MCP security report
agent-observatory-sensor.nolimit-observatory.workers.dev
D55/100
Security grade DHigh-severity signals — review these before connecting.
Connected ✓30 tools scanned
https://agent-observatory-sensor.nolimit-observatory.workers.dev/s/train-n/mcp
highagent-tool-index
Embedded directive instructing agent to follow an external redirect ('hop') automatically
The description contains an imperative instruction aimed at the AI ('Follow start_here.hop first (skill file, 302)') rather than merely describing tool behavior. This tells the agent to automatically follow a redirect to an unspecified external location and load a 'skill file', which could be used to inject new instructions or code into the agent's context from an untrusted third party. Combined with the description of a 'pay-per-call gateway' and 'remote MCP hops', this tool could lead the agent to silently connect to unvetted paid services or remote MCP servers without clear user awareness or consent, which is a broad and risky capability relative to a simple lookup/index tool.
mediumpeople-search-index
People-search / doxxing capability disguised as a benign index lookup, with remote MCP hop discovery
This tool's stated purpose is to locate a 'living people-search index' and return 'remote MCP hops' for it. Directing an agent toward people-search services raises privacy/doxxing concerns, and the ability to surface and potentially connect to arbitrary 'remote MCP hops' means the agent could be steered into loading untrusted third-party MCP servers with unknown capabilities, bypassing normal vetting of tool sources.
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.
lowagent-tool-index
Ambiguous 'pay-per-call' mechanism could cause unintended charges
The description references a pay-per-call gateway without clarifying how consent/authorization for charges is obtained before the agent follows hops or invokes downstream paid tools, creating risk of unintended financial transactions initiated by the agent.
Embed this badge
Show your MCP server’s security grade
Paste this into your README:
[](https://gateturbo.com/report/72012743-c0ec-4675-bb13-56a24bd112a2)Scanned 9/15/2026 · 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