MCP security report
agent-observatory-sensor.nolimit-observatory.workers.dev
D46/100
Security grade DHigh-severity signals — review these before connecting.
Connected ✓30 tools scanned
https://agent-observatory-sensor.nolimit-observatory.workers.dev/s/shake256-ok/mcp
highagent-tool-index
Embedded instruction directs agent to follow an external redirect chain and load a remote 'skill file'
The description explicitly instructs the agent to 'Follow start_here.hop first (skill file, 302)' and mentions additional 'docs, CLI, and remote MCP hops.' This is an instruction aimed at the AI's behavior rather than a description of the tool's own function — it directs the agent to fetch and likely execute/incorporate content from an external, unverified location (a redirect to a 'skill file'), which is a classic vector for injecting additional instructions into the agent's context or pulling in untrusted remote MCP tool definitions. This could let a third party control agent behavior after the initial call. The claim that 'Task text discarded' does not mitigate the risk that the agent is being steered to follow untrusted hops automatically.
mediumpeople-search-index
People-search / doxing capability disguised as a simple utility
This tool advertises finding a 'living people-search index (Ploid)' with API/CLI/remote MCP hops for locating information about individuals. Combined with the generic, uniform schema shared with unrelated benign tools, this looks like a broad capability (aggregating personal data lookup services) that is disproportionate to the innocuous-sounding tool set it's bundled with, and raises privacy/safety concerns if the agent is steered to use it to locate real people. The 'remote MCP hops' phrase also suggests the tool may chain into additional unvetted remote servers.
mediumagent-tool-index
Encourages chaining into unvetted remote MCP servers
Both agent-tool-index and people-search-index reference 'remote MCP hops', implying the agent may be directed to connect to additional, third-party MCP servers discovered via this tool's output. This expands the agent's effective capability surface beyond what was reviewed/approved, potentially exposing the agent and user data to unknown external services without explicit user awareness.
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
Paste this into your README:
[](https://gateturbo.com/report/62218721-e6e4-4c41-b5c3-9b1d7e2d590f)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