MCP security report
mcp.myotp.app
F16/100
Security grade FA few things are worth a closer look before connecting.
Connected ✓10 tools scanned
https://mcp.myotp.app/mcp
mediumgenerate_otp
References secrets or data exfiltration
The tool text references credentials, environment variables, or sending data elsewhere. This can be legitimate, but review what this tool actually accesses.
mediumget_account_info
References secrets or data exfiltration
The tool text references credentials, environment variables, or sending data elsewhere. This can be legitimate, but review what this tool actually accesses.
mediumcreate_account
References secrets or data exfiltration
The tool text references credentials, environment variables, or sending data elsewhere. This can be legitimate, but review what this tool actually accesses.
mediumget_topup_quote
References secrets or data exfiltration
The tool text references credentials, environment variables, or sending data elsewhere. This can be legitimate, but review what this tool actually accesses.
mediumtop_up_credits
References secrets or data exfiltration
The tool text references credentials, environment variables, or sending data elsewhere. This can be legitimate, but review what this tool actually accesses.
mediumtop_up_credits
Autonomous payment capability with implicit credential use
This tool can complete a financial transaction (crediting the account via USDC or card) without requiring explicit per-transaction user confirmation. The description states that if a 'credential-carrying MPP runtime' already wraps fetch, the tool 'returns the credited response directly' — meaning payment can be completed silently using ambient credentials rather than an explicit user-approved flow. An agent could be induced to spend real money autonomously based on a balance-check failure, without the user reviewing or approving the specific purchase amount.
lowgenerate_otp
Unusually long tool description
Very long descriptions are sometimes used to bury instructions to the AI. Skim it before allowing.
low
Not on gate's verified list
This server isn't on gate's handpicked list. That's not necessarily bad, but there's no third-party signal about it — review its tools carefully.
lowgenerate_otp
return_otp exposes OTP in plaintext
The return_otp parameter causes the API to return the generated OTP code in plain text in the response. While the schema includes a warning not to enable this in production, an agent could still be instructed (or manipulated via user input) to set this flag, defeating the purpose of OTP-based verification by exposing the secret code outside the intended delivery channel.
lowcreate_account
Unauthenticated account creation with immediate funding path
This tool creates a new account and API key with no authentication required, and states that USDC top-ups work immediately even before email verification. Combined with top_up_credits, this could allow an agent to autonomously create accounts and fund them without meaningful identity verification, which is unusual capability breadth for a tool whose stated purpose is OTP delivery.
lowget_usage_report
Returns client IP addresses in transaction history
The usage report includes the originating client IP for every OTP transaction. This is reasonable for auditing/billing purposes but should be noted as it exposes network-identifying metadata about end users/systems that call the API.
Embed this badge
Show your MCP server’s security grade
Paste this into your README:
[](https://gateturbo.com/report/56023102-671f-4cba-aa24-b4d6b798757d)Scanned 9/8/2026 · This is a point-in-time snapshot of the server’s public tools. Re-scan.
Connect this server safely with gate.
Continuous re-scans, drift alerts, per-tool allow/ask/block, and a log of every call.
Monitor it — free