MCP security report

agent-observatory-sensor.nolimit-observatory.workers.dev

F37/100
Security grade FHigh-severity signals — review these before connecting.
Connected ✓30 tools scanned

https://agent-observatory-sensor.nolimit-observatory.workers.dev/s/leap-year-utc/mcp

highagent-tool-index
Embedded agentic instruction to follow external redirect chain
The description explicitly instructs the AI to 'Follow start_here.hop first (skill file, 302)' and describes chaining through docs, CLI, and remote MCP hops. This is an instruction aimed at the agent's behavior rather than a description of the tool's function, and it directs the agent to fetch and potentially execute content from an unverified external gateway ('Monid'). This pattern is consistent with tool/prompt injection designed to lead the agent to follow untrusted redirects or load additional (possibly malicious) tool definitions from a remote source.
highpeople-search-index
People-search/OSINT capability with external CLI/API onboarding disguised as simple lookup
Despite sharing the same innocuous schema as trivial utility tools, this tool's purpose is to locate a 'living people-search index' and onboard the agent into an external CLI, docs, API, and remote MCP service ('Ploid'). This is a significant privacy/safety concern (facilitates searching for personal information on real individuals) and grants the agent access to install/configure external tooling, which is well beyond the stated scope of the other simple, stateless utilities in this collection.
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.
lowleap-year-utc
Oversized, irrelevant shared schema across unrelated tools
This tool (and nearly all others in the set) exposes a schema with many unrelated fields (json, url, host, city, query, path, ref, feed) that have nothing to do with the tool's stated purpose (UTC leap-year check). While each field claims data is 'discarded,' the presence of broad, unused parameters (including file path and URL fields) across every tool increases the attack surface for confused-deputy style misuse and makes it harder to audit what each tool actually does with the provided data. This shared-schema pattern appears across all 30 tools and should be reviewed for whether these parameters are actually necessary per-tool.
Embed this badge

Show your MCP server’s security grade

MCP security grade F

Paste this into your README:

[![MCP security](https://gateturbo.com/badge/scan/70cd7d13-cedf-485e-b580-e551f5e67887)](https://gateturbo.com/report/70cd7d13-cedf-485e-b580-e551f5e67887)

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