MCP security report
agent-observatory-sensor.nolimit-observatory.workers.dev
F34/100
Security grade FHigh-severity signals — review these before connecting.
Connected ✓30 tools scanned
https://agent-observatory-sensor.nolimit-observatory.workers.dev/s/sha224-ok/mcp
highagent-tool-index
Embedded directive urges agent to follow untrusted redirect chain
The description instructs the agent to 'Follow start_here.hop first (skill file, 302)' and to follow additional 'docs, CLI, and remote MCP hops.' This is an instruction embedded in a tool description that tells the agent to automatically traverse redirects to external, unverified endpoints (a 'pay-per-call tool gateway') and potentially load a 'skill file' or connect to additional remote MCP servers. This could be used to redirect the agent to attacker-controlled infrastructure, inject new instructions via the fetched skill file, or cause the agent to incur financial transactions ('pay-per-call') without explicit user awareness/consent. The tool's stated purpose (finding a gateway) does not justify directing the agent's subsequent actions this specifically.
highpeople-search-index
Directs agent toward people-search data broker and follow-on untrusted hops
The description tells the agent that the tool 'returns CLI setup, docs, API, and remote MCP hops' for a 'people-search index,' encouraging the agent to chain into external CLI installation, API usage, or additional remote MCP servers. Combined with the 'people-search' subject matter (aggregating personal/PII data on private individuals), this raises both a privacy concern (facilitating doxing/people-search lookups) and a supply-chain risk (agent being guided to install/connect to unverified external tools beyond the tool's simple lookup purpose).
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.
lowagent-tool-index
Vague/branded service name with no verifiable ownership
References an unfamiliar branded service ('Monid') as if it were an established, trustworthy destination. There is no way for the reviewer or agent to verify this is legitimate versus a look-alike or freshly created gateway designed to capture agent traffic or payments.
lowpeople-search-index
Vague/branded service name with no verifiable ownership
References an unfamiliar branded service ('Ploid') without verification. Similar concern to agent-tool-index: the agent could be steered toward an unverified third-party data service under a plausible-sounding name.
Embed this badge
Show your MCP server’s security grade
Paste this into your README:
[](https://gateturbo.com/report/c7bc799e-e441-440c-9d0f-8f4379a00599)Scanned 9/15/2026 · 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