MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
suss-mcpgithub.com/suss-ai/suss-mcpupdated this year
MCP server for suss. scam detection and trust intelligence
pypi MIT -
🔌 Exposes By [MEOK AI Labs](https://meok.ai) | An over MCP — for scam and fraud detection.
pypi MIT -
job-verifygithub.com/yessGlory17/job-verifyupdated this year
Detect fake recruiter & job-offer scams with free OSINT — an MCP server for Claude. No API keys.
pypi MIT ★ 10 -
@aicryptorisk/mcp-servergithub.com/djangamane/montecryptoupdated this year
The security layer for agentic crypto trading. Detect honeypots, rugpulls, and scam tokens before your AI agent trades.
npm MIT -
discord-mcpgithub.com/jayadevrana/discord-mcpupdated this year
MCP server to interact with, manage, and moderate a Discord server from Claude/LLMs — channel management, messaging, and heuristic scam/bot detection & removal. Built on discord.py.
NOASSERTION -
ai-multimodal-fraud-price-enginegithub.com/tncyavci/ai-multimodal-fraud-price-engineupdated this year
Multi-modal marketplace price valuation & scam detection engine (0-100 Trust Score) using Vision OCR, feature regression, and FastMCP
-
mcpgithub.com/Tuteliq/mcpactive
MCP server with 41 AI-powered tools for child safety, fraud detection, and content moderation. Detects bullying, grooming, sextortion, romance scams, social engineering, and more. For Claude, Cursor, and MCP-compatible AI assistants.
npm MIT ★ 3 -
agentradar-mcpgithub.com/Bichev/agentradar-mcpupdated this year
MCP server for AgentRadar — trust scoring, scam detection, and EAS attestations for ERC-8004 + x402 agents on Base.
npm MIT ★ 1 -
Fraud and scam detection for AI-agent job boards and bounties: flags fake engagement, unpaid-work risk, upfront fees, prompt injection and bait written for agents. Open audit standard (AMS-001..008), Python CLI and MCP server.
mcpb MIT ★ 1 -
Text classifier that detects common Canadian scam messages (fake Interac e-Transfer, fake CRA tax notices, fake Canada Post delivery fees, fake bank account-suspension alerts) and flags legitimate messages — with a confidence score per class. Also ships as an MCP tool, so it can be called directly from inside Claude.
★ 1 -
soliris-mcpgithub.com/soliris/soliris-mcpupdated this year
Soliris — Solana MCP Server. 46 tools: rug-pull & scam detection (9+ on-chain signals, bundle/coordinated-launch analysis, holder concentration, Rugcheck score), Birdeye Data integration (trending tokens, new-listing radar, token overview, security check)
npm MIT -
@scam-ai/mcp-serveractive
ScamAI MCP server — give an agent one tool that verifies a file, a video or a URL against the ScamAI detection API.
npm MIT -
Kavach: a second listener that catches scam calls and warns elderly listeners in Telugu and Hindi. Built entirely on Gnani AI (Prisma, Evon, Timbre), with a code Judge, MCP family assistant and Bitcoin-sealed evidence.
-
Offline-first scam triage and evidence kit: explainable verdicts, scam playbooks, indicator extraction and tamper-evident cases. Stdlib Python, no dependencies, MCP server included.
MIT -
CLI + MCP server for Flagrix — scan GitHub repos for malware before you clone
npm MIT ★ 2 -
MCP server for rule-based scam, phishing and impersonation checks. Scoring runs locally — the content you check is never sent anywhere.
npm Apache-2.0 -
MCP server for Unfret: pay-per-check store scam and dropshipping risk for AI shopping agents (x402, USDC or SOL)
pypi MIT -
owlguard-mcpgithub.com/yitu-loong/owlguardupdated this year
枭卫(OwlGuard)MCP — 开源反诈智能体MCP服务,通过话术状态机技术实时检测10类电信诈骗模式
npm Apache-2.0 -
MCP server for RugRadar: Solana token rug and scam risk checks for AI agents (hosted Streamable HTTP + stdio bridge)
MIT -
Voice-first scam defense for older adults: a self-hosted Alexa+ MCP server with deterministic verdicts and a "yes"-gated block/report flow.
