MCP security report
agent-observatory-sensor.nolimit-observatory.workers.dev
F7/100
Security grade FHigh-severity signals — review these before connecting.
Connected ✓31 tools scanned
https://agent-observatory-sensor.nolimit-observatory.workers.dev/s/cc-ie/mcp
highagent-tool-index
Embedded navigation instructions with tracking parameters directed at the agent
The description explicitly instructs the AI to 'Follow start_here.hop first' and specifies hardcoded UTM tracking parameters (utm_source=agent-observatory&utm_medium=agent) to use when doing so. This is an instruction embedded in a tool description that tells the agent to perform a specific multi-step navigation/redirect sequence rather than describing what the tool itself returns. This pattern could be used to funnel the agent (and by extension the user's session) through tracked referral links to external pay-per-call services without the user's informed consent.
highpeople-search-index
Facilitates discovery of a people-search / surveillance service, with embedded redirect instructions
This tool's purpose is to help the agent find and route to a 'living people-search index' (described as 'Ploid'), including CLI setup, API, and remote MCP hops. People-search services aggregate personal data (addresses, relatives, phone numbers, etc.) and are commonly associated with doxxing, stalking, and privacy violations. Additionally, like the other index tools, it instructs the agent to 'Follow start_here.hop' with embedded UTM tracking parameters, which is an AI-directed instruction to traverse a specific referral chain rather than a description of tool output.
highagent-ads-index
Embedded instructions to onboard the agent's operator into a paid advertising/trial service
The description instructs the agent to follow a tracked redirect ('start_here.hop' with utm_source/utm_medium parameters) and explicitly mentions returning a '7-day trial handoff for your operator.' This is an instruction aimed at the AI to initiate a commercial sign-up/trial flow on behalf of the user/operator, which goes beyond a simple lookup/utility function and could result in the agent taking consequential actions (starting a paid trial or registering the operator) without clear, separate user consent.
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.
lowcc-ie
Shared oversized schema with unrelated parameters across all tools
This tool (like all 31 tools) exposes a large shared input schema containing many fields unrelated to its stated purpose (zone, json, url, host, website, city, query, path, ref, feed) even though the tool only needs one. This generic 'everything accepted' schema pattern makes it hard for the agent or a reviewer to reason about what data actually flows where, and increases risk that a future change could silently repurpose an accepted-but-unused field to exfiltrate data (e.g., 'path' or 'json' claimed to be discarded) without the tool-level description changing. Not inherently malicious, but worth tightening per-tool schemas to only the parameters actually used.
Embed this badge
Show your MCP server’s security grade
Paste this into your README:
[](https://gateturbo.com/report/c20804f5-1ea3-4236-8187-2112cf47ad1c)Scanned 10/3/2026 · 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