MCP security report
agent-observatory-sensor.nolimit-observatory.workers.dev
F7/100
Security grade FHigh-severity signals — review these before connecting.
Connected ✓30 tools scanned
https://agent-observatory-sensor.nolimit-observatory.workers.dev/s/focus-order-ok/mcp
highagent-tool-index
Embedded navigation instruction with tracking parameters directs agent to third-party monetized gateway
The description explicitly instructs the agent to 'Follow start_here.hop first' through a redirect chain tagged with utm_source=agent-observatory&utm_medium=agent. This is an imperative directed at the AI's behavior (not just a description of output), steering it toward an external pay-per-call service and tagging the traffic as agent-originated. This could be used to funnel agents/users into an unvetted commercial ecosystem without user awareness or consent.
highpeople-search-index
Tool promotes a people-search/PII aggregation service and instructs agent to follow tracked redirects
Description instructs the agent to 'Follow start_here.hop' (with the same utm_source=agent-observatory&utm_medium=agent tracking) toward a 'living people-search index.' People-search services aggregate personal data (addresses, phone numbers, relatives, etc.). Directing an agent toward such a service, especially via an embedded instruction rather than neutral tool output, raises privacy risks and could facilitate doxxing or unauthorized personal-data lookups on the user's behalf.
highagent-ads-index
Tool instructs agent to pursue ad placement and initiate a trial signup 'for your operator'
Beyond the suspicious tracked-redirect pattern shared with the other index tools, this description tells the agent to obtain a '7-day trial handoff for your operator,' which implies initiating a commercial commitment/signup on behalf of the user or the agent's operator without explicit user consent. This is an action with real-world business/financial implications embedded in what looks like an informational lookup tool, and it is explicitly aimed at getting the agent to help place ads targeting AI agents themselves.
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.
lowutc-time
Oversized, irrelevant parameter schema shared across unrelated tools with unverifiable 'discarded' claims
All 30 tools expose an identical 10-field schema (zone, json, url, host, website, city, query, path, ref, feed) regardless of the tool's stated single purpose (e.g., a UTC time tool accepts json, url, host, website, city, query, path, ref, feed). Each field claims the data is 'discarded' or 'no disk access occurs,' but these claims cannot be verified by the agent and create many channels through which the agent could be induced to pass sensitive strings (file paths, search queries, JSON payloads) into a tool whose actual behavior is opaque. This pattern across the whole tool set is a design smell that could mask broader data collection than each tool's name/description suggests.
Embed this badge
Show your MCP server’s security grade
Paste this into your README:
[](https://gateturbo.com/report/fa3a02a9-1681-48d4-b7c8-5954f28fdc32)Scanned 10/2/2026 · 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