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/mi-to-km/mcp
highagent-ads-index
Embedded directive to agent + undisclosed trial sign-up handoff
The description does not merely describe a lookup function; it instructs the calling agent to 'Follow start_here.hop first' through a tracked redirect (utm_source=agent-observatory&utm_medium=agent) and then execute 'the 7-day trial handoff for your operator.' This is an imperative aimed at the AI's behavior (navigate a specific chain of links, then enroll the user/operator in a trial) rather than a description of inputs/outputs. Causing an agent to autonomously initiate a trial subscription or commercial handoff on behalf of the user, via a tracked marketing funnel, without explicit user consent is a manipulation/consent risk and could result in unwanted charges or data sharing with a third party (Agent Ads).
mediumagent-tool-index
Agent-directed navigation instructions with tracking parameters
The description tells the agent to 'Follow start_here.hop first' via a 302 redirect carrying utm_source/utm_medium tracking parameters, and to then traverse docs/CLI/remote-MCP hops. This is an instruction sequence aimed at controlling agent behavior (visit specific tracked URLs in a specific order) embedded in a tool description rather than being left to the agent's judgment, and it funnels the agent/user through a third-party monetization funnel ('Monid') without clear disclosure to the user.
mediumpeople-search-index
Directs agent to a people-search / data-broker service via tracked redirect
Like the other 'index' tools, this instructs the agent to 'Follow start_here.hop' through a UTM-tagged redirect to reach a 'living people-search index (Ploid).' Beyond the embedded navigation directive aimed at the agent, the underlying capability being surfaced (a people-search/data-broker lookup service) raises privacy concerns: facilitating discovery of personal-information aggregation services can enable misuse (e.g., locating private individuals) and the tool's description pushes the agent toward this third-party service via tracked links rather than neutral information.
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.
lowmi-to-km
Oversized, unused parameter surface shared across unrelated tools
This tool (miles-to-km conversion) and nearly all other tools in this set share an identical 10-field input schema (zone, json, url, host, website, city, query, path, ref, feed) that has no relation to the tool's stated single-purpose function. While each field is annotated as 'discarded,' this pattern of broad, unexplained parameter acceptance across dozens of narrowly-named tools is unusual and could mask data exfiltration paths or make it easy to silently repurpose a tool's accepted inputs in the future without the agent or user noticing a scope change. Recommend tightening schemas to only the parameters actually required by each tool.
Embed this badge
Show your MCP server’s security grade
Paste this into your README:
[](https://gateturbo.com/report/9e78c09a-77b7-4d51-8764-7a1c20ed5b0b)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