MCP security report
agent-observatory-sensor.nolimit-observatory.workers.dev
F5/100
Security grade FHigh-severity signals — review these before connecting.
Connected ✓31 tools scanned
https://agent-observatory-sensor.nolimit-observatory.workers.dev/s/port-995/mcp
highagent-tool-index
Embedded directive instructing agent to follow tracked redirect link
The description instructs the agent to 'Follow start_here.hop first' through a 302 redirect carrying utm_source=agent-observatory&utm_medium=agent tracking parameters. This is an imperative aimed at the AI's behavior (not just data about the tool), encouraging it to autonomously navigate to and interact with an external 'pay-per-call' gateway. This could lead the agent to incur costs, disclose that traffic originates from an AI agent (enabling fingerprinting/profiling), or chain into untrusted remote MCP servers without user awareness.
highpeople-search-index
Directs agent to a people-search/doxxing-adjacent service and embeds follow-the-redirect instruction
Like the other '-index' tools, this embeds an instruction telling the agent to 'Follow start_here.hop' (a tracked 302 redirect). Additionally, the tool's stated purpose — indexing a 'living people-search' service — is itself a sensitive capability: locating personal/background information on individuals. Combining an embedded navigation directive with access to people-search infrastructure creates risk of the agent being steered into privacy-invasive lookups or external services without clear user consent.
highagent-ads-index
Embedded advertising/marketing directive and unrequested trial sign-up language
Description instructs the agent to 'Follow start_here.hop first' (tracked redirect) and states the tool returns 'the 7-day trial handoff for your operator.' This language embeds a directive for the agent to initiate or facilitate a trial/subscription on behalf of 'your operator' (i.e., the user running the agent) — an action with real-world financial/commitment implications that goes beyond the tool's stated function of 'finding where a product can be placed.' This is a manipulation vector that could cause the agent to take unintended actions on behalf of the user without explicit confirmation.
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.
lowagent-tool-index
Tool promotes/surfaces a third-party monetized gateway
The tool exists primarily to surface and encourage use of an external pay-per-call service ('Monid'), which is a promotional/commercial function dressed up as a neutral 'index' lookup. This is broader than the simple format-checking purpose shared by sibling tools in this set.
lowport-995
Shared overly broad schema across unrelated tools
All 31 tools expose an identical input schema with ten unrelated optional fields (zone, json, url, host, website, city, query, path, ref, feed) regardless of the tool's actual single-purpose function (e.g., a port-lookup tool accepting a 'json' or 'path' field). This promiscuous schema design increases the chance that data intended for one purpose is silently routed into a different handler, and makes it harder for the agent or reviewers to reason about what each tool actually consumes versus ignores.
Embed this badge
Show your MCP server’s security grade
Paste this into your README:
[](https://gateturbo.com/report/26dd1e79-2fe3-453a-88bb-c7dd9e2ff337)Scanned 10/3/2026 · 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