CyberSafe MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CYBERSAFE_ML_MODEL | No | Optional HuggingFace model to use for local scam detection, e.g. Horizon-Labs/phishing-scam-detector-base. Defaults to mrm8488/bert-tiny-finetuned-sms-spam-detection. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| analyze_scam_messageA | Check a suspicious SMS, WhatsApp, email, or call script for scam red flags. Combines regional rule packs with an optional local HuggingFace AI scam model. Args: message: The exact text of the suspicious message or call script. channel: Where it arrived (e.g. 'SMS', 'WhatsApp', 'Email', 'Phone Call'). region: Regional scam pack to apply ('all', 'global', 'india', or 'us_uk'). |
| check_url_safetyA | Check whether a suspicious web link looks like a phishing or malware URL. Combines local heuristic checks with live abuse.ch URLhaus lookups (when URLHAUS_AUTH_KEY is set). Never visits or opens the submitted link. Args: url: The web link to inspect (for example, 'https://example.com/login'). |
| check_email_breachA | Check if an email address appeared in known public data breaches via XposedOrNot. Args: email: The email address to check (never logged or stored). |
| get_latest_alertsA | Get recent actively exploited security alerts from the free CISA KEV catalog in plain English. Args: limit: Number of alerts to return (1 to 15, default 5). consumer_only: If True, focuses on everyday devices & browsers (Apple, Google, Microsoft, etc.). keyword: Optional product or vendor filter (e.g. 'Chrome', 'iPhone', 'Windows'). |
| check_password_hygieneA | Check password strength locally in memory without logging or sending it anywhere. Tip: Test a similar pattern rather than pasting your real banking password. Args: password_sample: The password or sample pattern to evaluate. |
| get_daily_cyber_tipA | Get one short, jargon-free daily cybersecurity tip. Args: category: One of 'phone', 'laptop', 'ai', or 'general'. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| am_i_being_scammed | Guide the AI to calmly walk a user through checking a possible scam. |
| monthly_security_checkup | Run a friendly 5-minute monthly security checkup for a phone or laptop. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| guides_index | List all available plain-language cybersecurity playbooks. |
| scam_packs_index | List all loaded regional scam rule packs and AI model status. |
TDQS
Scored across 6 tools
Each tool targets a clearly distinct artifact: a URL, an email address, a message transcript, a threat feed, a password, and a daily tip. There is no overlap in inputs or purpose, so an agent can select the right tool from the input type alone.
All six tools follow a consistent snake_case verb_noun pattern (check_url_safety, get_latest_alerts, analyze_scam_message, etc.). The check_/analyze_/get_ prefixes are all conventional verb forms and remain predictable across the set.
Six tools is well-scoped for a consumer cybersecurity helper; each tool covers a distinct check with no redundancy. Nothing feels padded or missing at the structural level.
The surface covers the core consumer safety checks: link, email breach, message scam, vulnerability alerts, password, and tips. Minor gaps exist for adjacent checks such as IP/domain reputation or phone-number breach lookup, but agents can work around them.