MCP security report
texasautoquotes.com
D46/100
Security grade DA few things are worth a closer look before connecting.
Connected ✓8 tools scanned
https://texasautoquotes.com/mcp
mediumpull_requests
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.
mediummarket_data
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.
mediumrequest_agent_contact
sell_identity scope permits selling consumer PII to marketing partners
The consent object allows a scope value 'sell_identity' that 'additionally permits sharing with marketing partners,' beyond the core function of connecting a consumer to licensed agents. This is a broad, monetization-oriented capability bundled into what is framed as a quote-facilitation tool. An agent could be induced to present or default to this broader scope, resulting in user contact data being sold to third parties beyond what the user reasonably expects from 'connecting with an agent.'
mediumregister_agency
'handoff' feature pre-selects an agency before consent is presented
The handoff parameter causes a specific agency to be 'named in the consumer's consent before consent is given' and to receive the consumer's record exclusively, in exchange for a $25 fee to the agency when accepted. This creates an incentive structure where the consumer's 'consent' is obtained after the routing decision has already been made in favor of a paying agency, which risks presenting the consumer with a choice that appears neutral but is commercially predetermined.
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.
lowrequest_agent_contact
Consent flag relies on agent's self-attestation
The 'consent.granted' boolean is simply passed by the calling agent with no independent verification other than an optional evidence field or consent URL. The tool's own description says granted should be true 'only if the human agreed,' but nothing structurally prevents an AI agent from setting granted=true without real human confirmation, effectively bypassing the stated consent gate for sharing name/phone/email with outside parties.
lowpull_requests
Accepts raw payment/authorization payloads as plain string parameters
The tool accepts 'credential' described as 'the base64url JSON that would follow "Authorization: Payment"' and an 'x402 X-PAYMENT payload' and 'AP2 Payment Mandate' as plain input fields rather than via a secure transport/header mechanism. While this may be necessary for the protocol, exposing raw authorization-equivalent payloads as tool arguments increases the risk they could be logged, leaked, or requested inappropriately by an agent from a user under the guise of 'payment info.'
Embed this badge
Show your MCP server’s security grade
Paste this into your README:
[](https://gateturbo.com/report/62b79f19-4683-45ac-9995-318486bdeb60)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