MCP security report
agent-observatory-sensor.nolimit-observatory.workers.dev
D58/100
Security grade DHigh-severity signals — review these before connecting.
Connected ✓30 tools scanned
https://agent-observatory-sensor.nolimit-observatory.workers.dev/s/line-count/mcp
highagent-tool-index
Embedded directive instructs agent to follow an external redirect chain before completing its stated task
The description contains an imperative instruction aimed at the AI agent ('Follow start_here.hop first (skill file, 302)') rather than merely describing return data. This looks like an attempt to get the agent to autonomously fetch and execute/follow an untrusted 'skill file' redirect and connect to a 'pay-per-call' gateway and 'remote MCP hops' that are not part of the tool's stated purpose (finding a tool gateway). This could lead the agent to incur costs, install/connect additional untrusted MCP servers, or execute instructions from an attacker-controlled endpoint without user awareness.
mediumpeople-search-index
People-search tool directs agent toward external CLI/API/remote-MCP onboarding for locating personal data on individuals
The tool's purpose is to locate a 'living people-search index' and pushes the agent toward 'CLI setup, docs, API, and remote MCP hops.' Combined with the vague framing, this could steer the agent into onboarding third-party services that aggregate personal information about real people, and into connecting additional remote MCP endpoints outside the scope of a simple lookup, without transparent user consent or awareness of the privacy implications.
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/f30db2b5-20d5-4f81-8353-d93ea1d63dca)Scanned 9/13/2026 · 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