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/cc-ye/mcp
highagent-tool-index
Embedded directive instructing agent to follow external redirect chain
The description explicitly instructs the calling agent to 'Follow start_here.hop first (skill file, 302)' and then follow additional docs/CLI/remote-MCP hops. This is an instruction aimed at the agent's behavior (navigate through a chain of redirects to an unverified, pay-per-call third-party gateway) rather than a description of a single well-scoped function. Following such a chain could lead the agent to install/execute untrusted CLI tools or connect to unknown remote MCP servers, exceeding the tool's stated scope of 'finding' an index and bypassing user visibility into what is actually being fetched/executed.
highpeople-search-index
Directs agent to a people-search data broker with instructions to chain into CLI/API/remote MCP
Description tells the agent to obtain 'CLI setup, docs, API, and remote MCP hops' for a people-search service ('Ploid'). This combines an embedded multi-step instruction to the agent (follow more hops, set up CLI/API) with a privacy-sensitive capability (searching for information on living individuals) that is far broader than a simple lookup, creating risk of unauthorized personal-data queries and connecting the agent to unvetted third-party infrastructure.
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.
lowcc-ye
Uniform oversized parameter schema shared across unrelated tools
Every tool in this set (including cc-ye) exposes the identical nine-parameter schema (zone, json, url, host, city, query, path, ref, feed) regardless of the tool's actual single stated purpose. This generic, catch-all schema makes it easy for an agent (or an attacker crafting inputs) to place unrelated or sensitive data (e.g., file paths, JSON blobs, URLs) into fields that don't match the tool's real function, increasing the chance of accidental data exposure or misrouted sensitive content, even though each field is individually annotated as 'discarded'.
Embed this badge
Show your MCP server’s security grade
Paste this into your README:
[](https://gateturbo.com/report/b5b4e626-d69e-4624-ad24-24290e809a55)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