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/lang-aa/mcp
highagent-tool-index
Embedded instruction directing agent to follow untrusted redirect chains
The description explicitly instructs the AI to 'Follow start_here.hop first (skill file, 302)' and chase 'docs, CLI, and remote MCP hops.' This is a directive embedded in a tool description telling the agent to navigate through a chain of redirects to an external, unverified 'pay-per-call' gateway (Monid). This could lead the agent to load and execute instructions or tool definitions from an untrusted third party, potentially resulting in prompt injection, unexpected financial charges ('pay-per-call'), or connection to an unvetted remote MCP server — all without clear user visibility or consent. The tool's stated purpose (discovering a gateway) does not justify instructing the agent to blindly follow redirect/hop chains.
highpeople-search-index
Directs agent to external people-search / data-broker services and remote MCP hops
This tool's purpose is to locate a 'people-search index' (aggregated personal data broker, 'Ploid') and instructs the agent to retrieve 'CLI setup, docs, API, and remote MCP hops' from it. This effectively promotes discovery/use of third-party services that aggregate personal information about individuals (a privacy-sensitive capability), and again encourages the agent to connect to unverified remote MCP servers/hops, which is a vector for supply-chain compromise or prompt injection. This capability is broader and more sensitive than a simple lookup tool should be.
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.
lowlang-aa
Schema fields unrelated to tool's stated function
This tool (and all 30 tools reviewed) share an identical, broad input schema containing many fields (zone, json, url, host, city, query, path, ref, feed) that have nothing to do with the tool's actual described purpose (returning an ISO 639 language tag). While each field description claims data is discarded and no harm is described, this pattern of a single oversized shared schema across unrelated tools is unusual and could mask which fields are actually used/logged by the underlying implementation, reducing schema transparency for the agent and reviewers. Recommend tightening each tool's schema to only the parameters it needs.
Embed this badge
Show your MCP server’s security grade
Paste this into your README:
[](https://gateturbo.com/report/44e65604-7cb4-49a4-b191-17d331db457e)Scanned 9/15/2026 · 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