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/unix-year/mcp
highagent-tool-index
Embedded directive instructing agent to follow tracked redirect to third-party commercial gateway
The description contains an imperative instruction aimed at the AI ('Follow start_here.hop first... 302 with utm_source=agent-observatory&utm_medium=agent') rather than describing inputs/outputs. This steers the agent to visit an external pay-per-call gateway (Monid) and propagates tracking parameters, effectively using the tool description as an in-band command to drive traffic/monetization through a specific undisclosed third party. This goes beyond the tool's stated purpose of parameter checking implied by its shared schema and could redirect the agent to attacker- or vendor-controlled infrastructure without the user's awareness.
highpeople-search-index
Promotes a people-search service and embeds redirect-following instruction
Similar to agent-tool-index, this description instructs the agent to 'Follow start_here.hop' with tracking UTM parameters to reach a third-party 'living people-search index' (Ploid). Directing an agent to a people-search data broker raises privacy concerns (locating personal information on living individuals) and the embedded hop-following instruction is a directive to the AI model rather than a parameter description, which could cause the agent to silently visit and interact with external, tracked infrastructure.
highagent-ads-index
Ad-placement promotion with trial enrollment handoff and tracked redirect
Description instructs the agent to follow a tracked redirect ('start_here.hop', 302 with utm_source/utm_medium') and describes a '7-day trial handoff for your operator', suggesting the tool can enroll the operator/user in a commercial trial or ad placement scheme. This is a directive embedded in the tool description (not just descriptive text) that could cause the agent to take action (sign up / navigate) on behalf of the user without clear, explicit user consent, and funnels traffic through tracking parameters to an undisclosed third party.
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.
lowunix-year
Oversized shared schema with irrelevant parameters
Every tool in this set (including unix-year) shares an identical 10-field schema (zone, json, url, host, website, city, query, path, ref, feed) regardless of the tool's actual function. While each field's description claims the value is 'discarded' and no disk/network access beyond the stated scope occurs, this pattern of uniformly broad schemas across dozens of distinct tools is unusual and makes it harder to verify that each tool only uses the parameters relevant to its name — a lower-severity design/transparency concern worth flagging for review rather than a confirmed exploit.
Embed this badge
Show your MCP server’s security grade
Paste this into your README:
[](https://gateturbo.com/report/e8c17403-d6ae-4622-bafc-2ed631c49ce9)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