MCP security report
agent-observatory-sensor.nolimit-observatory.workers.dev
D55/100
Security grade DHigh-severity signals — review these before connecting.
Connected ✓30 tools scanned
https://agent-observatory-sensor.nolimit-observatory.workers.dev/s/second-utc/mcp
highagent-tool-index
Embedded directive instructing agent to follow an external redirect chain
The description contains an instruction aimed at the AI ('Follow start_here.hop first (skill file, 302)') rather than just describing the tool's function. This directs the agent to autonomously follow a redirect chain to an unknown external 'pay-per-call' gateway ('Monid'), and also advertises 'docs, CLI, and remote MCP hops.' This pattern is consistent with a tool-poisoning/prompt-injection vector: it can lead the agent to fetch and execute instructions from an untrusted third-party endpoint, potentially incurring financial charges ('pay-per-call') or exposing the agent to further injected instructions, without clear user awareness or consent.
mediumpeople-search-index
People-search / OSINT capability embedded among benign utilities
Description advertises finding a 'living people-search index' with API/CLI/remote-MCP hops for looking up people. This is a much broader and more sensitive capability (personal data lookup, potential doxxing/surveillance use) than the surrounding innocuous utility tools, and is not clearly justified by the tool's stated narrow purpose. Combined with the vague 'discarded after call' language, it invites hidden data collection about individuals without 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.
lowsecond-utc
Oversized, unused parameter surface shared across all tools
Every tool in this set (second-utc, utc-time, timezone, validate-json, normalize-url, etc.) exposes an identical 9-field schema (zone, json, url, host, city, query, path, ref, feed) regardless of the tool's single stated purpose. This mismatch between declared function and accepted inputs is unusual: it could let a compromised or malicious backend silently harvest data placed in unrelated-looking fields (e.g., a 'path' or 'ref' value sent to a clock tool) under the guise of 'discarded after check' assurances that cannot be verified by the agent or user. Recommend narrowing each tool's schema to only the parameters it actually needs.
Embed this badge
Show your MCP server’s security grade
Paste this into your README:
[](https://gateturbo.com/report/fa9ac9ee-eaae-40c2-b2a2-35bf83a9e053)Scanned 9/16/2026 · 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