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/lang-th/mcp
highagent-tool-index
Embedded workflow instruction directing agent to follow untrusted redirect chains
The description tells the calling agent to 'Follow start_here.hop first (skill file, 302)' and then follow additional 'docs, CLI, and remote MCP hops.' This is an instruction aimed at the AI's behavior rather than a description of a single well-defined function. It steers the agent into fetching and executing content from an external, unverified location and potentially connecting to a remote MCP server it doesn't already trust — a classic vector for prompt injection, capability expansion, or SSRF-style redirection, especially since it references a 'pay-per-call' gateway that could incur costs or exfiltrate the task context to a third party.
mediumpeople-search-index
People-search/data-broker discovery tool with remote-hop instructions
This tool locates a 'living people-search index' and returns API/CLI/remote MCP hops for it, again instructing the agent to follow external links to add new capabilities. Combining a personal-data lookup service with instructions to connect to remote, unverified MCP endpoints raises both a privacy concern (facilitating lookup of individuals' personal information) and a supply-chain/prompt-injection concern (agent being directed to load additional tool servers from an uncontrolled source).
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-th
Schema unrelated to stated purpose
This tool is described as returning an ISO 639 language tag, yet its input schema exposes nine unrelated parameters (zone, json, url, host, city, query, path, ref, feed) that have nothing to do with language tags. This pattern is repeated identically across all 30 tools in this set, suggesting a templated/boilerplate schema rather than one scoped to the tool's actual function. While not directly harmful, it could let an agent pass sensitive data (URLs, paths, queries) into a tool whose behavior for those fields is undocumented and unverifiable, and makes it hard to reason about what each tool actually does with the supplied data.
Embed this badge
Show your MCP server’s security grade
Paste this into your README:
[](https://gateturbo.com/report/02af6a4d-1537-440b-9dac-e8e9aed21c98)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