Check an email before an AI agent sends it: send / ask a human / block. Detects prompt injection.
Runs on your machine from its package; the steps are below.
At most: moves money, runs code or commands, deletes data, or sends messages for you.
Odel charges nothing per call. The publisher may charge for its own service.
Runs locally over stdio
This server isn't hosted — your MCP client launches it from a package registry. Use one of the commands below, or drop the config into your client (e.g. Claude Desktop).
Run
npx -y qorami-mcp
MCP client config
{
"mcpServers": {
"qorami": {
"command": "npx",
"args": [
"-y",
"qorami-mcp"
]
}
}
}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.
| Path | What |
|---|---|
js/ | Zero-dependency JavaScript / TypeScript client (fetch, Node 18+ or browser). |
python/ | Zero-dependency Python client (stdlib only) + LangChain, CrewAI, LlamaIndex & OpenAI-Agents tools. |
tools/ | Drop-in OpenAI function-calling & Anthropic tool-use schemas for qorami_check_email. |
mcp/ | Stdio MCP server (qorami_health, verify_email, check_action_status) for Claude Desktop, Cursor, any MCP client. |
n8n-nodes-qorami/ | n8n community node (Settings → Community Nodes → n8n-nodes-qorami) — guard an email, usable as an AI-Agent tool. |
n8n/ | No-code recipe: guard a workflow's email with a plain HTTP Request node (no install). |
examples/ | Runnable Node & Python quickstarts. |
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'.
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
pip install qorami[<framework>] ships a drop-in qorami_check_email wrapper —
each returns ALLOWED / NEEDS HUMAN APPROVAL / BLOCKED and reuses the client:
| Framework | Install | Import |
|---|---|---|
| LangChain | pip install qorami[langchain] | from qorami_langchain import build_qorami_tool |
| CrewAI | pip install qorami[crewai] | from qorami_crewai import QoramiEmailGuard |
| LlamaIndex | pip install qorami[llamaindex] | from qorami_llamaindex import build_qorami_tool |
| OpenAI Agents SDK | pip install qorami[openai-agents] | from qorami_openai_agents import qorami_check_email |
from qorami_langchain import build_qorami_tool
tool = build_qorami_tool() # reads QORAMI_API_KEY
No-code workflows (n8n) use a plain HTTP Request node — see n8n/.
Register Qorami as a native tool in Claude Desktop / Cursor / any MCP client —
see mcp/. It exposes qorami_health, verify_email and check_action_status over stdio.
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.
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.
MIT — see LICENSE.