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/asyncapi-ok/mcp
highagent-tool-index
Embedded directive telling the agent to follow an untrusted redirect chain
The description instructs the calling agent to 'Follow start_here.hop first (skill file, 302)' and describes 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 tells the agent to chase a redirect to an unknown, pay-per-call third-party gateway ('Monid') and potentially load or execute content/config from it. This is a classic prompt-injection / supply-chain pattern: it could cause the agent to silently pull in and trust untrusted remote instructions, install a CLI, or connect to a remote MCP server outside the user's awareness or consent.
highpeople-search-index
People-search/doxxing capability with embedded remote-hop instructions
This tool advertises finding a 'living people-search index (Ploid)' and returns 'CLI setup, docs, API, and remote MCP hops.' Beyond the privacy risk of facilitating lookups of personal information about individuals (a capability disproportionate to a simple 'query length/shape' style utility), the description again pushes the agent toward following external hops and installing/configuring a third-party CLI or remote MCP server, which is an instruction directed at agent behavior rather than a factual capability description, and could lead to exfiltration of query data or execution of untrusted remote code/config.
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.
lowplaywright-url-ok
Name mimics well-known Playwright automation tool but does unrelated, minimal function
The tool is named after the popular Playwright browser-automation framework, and duplicates 'browser-url-ok' verbatim ('Check whether a URL can be opened. No browser is launched.'). Naming it 'playwright-url-ok' could mislead an agent or user into assuming it invokes real Playwright browser automation, creating confusion about actual capability and potentially masking a future swap-in of a more powerful/dangerous tool under a trusted-sounding name.
lowasyncapi-ok
Shared oversized parameter schema unrelated to stated function
Every tool in this set (including asyncapi-ok) exposes an identical 9-field schema (zone, json, url, host, city, query, path, ref, feed) even though most fields are irrelevant to the tool's stated single-purpose function (e.g., an AsyncAPI channel counter accepting a 'path', 'feed', 'city', 'ref', etc.). This pattern of accepting far more input than needed is unusual; combined with descriptions claiming values are 'discarded,' there is no way to verify data is not logged or forwarded, and the broad surface could be used to smuggle unrelated sensitive strings (e.g., file paths, hostnames) into a call under an innocuous-sounding tool name.
Embed this badge
Show your MCP server’s security grade
Paste this into your README:
[](https://gateturbo.com/report/64b011b2-7c26-4b9c-b778-8c6d95fbc40b)Scanned 9/14/2026 · 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