- PreClick — An MCP-native URL preflight scanning service for autonomous agents. @preclick/preclick-mcpPreClick scans links for threats and confirms intent match with high accuracy before agents click.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.6 GitHub stars.
- PhoneInfoga - International Phone Number OSINT @anshumanatrey/phoneinfoga-phone-osintPhoneInfoga - International Phone Number OSINT19% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.5 GitHub stars.
- Strale - 290+ API capabilities for AI agents @strale-io/strale290+ quality-scored API capabilities for AI agents across 27 countries via MCP.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.5 GitHub stars.
- Verantis @m9labs-railscope/verantis-mcpVerified directory for machine payments (x402 & MPP): check services and wallets before agents pay.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.4 GitHub stars.
- Seraph @kondux/seraphCrypto transaction firewall and risk tools for MCP agents.11% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.4 GitHub stars.
- MolTrust MCP Server @moltycel/moltrust-mcp-serverGive an agent a verifiable identity, and check another agent's before dealing with it.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.4 GitHub stars.
- Mindjack MCP @mindjack/mcpSolana memecoin rug check for trading agents: pump.fun launches, calibrated rug risk, wallets, KOL.12% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.3 GitHub stars.
- Agent Skill @deep-identity-inc/agent-skillAn MCP Server that provides identity verification and anti-fraud tools for AI agents via deepidv.27% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.3 GitHub stars.
- Revettr @alexanderlawson17/revettr-mcpCounterparty risk scoring for agentic commerce via x402 micropayments.10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.3 GitHub stars.
- Tuteliq MCP @tuteliq/mcpDetect grooming, bullying, fraud, and 16+ online threats across text, voice, image, and video.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.3 GitHub stars.
- HORIZON SHIELD: Construction Estimate Auditor for Japan (KIRA) @ogasurfproject-jpg/horizon-shield-webmcpAgent intake desk for property renovation. Read only, CORS open, fail closed, receipts recompute.16% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.2 GitHub stars.
- Cybercentry Verification @cybercentry/verificationTwelve tools: token, wallet, contract and site security. Two free, the rest $1 in USDC over x402.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.2 GitHub stars.
- x402-seller — rug protection & safe-alpha for trading agents @wyattpalm2-eng/x402-sellerRug-check & launch radar for trading agents: composite honeypot score, EVM+Solana, keyless x402.12% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.2 GitHub stars.
- Quesen Deterministic Agent Decision Layer @shxnque/quesenDeterministic decision layer for autonomous agents: reproducible PROCEED/REVIEW/SKIP verdicts.10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.2 GitHub stars.
- IntentFence Agent Action Firewall @razel369/intentfenceFail-closed action authorization, MCP risk scanning, x402 checks, and signed receipts.10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.2 GitHub stars.
- Macfax @macfax/macfaxIdentify any Apple serial and read its device record, plus used-Mac prices, listings and checks.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.2 GitHub stars.
- Mainstreet @philpof102-svg/mainstreetReputation oracle for AI agents on Base: SAFE/CAUTION/BLOCK + 0-100 score before you pay. x402+MCP7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.2 GitHub stars.
- Vouch @notifuturo/vouchCheck if a counterparty is safe to pay: trust/risk score for AI agents. Scam/phishing screen.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.2 GitHub stars.
- Onyx @dimitrilaouanis-tech/onyx-mcpEd25519-signed ground-truth oracle — 63 paid x402 tools live on Base mainnet.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.2 GitHub stars.
- Limitguard Lead Verification @limitguard/limitguardLead validation over MCP: KVK/KBO register, EU VAT, sanctions and email checks with sources.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.1 GitHub stars.
- Outris Identity @outris-dev-user/outris-identity-mcpIdentity resolution MCP server for phone/email lookups across 31+ services. Global + India coverage.30% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.1 GitHub stars.
Fraud & scam detection MCP servers
A server here checks whether a link, number, merchant, token or document is a scam or fraudulent.
Not here: general reviews.
539 remote200 localTagged by Odel's AI, which can make mistakes
Most popular in Fraud & scam detection
By GitHub stars, at most two per publisher- Number 1: Hive Intelligence MCP@hiveintelligence/mcpEvidence-backed crypto due diligence with sources, freshness, and a runtime receipt on every call.10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.20 GitHub stars.
- Number 2: Scholar Sidekick@mlava/scholar-sidekick-mcpCatch AI-fabricated citations (real DOI + fake title). Retraction, open-access, 10,000+ CSL styles.3% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.11 GitHub stars.
- Number 3: PreClick — An MCP-native URL preflight scanning service for autonomous agents (formerly URLCheck).@urlcheck/urlcheck-mcpPreClick scans links for threats and confirms intent match with high accuracy before agents click.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.6 GitHub stars.
