Fraud patterns a message or call resembles in Kenya and Nigeria, and where to report.
Scored across 3 tools
The three tools map to clearly separate intents: evaluating a specific message, browsing the catalogue of described fraud patterns, and finding reporting channels. Descriptions explicitly delimit what each does and does not do, leaving little room for misselection.
All three names follow the same namespaced verb_noun pattern (check_message, list_patterns, where_to_report) in consistent snake_case. The shared africa_scams prefix reinforces predictability.
Three tools is on the lean side, but each covers a genuinely distinct step of the user journey (diagnose, learn, report) with no filler. Slightly thin for the domain but well scoped rather than padded.
The surface covers the full advisory loop: matching a suspicious message, enumerating known patterns with sourced guidance, and pointing to reporting channels with next steps. Gaps are minor, e.g. no way to query beyond Kenya/Nigeria or get deeper per-pattern detail beyond the listed descriptions.
Use this when someone in Kenya or Nigeria shares a text, a WhatsApp message, an email or an account of a phone call about mobile money, a bank, a prize, a job, an investment, a loan or a request for money, and wants to know which known fraud patterns it resembles. It returns the patterns the wording resembles, what the bodies that describe them say to do, and where to report, each with its source. It does not judge the message: say so, and never tell someone a message is fine because nothing matched. Do not use it for other countries, for legal advice, or to decide whether to pay. Leave any PIN, password or one-time code out of what you pass to it.
Inputs: country (required), message (required). Returns: limits, country, read_on, report_to, +4 more
Use this when someone asks which frauds the banks, mobile networks and public bodies of Kenya or Nigeria have described, or how a named one works (for example a fake reversal instruction, a one-ring call from abroad, or a message about your BVN). Do not use it for other countries, and do not present the list as complete: it covers patterns that were found described on the bodies' own pages. Do not use it to decide whether a message is fine.
Inputs: country (required), pattern. Returns: limits, country, read_on, patterns, +2 more
Use this when someone in Kenya or Nigeria asks where to report fraud on a phone, a bank account or mobile money, or what the banks and authorities say to do after money or details have gone to a fraudster. It gives the reporting channels the bodies publish and the steps they give, each with its source. Do not use it for other countries or for legal advice, do not suggest that money will be recovered, and leave any PIN, password or one-time code out of what you pass to it.
Inputs: country (required), money_already_sent. Returns: steps, limits, country, read_on, +2 more
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Compares a message with fraud patterns reported in Ghana and says where to report.
Customer-care and complaints numbers in Kenya and Nigeria, each read on the body's own website.
Check a suspicious email, SMS, WhatsApp message or link for scam signals (Netherlands, Belgium).
AI-powered scam detection for suspicious texts, emails, and screenshots. US-focused.
Add one secure layer between your agents and this server.