convez.ai
PluginSegurançaIntermediário
loicfontaine-max

Qorami SDK

loicfontaine-max/qorami-sdk

Ponto de controle para agentes de IA verificarem emails antes de enviar

Ver no GitHub
InicialPluginScore · de 0 a 100

SDK oficial para integrar verificação inteligente de email em agentes de IA, oferecendo controle antes do envio. Retorna decisões de envio, requisição de confirmação humana ou bloqueio baseado em políticas de segurança. Disponível em JavaScript, Python e como MCP server nativo.

Instalação

$npx convez-ai loicfontaine-max/qorami-sdk

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
42%
Último commit
há 4 meses
Versão
v1.0.0
Issues abertas
0
Contribuidores
4

Casos de uso

  • Prevenir envio de emails com dados sensíveis ou links maliciosos
  • Implementar aprovação humana em workflows de automação de email
  • Integrar verificação de segurança em agentes Claude ou LangChain

Veredito

Solução focada e bem implementada para um problema real: evitar que agentes de IA enviem emails problemáticos. Suporte multiplataforma (JS/Python) e integração nativa com Claude via MCP tornam a adoção prática. Ideal para times que automatizam comunicação com clientes.

README

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

Qorami SDK

Official clients, tool schemas and an MCP server for Qorami — a control point between your AI agents and actually sending email. Before each send, the agent asks Qorami, which replies send, request_human_confirmation, or do_not_send.

Get an API key in the dashboard. Full API reference: https://qorami.fr/docs.

PathWhat
js/Zero-dependency JavaScript / TypeScript client (fetch, Node 18+ or browser).
python/Zero-dependency Python client (stdlib only) + a LangChain tool.
tools/Drop-in OpenAI function-calling & Anthropic tool-use schemas for qorami_check_email.
mcp/Stdio MCP server (verify_email + check_action_status) for Claude Desktop, Cursor, any MCP client.
examples/Runnable Node & Python quickstarts.

JavaScript / TypeScript

import { QoramiClient } from './js/qorami.mjs'

const qorami = new QoramiClient({ apiKey: process.env.QORAMI_API_KEY })

await qorami.guard(
  { recipient: 'client@example.com', subject: 'Our offer', body, policyProfile: 'sales' },
  {
    send: () => mailer.send(),                            // allowed
    requestHumanConfirmation: (r) => queue(r.action.id), // a human was notified
    doNotSend: (r) => log('blocked', r.decision),        // do not send
  },
)

Or step by step with qorami.verify(...) and, after a review, poll qorami.status(actionId) until nextAction.type === 'send'.

Python

from qorami import QoramiClient
qorami = QoramiClient(api_key=os.environ["QORAMI_API_KEY"])

result = qorami.verify(recipient="client@example.com", subject="Our offer",
                       body=email_body, policy_profile="sales")
if result.next_action_type == "send":
    send_email()
elif result.next_action_type == "request_human_confirmation":
    queue_for_review(result.action_id)   # a human was notified by email
# else: do_not_send

LangChain

python/langchain_tool.py exposes a qorami_check_email tool an agent can call before sending:

from langchain_tool import build_qorami_tool
tool = build_qorami_tool()        # reads QORAMI_API_KEY

MCP server

Register Qorami as a native tool in Claude Desktop / Cursor / any MCP client — see mcp/. It exposes verify_email and check_action_status over stdio.

The contract

Every client returns the same decision the agent must obey via nextAction.type: send, request_human_confirmation (a human approves first — poll the action), or do_not_send. See https://qorami.fr/docs.

Cleaned version (auto-remediation)

When an email is risky only because of mechanically-removable content (a leaked secret, a suspicious link, an IBAN/card/SSN), the verify result carries a cleaned, sendable copy — send remediation.safeBody instead of blocking outright:

const r = await qorami.verify({ recipient, subject, body, policyProfile: 'general' })
if (r.nextAction.type === 'do_not_send' && r.remediation?.safeToSend) {
  mailer.send({ ...email, body: r.remediation.safeBody })   // safe, redacted copy
}
r = qorami.verify(recipient=..., subject=..., body=email_body)
if r.next_action_type == "do_not_send" and (r.remediation or {}).get("safeToSend"):
    send_email(body=r.remediation["safeBody"])   # safe, redacted copy

remediation.removed lists what was stripped (e.g. ["secret", "link"]). The MCP server surfaces the same field.

License

MIT — see LICENSE.

Ver o original no GitHub

Bom para

Relacionados