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.
-
Real-time security monitoring and fraud detection, with explainable risk scores and a voice-queryable MCP interface.
MIT ★ 1 -
vigil-fraud-alert-mcpupdated this year
Vigil Fraud Alert API & MCP Server — proximity-based card authorization engine for real-time fraud detection, GPS tracking, and transaction risk scoring.
npm MIT -
claimdesk-fraud-detector-mcpupdated this year
MCP server for insurance fraud detection — AI-powered claim fraud scoring, red flag analysis, SIU referral reports, and fraud pattern matching for insurance claims
npm MIT -
@codespar/mcp-clearsaleupdated this year
MCP server for ClearSale — Brazilian fraud prevention, order risk scoring, device fingerprinting, and chargeback feedback
npm MIT -
@codespar/mcp-kondutoupdated this year
MCP server for Konduto — Brazilian fraud prevention, API-first order risk scoring, behavioral device intelligence, and blocklist/allowlist/reviewlist management
npm MIT -
@codespar/mcp-siftupdated this year
MCP server for Sift — global enterprise ML-based fraud detection, real-time risk scoring (payment/account/content abuse), decisions workflows, and event ingestion
npm MIT -
mcp-fraudgithub.com/zavora-ai/mcp-fraudupdated this year
Fraud MCP Server — unified fraud detection (signals + risk scoring) and case review (alerts, gated decisions, block/allow lists) for retail and insurance (SIU) fraud agents
cargo Apache-2.0 -
claimdesk-fraud-mcpupdated this year
MCP server for insurance fraud detection — red flag analysis, fraud risk scoring, pattern detection, SIU referral recommendations, and investigation checklists for all lines of business
npm MIT -
🛡️ Analyze transactions for fraud using advanced models and tools, providing insights and risk scores to enhance investigation efficiency.
Apache-2.0 ★ 1 -
MCP server exposing an n8n fraud-scoring agent as a callable tool — any MCP-compatible AI client can request live fraud risk assessments. Includes a real debugging log showing a Windows path-with-spaces bug that broke the client connection.
-
financial-mcp-servergithub.com/THE-DS-WAREHOUSE/financial-mcp-serverupdated this year
Custom MCP server exposing financial tools — portfolio analysis, XGBoost risk scoring, fraud detection, transaction lookup, and FinBERT market sentiment — connectable directly from Claude Desktop or any LangGraph agent.
-
Revnuvo Trust MCP server: verify companies, domains and counterparties from inside any AI agent. Entity resolution (200+ jurisdictions), UBO, sanctions screening, 0-100 fraud scoring. x402-payable ($0.10/call, USDC on Base) or API key.
npm MIT -
Agentic fraud investigation for Transakt — Kafka + ML scoring, LangGraph over MCP, human-in-the-loop, A2A, Grafana
-
MCP server for insurance claims triage — AI-powered fraud detection, claims routing, reserve estimation, FNOL processing, and priority scoring for claims adjusters and insurance operations
npm MIT -
trustswarmgithub.com/mrkingsleyobi/trustswarmupdated this year
Real-time blockchain fraud detection using autonomous multi-agent AI swarms. Detect fraud in <2s with 150x faster vector search (HNSW), 84.8% accuracy, and 73% cost reduction. Features ERC-1155 trust scores, MCP integration, and reflexion learning.
MIT ★ 1 -
The official CLI and MCP server of FFraud: check a whole website's security, score any IP for fraud, catch throwaway emails. Free, no key. npx ffraud
MIT -
ffraud-mcpactive
FFraud's MCP server and CLI under its first name: the same code as the ffraud package (npx ffraud). Website security, IP fraud scoring, disposable-email and domain checks. No key needed.
npm MIT -
AI-assisted hospital insurance claim review. LangGraph multi-agent pipeline (extraction, policy RAG validation, fraud scoring, summary) with human-in-the-loop decisions. FastAPI + Next.js 16 BFF, ChromaDB, MCP server, 3D UI.
-
ffraudactive
FFraud's open fraud database as a CLI and an MCP server: a whole website's security checked in seconds with every fix, IP fraud scoring with VPN/proxy/Tor detection, disposable-email checks, domain reputation and community abuse reports. No key needed.
npm MIT -
Real-time financial transaction monitoring dashboard with MCP integration, advanced filtering, fraud detection, and risk scoring. Built with Python and aiohttp.
MIT -
@mimranakb/trust-layer-mcpgithub.com/mimranchohan/x402-trust-layerupdated this year
MCP server for the x402 Trust Layer — 13 agent-payment trust tools (preflight guard, KYM merchant score, mandate diff, semantic escrow, receipt audit, Agent Trust Protocol v4: passport, fraud scan, credit score). Pay-per-call in USDC over x402; no API key
npm MIT -
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
-
@codespar/mcp-legitiactive
DEPRECATED: no live endpoint (collection-prod.inspcdn.net does not resolve). MCP server for Legiti — Brazilian fraud prevention (ticketing + ecommerce), real-time order evaluation, chargeback feedback, and account/event/sale collection
npm MIT -
Clients, MCP server and docs for the PhoneRisk API: phone number validation, line type, carrier, disposable-number detection and a 0-100 risk score
MIT -
ShieldLabs MCP server: read identifications, search history, summarize users, devices and IPs, explain Risk Scores and verify webhook signatures from any MCP client.
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.
-
reviewradar-benchmark-mcpupdated this year
MCP server for competitive review benchmarking — compare review authenticity scores across products, detect category-wide manipulation trends, benchmark trust scores against industry baselines, and generate competitive review intelligence reports
npm MIT -
reviewradar-detect-mcpgithub.com/crawde/mcp-reviewradar-detectupdated this year
MCP server for AI-powered fake review detection — analyze product reviews for authenticity, detect review manipulation patterns, calculate trust scores, and identify suspicious reviewer behavior across e-commerce platforms
npm MIT -
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 -
sanctscangithub.com/cognis-digital/sanctscanupdated this year
Screens counterparties and transactions against OFAC/EU/UN sanctions lists with fuzzy name matching and explainable hit scoring.
NOASSERTION -
ProofTell's MCP server: phone, email and IP checks and an identity's risk score as tools for Claude, Cursor, VS Code and any MCP client, with one API key.
npm MIT -
@notcrippledgod/uk-business-intelligence-mcpupdated this year
MCP server for UK company intelligence — search, directors, filings, financial accounts (iXBRL), website-vs-Companies-House legitimacy verification, and health scoring
npm MIT -
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 -
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 -
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