] @ git+https://github.com/benziRaz/hebrew-scam-shield"
hebrew-scam-shield "ืืืืจ ืืฉืจืื: ืืืืืื ืฉืื ืื ื ืืชื ืช ืืืกืืจื. ืืฉืจ ืืชืืืช ืชืื 12 ืฉืขืืช http://israelpost-il.top/x"HIGH RISK (score 90/100)
+25 Claims a parcel/delivery problem (address, payment, customs) - a very common lure.
+15 Creates artificial urgency or threatens a deadline.
+15 Link uses a top-level domain that is rarely used by genuine services. [http://israelpost-il.top/x]
+5 Link is not encrypted (http). [http://israelpost-il.top/x]
+30 Domain contains a known brand/institution name but is not that organisation's domain. [http://israelpost-il.top/x]Use --lang he for Hebrew explanations and --json for machine-readable output. Exit codes: 0 low, 1 suspicious, 2 high.
As a library
from hebrew_scam_shield import analyze
result = analyze(message_text)
result.level # "low" | "suspicious" | "high"
result.score # 0-100
result.reasons # list of Reason(id, weight, en, he, detail)As an MCP server (for Claude and other assistants)
{
"mcpServers": {
"hebrew-scam-shield": { "command": "hebrew-scam-shield-mcp" }
}
}The server exposes one tool, check_message(text). Ask your assistant: "Is this message a scam?" and paste the text.
Related MCP server: ScamCheck MCP Server
What it looks for
Signal | Example |
Parcel / customs / address problem | "ืืืืืื ืื ื ืืชื ืช ืืืกืืจื, ืืฉืจ ืืชืืืช" |
Artificial urgency | "ืชืื 12 ืฉืขืืช", "ืืืจืช ืืืฉืืื ืืืืกื" |
Government / bank impersonation with an account problem | "ืคืขืืืืช ืืจืืื ืืืฉืืื" + link |
Requests for verification codes, passwords, card data | "ืืื ืืช ืงืื ืืืืืืช" |
Fake emergency or "security update" app installs | "ืืืจื ืืช ืืืคืืืงืฆืื" |
Prize and voucher lures | "ืืืืช ืืฉืืืจ" |
Wallet-linking tricks | "ืืงืฉืจ Apple Pay ืืฉืืจืืจ ืืืืืื" |
"Reply Y to activate the link" | "ืืฉื Y" |
Suspicious links | shorteners, look-alike brand domains, odd TLDs, raw IPs, |
Evasion | zero-width characters, niqqud |
Rules live in rules.py as readable data (weight + English/Hebrew explanation + regex groups). Sources are listed in docs/PATTERNS.md.
Honest limitations
It is a heuristic, not a guarantee. A low score does not prove a message is safe; a high score does not prove it is malicious.
Rules are public, so determined scammers can study them. Use this as one layer of defence, not the only one.
The list of official domains is short and non-exhaustive. Pull requests that add verified domains are very welcome.
It was built from public warnings, not from a private corpus of real messages, so expect false positives and gaps.
Not affiliated with the Israel National Cyber Directorate. If you receive a suspicious message in Israel, you can report it to the national 119 hotline.
Contributing
New scam patterns, official domains and false-positive reports are the most valuable contributions. See CONTRIBUTING.md. Never paste real personal data into issues: redact names, phone numbers and ID numbers first.
pip install -e ".[mcp,dev]"
pytestLicense: MIT
ืขืืจืืช
ืืืืื ืืื ืืืช ืืืืืขืืช ืคืืฉืื ื ืืขืืจืืช, ืขื ืืกืืจ ืืื ืืืืื. ืืืื ืขืืื ืขื SMS, ืืืืืกืืค ืืืืื, ืืื ืชืืืืืช ืืืฆืื ืืืช, ืืืืืข ืืฉืืจืช ืคืงืืื, ืืกืคืจืืื ืืคืืืชืื ืืืฉืจืช MCP ืฉืืืคืฉืจ ืืขืืืจื AI ืืืืืง ืืืืขืืช ืขืืืจื.
