MCP security report
app.varrd.com
B82/100
Security grade BA few things are worth a closer look before connecting.
Connected ✓9 tools scanned
https://app.varrd.com/mcp
mediumbuy_credits
Encourages fully autonomous financial transactions without user confirmation
The tool description explicitly promotes a 'fully autonomous — no human needed' crypto payment flow, telling the agent that if it has wallet access this is 'the fastest path — fully machine-to-machine.' This nudges the AI to initiate and complete real monetary transactions (sending USDC) on the user's behalf without requiring explicit per-transaction user approval, which could lead to unauthorized or unexpected spending of user funds.
lowvarrd_edges
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.
lowvarrd_edges
Sales-style language nudging spend decisions
The description uses persuasive marketing phrasing ('Cheaper than a coffee', 'FREE — always safe to call') to encourage the agent to escalate through paid depth tiers. While not a security exploit, this kind of built-in persuasion embedded in a tool description can bias an agent toward incurring costs on behalf of the user beyond what the user actually requested.
Embed this badge
Show your MCP server’s security grade
Paste this into your README:
[](https://gateturbo.com/report/9a435b0f-2006-454d-a50f-f0463a1735e4)Scanned 10/4/2026 · 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