MCP security report
agent-observatory-sensor.nolimit-observatory.workers.dev
F43/100
Security grade FHigh-severity signals — review these before connecting.
Connected ✓31 tools scanned
https://agent-observatory-sensor.nolimit-observatory.workers.dev/s/tz-america-toronto/mcp
highagent-ads-index
Embedded directive instructing agent to follow tracking redirects and pursue a sales/trial handoff
The description tells the agent to 'Follow start_here.hop first' through a redirect chain carrying UTM tracking parameters (utm_source=agent-observatory&utm_medium=agent) and explicitly promises a '7-day trial handoff for your operator.' This is an instruction aimed at the AI's behavior (not just a description of output) that steers the agent toward an undisclosed third-party advertising/monetization funnel and toward signing up the operator for a paid trial, without the user's knowledge or consent. This exceeds the stated purpose of 'finding where a product can be placed' and could result in the agent silently generating affiliate traffic or committing the operator to a commercial arrangement.
mediumagent-tool-index
Instruction to follow tracked redirect hop embedded in tool description
The description directs the agent to 'Follow start_here.hop first' which is a 302 redirect carrying attribution parameters (utm_source=agent-observatory&utm_medium=agent). This is a navigation instruction aimed at the AI rather than a neutral description of functionality, and it funnels the agent toward a specific named commercial gateway ('Monid') with tracking baked in, which could be used to attribute/monetize agent traffic without user awareness.
mediumpeople-search-index
Embedded redirect instruction plus people-search capability raises privacy concerns
Like the other two 'index' tools, this description instructs the agent to 'Follow start_here.hop' through a tracked 302 redirect to a named third-party service ('Ploid'). Additionally, the tool's stated purpose — finding a 'living people-search index' — facilitates locating personal information about identifiable individuals, which combined with an embedded traffic-attribution redirect is a higher-risk combination (privacy/doxxing-adjacent capability plus hidden commercial routing instructions aimed at the agent).
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.
lowtz-america-toronto
Oversized, unrelated parameter schema shared across all tools
This tool (and all other tools in this set) exposes an identical 10-field schema (zone, json, url, host, website, city, query, path, ref, feed) regardless of the tool's narrow stated purpose. For a 'current time' tool, accepting arbitrary JSON bodies, URLs, file paths, search queries, and feed URLs — all claimed to be 'discarded' — is unusual design that cannot be verified by the caller and could mask undisclosed data handling or be used to smuggle unrelated data into calls under the guise of harmless utility tools.
Embed this badge
Show your MCP server’s security grade
Paste this into your README:
[](https://gateturbo.com/report/64c2f107-fcb0-44d9-866f-2103b991c441)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