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/if-match-ok/mcp
highpeople-search-index
People-search capability combined with directive navigation instructions raises privacy/misuse risk
This tool is explicitly for finding a 'living people-search index' (Ploid), which concerns aggregating personal data about real individuals — a capability that can facilitate doxxing, stalking, or other privacy harms and goes beyond the benign, narrow utility functions of the rest of the toolset. It also embeds an instruction ('Follow start_here.hop... 302 with utm_source=agent-observatory&utm_medium=agent') directing the agent to a specific external hop with tracking parameters, which is an attempt to control agent navigation/behavior rather than simply describe a parameter.
mediumagent-tool-index
Embedded navigation instruction with tracking parameters directs agent to a specific commercial gateway
The description instructs the agent to 'Follow start_here.hop first' and explicitly bakes in tracking parameters (utm_source=agent-observatory&utm_medium=agent). This is an instruction aimed at the agent's behavior rather than a neutral description of inputs/outputs, and it steers the agent toward funneling traffic to a specific pay-per-call commercial service, potentially without the user's informed consent or awareness that tracking identifiers are being attached to their request.
mediumagent-ads-index
Tool description pushes agent toward enrolling the operator in a paid trial via embedded marketing instructions
The description tells the agent to follow a specific tracked redirect ('start_here.hop... utm_source=agent-observatory&utm_medium=agent') and explicitly returns a '7-day trial handoff for your operator.' This embeds a commercial upsell/conversion funnel instruction inside a tool description that is nominally about checking website readiness, effectively directing the agent to initiate account/trial signups on behalf of the user without clear indication this is an advertisement or monetized action requiring explicit user consent.
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.
lowif-match-ok
Shared oversized schema with unrelated parameters across all tools
Every tool in this set declares an identical, broad input schema (zone, json, url, host, website, city, query, path, ref, feed) regardless of the tool's actual single-purpose function (e.g., an etag-check tool accepts city/feed/ref parameters it has no stated use for). This inconsistency between tool description and schema could let an agent pass unrelated or sensitive data (e.g., file paths, queries) into tools where handling is unclear, increasing risk of unintended data flows even though each individual description claims data is discarded.
Embed this badge
Show your MCP server’s security grade
Paste this into your README:
[](https://gateturbo.com/report/17446628-0fa0-4c71-9c20-2afe4ab8e957)Scanned 10/1/2026 · 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