ืืืืขืืช ืขื "ืืืืื ืฉื ืชืงืขื", ืืชืจืืืช ืืืืืคืืช ืืืื ืง ืื ืืืืืื ื ืืงืืฉืืจืื ืืืคืืืงืฆืืืช ืืืจืื ืืืืืคืืช ืืืืขืืช ืืืืื, ืืื ืื ืืง ืืืื ืืืืืื ืืฆื ืื ืฉืืื ืืืื ืื ืฉืืขืืืจ: ืงืฉืืฉืื, ืืืืฉืื ืืืฉืื ืืงืืืืืช ืฉืืื ืืืืืื ืืจืืืืื ืื ืื ืืืื ืืฉืืืื. ืจืื ืืืกื ื ืื ื ืืชืื ืืื ืืืืช. ืืืื ืืื ื ืื ื ืืขืืจืืช, ืืื ืชืืฆืื ืืืืื ืืืกืืจ ืืจืืจ ืืื ืืืืืขื ื ืจืืืช ืืกืืื ืช.
ืืชืงื ื ืืฉืืืืฉ
pip install "hebrew-scam-shield[mcp] @ git+https://github.com/benziRaz/hebrew-scam-shield"
hebrew-scam-shield --lang he "ืืืืจ ืืฉืจืื: ืืืืืื ืฉืื ืื ื ืืชื ืช ืืืกืืจื. ืืฉืจ ืืชืืืช ืชืื 12 ืฉืขืืช http://israelpost-il.top/x"ืงืื ืืฆืืื: 0 ืกืืืื ื ืืื, 1 ืืฉืื, 2 ืกืืืื ืืืื.
ืืืืืืช
ืื ืืขืจืื ืืคื ืืืืื ืืื ืืืืืช. ืฆืืื ื ืืื ืื ืืืืื ืฉืืืืืขื ืืืืื, ืืฆืืื ืืืื ืื ืืืืื ืฉืืื ืืืื ืืช.
ืืืืืื ืคืืืืืื, ืืืื ื ืืืืื ื ืืืฉืื ืืืืืื ืืืืื ืืืชื. ืืืื ืืืฉืชืืฉ ืืืื ืืืืช ืืฉืืืืช ืืืื ื ืืื ืืฉืืื ืืืืื.
ืจืฉืืืช ืืืืืืื ืื ืืจืฉืืืื ืงืฆืจื ืืืืงืืช. ืชืืกืคืืช ืืืืืชืืช ืืชืงืืื ืืืจืื.
ืืืื ืื ืงืฉืืจ ืืืขืจื ืืกืืืืจ ืืืืืื. ืื ืฉืงืืื ืืืืขื ืืฉืืื ืืืฉืจืื ืืืื ืืืืื ืืงื 119.
ืชืจืืื ืืคืจืืืงื
ืืคืืกื ืืื ืื ืืืฉืื, ืืืืืื ืื ืจืฉืืืื ืืืืืชืื ืืืืืืืื ืขื ืืชืจืืืช ืฉืืื ืื ืืชืจืืื ืืื ืืฉืืื. ืคืจืืื ื-CONTRIBUTING.md. ืื ืชืืืืงื ืืืืข ืืืฉื ืืืืชื ื-issues: ืืืงื ืฉืืืช, ืืืคืื ืื ืืืกืคืจื ืืืืช.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelogโฆ
This server cannot be deployed
Maintenance
Related MCP Connectors
AI-powered scam and threat verification for phone numbers, URLs, texts, and emails.
Scam and phishing detection for AI agents: safe/warn/danger verdicts for URLs and messages.
Scan suspicious messages, URLs, and text for scams with AI. Free tier - no API key required.
AI-powered scam detection for suspicious texts, emails, and screenshots. US-focused.
Related MCP Servers
- AlicenseAqualityDmaintenanceAI-powered threat verification across 6 channels: phone numbers, URLs, text messages, emails, documents, and QR codes. Analyzes threats against 10M+ intelligence records from FTC, FCC, URLhaus, ThreatFox, and community reports, returning risk scores, verdicts, and detailed signals.101MIT
- AlicenseAqualityCmaintenanceScans suspicious messages, URLs, and text for scams inside any MCP-compatible AI assistant. No signup or API key needed for anonymous use.160 npmMIT
- AlicenseNot gradedqualityBmaintenanceEnables AI assistants to autonomously detect scams by checking URLs, messages, ABNs, and phone numbers using Australian-specific threat intelligence and privacy-preserving techniques.MIT
- AlicenseAqualityBmaintenanceEnables AI assistants to check whether a crypto token, link, or forwarded "gem" message is a scam by running contract rules, live test trades, creator history, and market data across 64 networks, returning plain-English or Pidgin verdicts. Also supports scanning messages, reviewing a token's past checks, and explaining individual findings.5MIT