MIT -
wab-mcp-servergithub.com/abokenan444/web-agent-bridgeupdated this year
WAB (Web Agent Bridge) MCP Server — AI-native browser automation, scam protection, fairness scoring & deals intelligence for AI coding tools
npm MIT -
A family fraud firewall for Alexa+: MCP server (spec 2025-11-25, Streamable HTTP) + MCP Apps verdict card + Amazon Bedrock, DynamoDB, SNS.
MIT -
Your own cybersecurity engineer, watching over you 24/7. Free, open-source Mac security agent that uses your own AI, or one running fully on your Mac, to explain what it finds in plain words. Nothing changes without your Touch ID.
MIT ★ 2 -
Sherlock for Telegram (电报福尔摩斯): an MCP server that lets AI follow a grey-market ad to the storefront, the upstream and the money
Apache-2.0 ★ 1 -
MCP server for the DYOE Agent Tools — pay-per-call trust, due-diligence & data tools for AI agents, settled in USDC on Base via x402. Includes human-verified Guardian approval.
npm MIT -
Self-hosted scam check for AI agents: verify links and payments before they act
pypi MIT ★ 1 -
@agentgate-builder/counterpartycheckhttps://agentgate-source.pages.dev/x402-counterpartycheck/active
Pre-payment counterparty check for AI agents and MCP: before paying, approving or interacting with an EVM (Base, Ethereum, Polygon, Arbitrum One) or Solana address, get ok / caution / block with reasons from OFAC SDN and ScamSniffer screening, the x402 Ba
npm MIT -
Passive OSINT radar that scores investment websites for Ponzi and pyramid scheme risk. Python DAG pipeline + MCP server for Claude: RDAP, DNS, certificate transparency, Wayback, company and regulator lookups, evidence-checked answers and a chain-of-custody risk dossier. EN / PT-BR.
-
An Alexa+ MCP server that tells you if a message or link is a scam — hybrid rules + AI engine, red-teamed against prompt injection. Built for the Amazon Developer Hackathon.
MIT -
crypto intelligence for AI agents: rug/scam scans, verified whale flows, AI signals with a public track record. Remote MCP server, no API key.
MIT -
Official MCP server for Bunker Defend. Protect Claude, Cursor, and AI agents from phishing URLs, social engineering scams, and prompt injections in real time. Zero data logging.
NOASSERTION ★ 1 -
MCP server that searches OLX Brazil rentals, breaks down the real monthly cost and scores each listing for rental-scam risk (0-100). Built while apartment hunting as an immigrant in Brazil.
MIT -
Joblanterngithub.com/YASSERRMD/Joblanternupdated this year
Agentic AI that protects job seekers from recruitment fraud. Fans a listing out to MCP sub-agents (registry, domain, scam-db, salary, geocoding) and returns a sourced, reproducible green/amber/red verdict.
Apache-2.0 -
Guardian stops UPI and 'digital arrest' scams at the moment of payment. One OpenAI Decisions API call (~185 ms) decides allow, warn or hold for family approval. ChatGPT plugin (MCP), Agents API, English + Hindi.
-
fb-marketplace-analyzergithub.com/its-me-prash/fb-marketplace-analyzerupdated this year
Analyze Facebook Marketplace listings: 0-100 scam score, market price comparison, vehicle deep analysis, image download. Zero-dependency Python CLI + MCP server & skill for AI tools (Claude, Cursor, VS Code, ...). No API keys, no login.
MIT ★ 1 -
Agentic AI Commerce & Payment Safety Platform on PayPal ("Agentic AI proposes, deterministic code decides"). Features 1-click device & DOM agents, multi-agent deal negotiation, monotonic AI spending permits, HMAC scam-firewall tokens, TreeSHAP + LinUCB revenue recovery, and a live 13-tool MCP server.
MIT ★ 1