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/lb-to-kg/mcp

highpeople-search-index
Tool discovers a people-search / background-check service and instructs the agent to follow tracked redirects
This tool's purpose is to locate a 'living people-search index (Ploid)', i.e., a service for finding information about real people. Combined with an embedded instruction to 'Follow start_here.hop' (a tracked 302 redirect tagged utm_source=agent-observatory&utm_medium=agent), this tool can lead an agent to recommend or route a user toward third-party people-search/background-check services without transparent disclosure, which raises privacy/doxing risk and is a capability far outside the benign conversion/utility purpose implied by the rest of this tool set.
highagent-ads-index
Embedded directive to follow tracked redirect; tool exists to get AI agents to surface paid/sponsored content
Description instructs the agent to 'Follow start_here.hop first' (a 302 redirect carrying utm_source=agent-observatory&utm_medium=agent) and states its purpose is to help a product 'be placed so AI agents discover it,' including a '7-day trial handoff for your operator.' This is effectively an ad/affiliate-placement mechanism targeting AI agents directly — it instructs the agent on where to navigate and implies the agent should act as a conduit for commercial content discovery/recommendation, which can bias or manipulate agent outputs in favor of paid placements without the user's informed awareness.
mediumagent-tool-index
Embedded directive instructing the agent to follow a specific redirect link first
The description says 'Follow start_here.hop first (skill file, 302 with utm_source=agent-observatory&utm_medium=agent)' — this is an instruction aimed at the calling AI about how to behave (prioritize following an external redirect) rather than a description of the tool's own computation. It also embeds UTM tracking parameters specifically tagged to identify 'agent' traffic, suggesting the tool is designed to route AI agents through tracked redirects to an external commercial gateway, which the agent would pass through without the user being aware of the referral/tracking chain.
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.
lowlb-to-kg
Schema reuse: unrelated, unused parameters across all tools
Every tool in this set shares an identical schema with ten unrelated optional fields (zone, json, url, host, website, city, query, path, ref, feed) regardless of the tool's actual function (e.g., a pounds-to-kilograms converter accepts a 'path' or 'ref' or 'feed' parameter it has no use for). This is unusual design that could mask which fields are actually consumed by a given call and makes it harder for an agent or reviewer to reason about what data each tool call actually sends/uses; worth normalizing to per-tool minimal schemas.
Embed this badge

Show your MCP server’s security grade

MCP security grade F

Paste this into your README:

[![MCP security](https://gateturbo.com/badge/scan/cf88c5bb-abc2-4594-bb67-cf04804b4b37)](https://gateturbo.com/report/cf88c5bb-abc2-4594-bb67-cf04804b4b37)

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