Bewary: scam, phishing and fraud detection
Server Details
Bewary is a scam detection API and MCP server for apps and AI agents: phishing, fraud and threat intelligence lookups an agent runs before it opens a link, calls a number, pays or replies. It checks links and domains (phishing, domain age, lookalike brands), IP addresses, phone numbers (FTC and FCC complaints), SMS short codes, email addresses, crypto wallets (scam reports, OFAC sanctions), IBANs, mobile apps and payment handles. Each answer is a typed verdict (scam, suspicious, safe or unknown) with the facts and reason codes behind it, built from evidence rather than a language model. Watches send an event when a watched domain, number, wallet or brand changes. A free key gets 1,000 credits a month with no card; OAuth sign-in is supported.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-06-18
- URL
- Server Listing
- bewary
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 15 tools
Each lookup_* tool targets a clearly distinct entity type (app, domain, email, IBAN, IP, payment handle, phone, shortcode, URL, wallet), and watch/unwatch/list_events/list_watches are cleanly separated by resource and lifecycle. related_domains is distinguishable from lookup_domain as a pivoting tool rather than a direct reputation check.
The set is mostly built on predictable list_* and lookup_* verb_noun prefixes, which makes scanning easy. Minor deviations are related_domains, which is not verb_noun, and the bare watch/unwatch pair, though both remain clear.
With 15 tools, the server sits at the upper end of a well-scoped set without feeling bloated. Each tool covers a distinct lookup category or watch lifecycle operation, so the count is appropriate for a fraud-checking service.
The surface covers a broad range of fraud-relevant entity lookups plus relationship discovery and watch/event lifecycle management. Minor gaps exist around explicit reporting, account/credit management, or bulk lookup operations, but core workflows are covered.
Publisher details
- Operator
- Reply200 Inc. · Publisher source
- Operator website
- https://bewary.app · Publisher source
- Vendor relationship
- First-party · Publisher source
- Documentation
- https://bewary.app/mcp · Publisher source
- Privacy policy
- Not provided
- Trust center
- Not available
- Restrictions
- Every call needs a Bewary API key or an OAuth sign-in. A free key gets 1,000 credits a month with no card; a lookup costs 1 credit. · Publisher source
Available Tools
15 toolslist_eventsRead eventsARead-onlyIdempotentInspect
Events of the account's watches, oldest first. Keep next_cursor and pass it as cursor to read only what came after. Cost: free; API key required.
Inputs: limit, types, cursor, watch_id. Returns: events, has_more, next_cursor
list_watchesList watchesARead-onlyIdempotentInspect
Every live watch on the account. Cost: free; API key required.
Inputs: no named parameters. Returns: watches
lookup_appLook up a mobile appARead-onlyInspect
Is this app live on the Apple App Store or Google Play, or did the store pull it? Name, developer, rating count and when we first and last saw it live. Cost: 1 credit.
Inputs: store (required), app_id (required), storefront. Returns: p_scam, verdict, degraded, entities, +3 more
lookup_domainLook up a domainBRead-onlyInspect
Domain age, lookalike-brand technique, abused TLD, blocklist status and a verdict. Cost: 1 credit, deep 30.
Inputs: domain (required), deep. Returns: p_scam, verdict, degraded, entities, +3 more
lookup_emailLook up an email addressCRead-onlyInspect
Mail server, disposable or free provider, role mailbox, and the sender domain's facts. Cost: 1 credit.
Inputs: address (required). Returns: p_scam, verdict, degraded, entities, +3 more
lookup_ibanLook up an IBANARead-onlyInspect
Is this IBAN valid (country length and structure, check digits), which bank does it belong to (name, BIC), and did a community report name it? Pass the country the payee claims to catch a mismatch. Cost: 1 credit.
Inputs: iban (required), claimed_country. Returns: p_scam, verdict, degraded, entities, +3 more
lookup_ipLook up an IP addressCRead-onlyInspect
Network owner, ASN, country, hosting type, reverse DNS. Cost: 1 credit.
Inputs: ip (required). Returns: p_scam, verdict, degraded, entities, +3 more
lookup_payment_handleLook up a payment handleARead-onlyInspect
Does this Cash App $Cashtag, PayPal.me name or Venmo username exist, is it active, and is it on Bewary's scam list? Existence and status only, never the person's name. Cost: 1 credit.
Inputs: handle (required), provider (required). Returns: p_scam, verdict, degraded, entities, +3 more
lookup_phoneLook up a phone numberCRead-onlyInspect
Country, number type, blocklist status and a verdict for a phone number. Cost: 1 credit, with line type 10.
Inputs: number (required), line_type. Returns: p_scam, verdict, degraded, entities, +3 more
lookup_shortcodeLook up an SMS short codeBRead-onlyInspect
Who operates this SMS short code, and is it legitimate, shared or a scam code? Cost: 1 credit.
Inputs: code (required), country. Returns: p_scam, verdict, degraded, entities, +3 more
lookup_urlLook up a linkARead-onlyInspect
Is this link safe to open? Resolves shorteners and redirects and checks where it really goes; on a shortener, says whether the shortener itself disabled, flagged or removed the link. Cost: 1 credit, deep 30.
Inputs: url (required), deep. Returns: p_scam, verdict, degraded, entities, +3 more
lookup_walletLook up a crypto walletBRead-onlyInspect
Is this wallet on Bewary's scam list? Cost: 1 credit.
Inputs: chain (required), address (required). Returns: p_scam, verdict, degraded, entities, +3 more
unwatchStop watchingADestructiveIdempotentInspect
Delete a watch: no more events or charges. Its events stay readable. Cost: free.
Inputs: id (required). Returns: id, deleted
watchWatch an entityAIdempotentInspect
Get events when a domain, phone number, wallet or brand changes: a domain's IP addresses, name servers, down/up/parked, re-registered, expiring or expired; a listing or delisting; a new lookalike domain of a brand. Watching it again updates the event types. Cost: 1 credit a day (a brand watch also 1 per lookalike event); API key required.
Inputs: type (required), value (required), events. Returns: id, entity, events, status, +2 more
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Scan suspicious messages, URLs, and text for scams with AI. Free tier - no API key required.
Scam and phishing detection for AI agents: safe/warn/danger verdicts for URLs and messages.
AI-powered scam and threat verification for phone numbers, URLs, texts, and emails.
Pay-per-call safety checks for AI agents: screen a crypto address or URL before you transact.
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
- FlicenseNot gradedqualityDmaintenance53 security & enrichment MCP tools for AI agents. Contract scanning, threat intel, OSINT, crypto data, DNS/WAF recon. Pay-per-call via HTTP 402 + USDC on Base mainnet. No API keys. First call free.-
- AlicenseAqualityBmaintenanceEnables AI agents to verify links and payments for scam risk before acting, returning deterministic allow/ask/deny verdicts with scores, reasons, and warnings using local checks.31MIT
- AlicenseNot gradedqualityCmaintenanceProvides AI agents with zero-cost, zero-dependency trust evaluation for domains, URLs, wallets, APIs, and IPs, returning a 0-100 score with SSL, DNS, WHOIS, security header, and content sub-scores, plus batch comparison to rank multiple targets.MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.