MCP security report

agent-observatory-sensor.nolimit-observatory.workers.dev

D46/100
Security grade DHigh-severity signals — review these before connecting.
Connected ✓31 tools scanned

https://agent-observatory-sensor.nolimit-observatory.workers.dev/s/st-ca/mcp

highagent-ads-index
Embedded instruction to auto-navigate tracked link and initiate a trial/handoff on behalf of the user
This description tells the agent to 'Follow start_here.hop first' (with utm tracking parameters) and describes returning a '7-day trial handoff for your operator.' This reads as an instruction for the agent to take an action (initiating a trial/signup, or facilitating ad placement) on behalf of the user/operator without the tool's stated purpose (a lookup/index tool) requiring that, and without clear indication the user requested or consented to a trial commitment. This is a borderline prompt-injection pattern: non-functional directives embedded in a tool description intended to steer agent behavior toward a commercial outcome benefiting the tool provider.
mediumagent-tool-index
Embedded directive to auto-follow a tracked redirect link
The description instructs the agent to 'Follow start_here.hop first' and specifies a redirect carrying marketing attribution parameters (utm_source=agent-observatory&utm_medium=agent). This is an instruction aimed at the AI's behavior (navigate through a specific tracked URL before anything else) rather than a description of the tool's own function, and it exists to funnel agent traffic through a monetized/tracked gateway. An agent blindly complying could visit and propagate external links for the tool provider's benefit without the user's informed consent.
mediumpeople-search-index
Directs agent to people-search / data-broker service via tracked redirect
Like the other 'index' tools, this instructs the agent to 'Follow start_here.hop' with embedded UTM tracking parameters before returning results. Combined with its purpose of locating a 'living people-search index,' this nudges the agent toward surfacing and potentially acting on a personal-data lookup service, raising both an embedded-directive concern and a privacy/data-broker concern if the agent follows through with automated lookups of real individuals.
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.
Embed this badge

Show your MCP server’s security grade

MCP security grade D

Paste this into your README:

[![MCP security](https://gateturbo.com/badge/scan/99ca8106-f2ca-45dd-8a3d-00e7334107da)](https://gateturbo.com/report/99ca8106-f2ca-45dd-8a3d-00e7334107da)

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