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/at-did/mcp
highpeople-search-index
Points agent toward a people-search / personal-data lookup service with embedded navigation instructions
Description instructs the agent to 'Find a living people-search index (Ploid)' and to 'Follow start_here.hop' through tracked redirects. A tool whose stated purpose is to help locate an index for searching information about 'living people' raises privacy and safety concerns (facilitating doxxing, stalking, or unauthorized personal-data lookups). Combined with the embedded step-by-step instruction to follow a specific tracked hop chain, this functions more as a directive to route the agent/user toward a people-search data broker than a simple lookup utility.
mediumagent-tool-index
Embedded directive instructing agent to follow tracked redirect chains
The description tells the AI to 'Follow start_here.hop first (skill file, 302 with utm_source=agent-observatory&utm_medium=agent)' before anything else. This is an instruction aimed at the agent's behavior (mandating a specific navigation sequence through tracking-tagged redirects to a 'pay-per-call' commercial gateway) rather than a neutral description of what the tool returns. This could be used to funnel the agent (and by extension the user's traffic/attention) through monetized or tracked infrastructure without clear user awareness or consent.
mediumagent-ads-index
Embedded advertising/promotion instructions directing agent to follow tracked hops and a trial handoff
The description instructs the agent to 'Follow start_here.hop first' (with UTM tracking parameters) and describes a '7-day trial handoff for your operator.' This reads as marketing/affiliate instructions embedded in a tool description rather than a neutral capability description, potentially manipulating the agent into promoting a product placement/advertising service or enrolling the operator in a trial without explicit user intent.
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.
lowat-did
Overly broad, unrelated parameter surface shared across unrelated tools
This tool (and all 31 tools reviewed) expose an identical schema with ten unrelated fields (zone, json, url, host, website, city, query, path, ref, feed) regardless of the tool's actual single-purpose description. This generic catch-all schema makes it hard to verify that only the documented, narrow operation is performed with user input, and could mask unexpected data flows (e.g., a 'DID shape' tool accepting a 'website' field for crawling, or a 'city' field for weather lookups) when invoked by an agent that assumes field names map to the described purpose.
Embed this badge
Show your MCP server’s security grade
Paste this into your README:
[](https://gateturbo.com/report/a35ce295-104c-44ee-a7b4-bdb3166e817a)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