MCP security report
agents.samedaydesk.com
F5/100
Security grade FA few things are worth a closer look before connecting.
Connected ✓24 tools scanned
https://agents.samedaydesk.com/mcp
mediumextract_batch
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.
mediumlockfile_pin_delta
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.
mediumscan
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.
mediumagent_discoverability_audit
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.
mediumpayment_offer_preflight
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.
mediumseller_integrity_audit
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.
mediumcontract_qualified_search
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.
mediumagent_surface_budget_audit
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.
mediumwallet_policy_conformance
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.
mediumstateful_wallet_policy_conformance
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.
lowopportunity_preflight
Unusually long tool description
Very long descriptions are sometimes used to bury instructions to the AI. Skim it before allowing.
lowagent_discoverability_audit
Unusually long tool description
Very long descriptions are sometimes used to bury instructions to the AI. Skim it before allowing.
lowpayment_offer_preflight
Unusually long tool description
Very long descriptions are sometimes used to bury instructions to the AI. Skim it before allowing.
lowstateful_wallet_policy_conformance
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.
lowextract_batch
Embedded instruction about credential/domain binding on retry
The description tells the agent to retry with 'the identical authorized arguments and credential' and states the payment challenge is bound to a specific HTTPS domain 'not mcp://'. This is plausibly a legitimate x402 anti-replay/anti-phishing safeguard, but it is an unusual instruction embedded in a tool description that directs the agent's handling of payment credentials and retry behavior. Worth verifying this domain binding is enforced by the client rather than trusted purely from the tool text.
lowlockfile_pin_delta
Embedded instruction about credential/domain binding on retry
Same pattern as extract_batch: description instructs the agent to bind payment credentials to a specific external domain and to retry identical authorized arguments/credentials. Low risk since it appears to be a payment-protocol safeguard, but any tool description that dictates credential handling to the agent deserves scrutiny to confirm it can't be used to redirect credentials elsewhere.
Embed this badge
Show your MCP server’s security grade
Paste this into your README:
[](https://gateturbo.com/report/50914b7d-c3cf-42b8-a62a-cc8893b7d05a)Scanned 9/12/2026 · 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