convez.ai
MCP ServerSegurançaAvançado
zavora-ai

Fraud MCP Server

zavora-ai/mcp-fraud

Detecção e revisão de fraudes unificadas com scoring e auditoria para agentes

Ver no GitHub
InicialPluginScore · de 0 a 100

Servidor MCP unificado de detecção e revisão de fraudes, combinando sinais de fraude e scoring de risco com gestão de casos e decisões gateadas. Implementa auditoria imutável e listas de bloqueio/permissão para agentes de fraude em retail, e-commerce e seguros SIU.

Instalação

$npx convez-ai zavora-ai/mcp-fraud

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
2
Forks
0
Acompanhando
0
Saúde
50%
Último commit
há 3 meses
Versão
v1.1.0
Issues abertas
0
Contribuidores
1

Casos de uso

  • Detecção de fraudes em pedidos de e-commerce (velocity, chargebacks, padrões suspeitos)
  • Triagem de sinistros em seguros (sinistros em estágio, duplicatas, anéis de provedores)
  • Gestão de casos de fraude com atribuição a revisores e escalação para SIU
  • Administração de listas de bloqueio/permissão com decisões gateadas

Veredito

Solução robusta e completa para operações de fraude em escala empresarial. Bem arquitetada com 19 ferramentas, auditoria imutável e suporte a múltiplos fluxos (retail + seguros), mas requer compreensão profunda de regras de scoring e workflows de tomada de decisão.

README

A tradução para o português deste README ainda está na fila.

Fraud MCP Server

Crates.io License ADK-Rust Enterprise Registry Ready

A unified fraud layer for ADK-Rust Enterprise agents — combining fraud signals + risk scoring (detection) and case alerts + gated decisions (review) in one server. 19 MCP tools serving both the retail Fraud Review Agent and the insurance SIU Fraud Triage Agent.

One server, both halves of fraud

Fraud detection and fraud review are two ends of the same pipeline, so they live together: signals feed scores, scores open cases, cases reach decisions — with an immutable audit trail throughout.

AgentWhat it uses
Retail / e-commerce — Fraud Revieworder/transaction signals → score_entity → create_case/triage_entity → decide_case (approve/decline) → block/allow lists
Insurance — SIU Fraud Triageclaim signals (staged accident, duplicate claim, provider ring) → score → case → escalate_case to SIU → decide_case (refer)

Architecture

How Scoring Works

  • Each signal on an entity contributes a weight; the risk score is the capped sum (0–100).
  • A signal's weight is its explicit weight → else its risk rule weight → else a severity default.
  • Bands: Low (<30) · Medium (30–59) · High (60–79) · Critical (≥80).
  • Lists override: allow-listed entities score 0; block-listed force 100.
  • Rules are configurable at runtime (upsert_rule) — no code changes to tune the model.

Tools (19)

Signals & Scoring (5)

ToolWhat It Does
add_signalRecord an indicator on an entity
get_signalsList an entity's signals
score_entityAggregate score, band, and per-signal contributions
upsert_ruleCreate/update a signal-type → weight rule
list_rulesList configured rules

Cases & Decisions (10)

ToolWhat It Does
create_caseOpen a review case (scores at creation)
get_case · search_casesRead / filter (highest-risk first)
rescore_caseRecompute from current signals/lists
assign_caseAssign to a reviewer
escalate_caseEscalate (e.g. to SIU) — gated
add_noteInvestigation note
decide_caseapprove / decline / refer / hold — gated
close_caseClose after a decision — gated
get_audit_trailImmutable decision record

Block / Allow Lists (3)

add_to_list (gated) · remove_from_list (gated) · list_entries

Agentic (1)

triage_entity — score an entity and auto-open a case when it reaches the threshold band; returns score + recommendation. The final decision still flows through the gated decide_case.

Example

> add_signal(entity_type: "order", entity_ref: "order:LIVE1", signal_type: "velocity", severity: "medium")
> add_signal(entity_type: "order", entity_ref: "order:LIVE1", signal_type: "prior_chargeback", severity: "high")
> add_signal(entity_type: "order", entity_ref: "order:LIVE1", signal_type: "new_account_high_value", severity: "high")

> triage_entity(domain: "retail_ecommerce", entity_type: "order", entity_ref: "order:LIVE1", reporter: "fraud-bot")
  → risk_score 95 (critical) · recommendation "decline_or_refer" · case FRD-1011

> assign_case(id: "FRD-1011", actor: "lead", assignee: "review.amy")
> decide_case(id: "FRD-1011", actor: "review.amy", decision: "decline", disposition: "confirmed ATO fraud")
  → decided

> add_to_list(kind: "block", entity_type: "customer", entity_ref: "cust:BADActor", reason: "ATO ring", actor: "ops")
> score_entity(entity_ref: "cust:BADActor")   → 100 (block_listed)

Installation

1. Build

git clone https://github.com/zavora-ai/mcp-fraud
cd mcp-fraud
cargo build --release

2. Add to your MCP client

Claude Desktop / Kiro / Cursor / Windsurf:

{
  "mcpServers": {
    "fraud": {
      "command": "/path/to/mcp-fraud"
    }
  }
}

3. Use it

> search_cases(domain: "insurance", risk_band: "critical")
> score_entity(entity_ref: "claim:CLM-5521")

Governance & Data Handling

  • Gated high-impact writes — decide_case, escalate_case, close_case, and list changes require approval in production; signal/score reads are read_only.
  • Defensible decisions — every case mutation appends to an immutable audit trail.
  • Opaque entities — entities are references/tokens (order:…, claim:…, cust:…), not raw PII.
  • Integration scaffold — the in-memory store and scoring model are for development; back them with your real signals platform and decision store, and bind actors to authenticated identities in production.

MCP Server Manifest

server_id = "mcp_fraud"
display_name = "Fraud Detection & Review"
version = "1.0.0"
domain = "risk"
risk_level = "high"
writes_allowed = "gated"
transports = ["stdio"]

Contributors

James Karanja Maina

License

Apache-2.0 — see LICENSE for details.


Part of the ADK-Rust Enterprise MCP server ecosystem.

Registry Compliance

This server implements the ADK MCP SDK contract:

  • HealthCheck — async health probe for registry monitoring
  • mcp-server.toml — manifest declaring tools, risk classes, and approval gates
  • Structured tracing — RUST_LOG env-filter for observability
Ver o original no GitHub

Bom para

Relacionados