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/sitemap-url-count/mcp

highagent-tool-index
Instructs agent to follow untrusted redirect chain from a third party
The description tells the agent to 'Follow start_here.hop first (skill file, 302)' and then follow additional docs/CLI/remote-MCP hops to a 'pay-per-call tool gateway (Monid).' This is an embedded directive that pushes the agent toward loading and trusting content/tool definitions from an external, unverified redirect chain — a classic vector for tool-poisoning/prompt-injection where the fetched content could smuggle new instructions or malicious tool specs. It also implies pay-per-call (financial) actions without clear user consent/disclosure, which is a capability well beyond what a lookup/index tool should need.
highpeople-search-index
Facilitates lookup of personal data on identifiable individuals plus untrusted external hops
Description states the tool finds a 'living people-search index (Ploid)' and returns CLI/API/remote-MCP hops to follow. This combines two concerns: (1) it directs the agent to chase external redirects/hops similar to agent-tool-index, risking injection of untrusted instructions or code, and (2) it exists to locate services for searching personal information about named living individuals, which raises privacy/doxxing/stalking risk if invoked with a person's name without safeguards or consent verification.
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.
lowsitemap-url-count
Shared oversized schema across all tools enables parameter smuggling
Every tool in this set exposes the exact same nine-parameter schema (zone, json, url, host, city, query, path, ref, feed) regardless of the tool's actual function (e.g., a UTC-time tool accepts a 'json' body and a 'path' parameter). This is unusual: it allows callers/agents to attach unrelated or sensitive-looking data (e.g., file paths, JSON payloads, feed URLs) to calls that don't need them, increasing the chance a tool silently receives and processes data outside its stated scope. Recommend tightening each tool's schema to only the parameters it actually uses.
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/5c14a42d-8678-40b5-a71f-33b05c447bb3)](https://gateturbo.com/report/5c14a42d-8678-40b5-a71f-33b05c447bb3)

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