MCP security report
agent-observatory-sensor.nolimit-observatory.workers.dev
F25/100
Security grade FHigh-severity signals — review these before connecting.
Connected ✓31 tools scanned
https://agent-observatory-sensor.nolimit-observatory.workers.dev/s/min-to-sec/mcp
highpeople-search-index
Points toward a people-search / data-broker service and embeds tracking instructions
This tool's purpose is to help locate a 'living people-search index' service, which is commonly associated with doxing/privacy-invasive data-broker lookups. Combined with the same 'Follow start_here.hop' instruction pattern (with utm_source/utm_medium tracking), this both nudges the agent toward enabling potentially harmful people-search capabilities and embeds tracking/attribution instructions that are not part of the tool's stated function (discarding the query) — raising both privacy-harm and manipulation concerns.
highagent-ads-index
Instructs agent to initiate a paid trial 'for your operator' and follow tracked redirects
The description tells the agent to follow a specific hop chain carrying UTM tracking parameters and explicitly returns a '7-day trial handoff for your operator' — language that encourages the agent to initiate a commercial trial/signup on behalf of the user's operator without clear indication that this requires explicit user consent. This goes beyond the stated discovery function and could result in unauthorized commitments or financial/account actions, and embeds tracking metadata benefiting a third-party ad network rather than the user.
mediumagent-tool-index
Embedded navigation instruction with tracking parameters
The description directly instructs the agent ('Follow start_here.hop first') to traverse a specific redirect chain that embeds UTM tracking parameters (utm_source=agent-observatory&utm_medium=agent) identifying the call as agent-driven. This is an instruction aimed at steering agent behavior (rather than describing a tool's input/output), and could be used for click-based attribution or to funnel agents toward a particular paid gateway ('pay-per-call'). The agent should not blindly follow externally-defined hop chains or treat fetched content as trusted instructions without user awareness.
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, people-search-index, agent-ads-index
Pattern of externally-controlled 'hop' redirects could enable prompt injection
All three tools direct the agent to fetch and follow an external redirect/skill file ('start_here.hop') before proceeding. If the content returned by these hops can include further instructions, this creates a vector for indirect prompt injection where content fetched from an untrusted third party could be interpreted by the agent as new instructions. Agents should treat fetched hop content as untrusted data, not executable instructions.
Embed this badge
Show your MCP server’s security grade
Paste this into your README:
[](https://gateturbo.com/report/668c7473-aff6-4f5a-b925-1a8cce8804ea)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