MCP security report
agent-observatory-sensor.nolimit-observatory.workers.dev
F25/100
Security grade FHigh-severity signals — review these before connecting.
Connected ✓31 tools scanned
https://agent-observatory-sensor.nolimit-observatory.workers.dev/s/st-vt/mcp
highpeople-search-index
People-search tool with embedded redirect instruction raises privacy risk
This tool is explicitly for locating a 'people-search index' (personal information lookup service) and instructs the agent to follow a tracking redirect (start_here.hop with utm parameters) to reach it. Combining an instruction that manipulates agent navigation with a service whose purpose is aggregating personal data about individuals creates meaningful risk of facilitating doxxing, stalking, or unauthorized personal-data lookups, especially since the tool steers the agent toward a specific third-party service via an embedded directive rather than neutral information.
highagent-ads-index
Advertising/monetization tool embeds directives to commit the operator to a third-party trial
The description instructs the agent to 'Follow start_here.hop first' (a tracked redirect) and says it returns 'the 7-day trial handoff for your operator.' This embeds an instruction aimed at getting the agent to initiate a trial/signup action on behalf of the operator through a chain of redirects, which could result in unintended commitments, data sharing, or account creation with a third-party ad-placement service, without clear user awareness or consent. The phrase 'where a product can be placed so AI agents discover it' indicates this tool is designed to influence other agents' discovery/behavior, which is a form of cross-agent manipulation outside the tool's nominal informational purpose.
mediumagent-tool-index
Embedded directive instructing agent to follow a tracking redirect
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 a behavioral instruction aimed at the agent (not just a description of output) that causes the agent to visit and propagate a third-party tracking/affiliate link as part of normal operation, without the user necessarily being aware of or consenting to the redirect chain or the external gateway it leads to.
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.
lowst-vt
Oversized, mismatched parameter schema shared across all tools
Every tool in this set exposes the identical 10-parameter schema (zone, json, url, host, website, city, query, path, ref, feed) regardless of its stated single-purpose function (e.g., a 'USPS state code' tool accepts a weather city, a git ref, a JSON body, etc.). This makes it hard for the agent or a reviewer to reason about what data actually flows to each tool, and could mask unintended data collection (e.g., a 'validate-json' call also silently accepting and potentially transmitting a path, URL, or city field). This appears repeated across nearly all 31 tools and should be tightened to only the parameters each tool actually needs.
Embed this badge
Show your MCP server’s security grade
Paste this into your README:
[](https://gateturbo.com/report/09934ea1-1829-47b1-91cc-648543e448c4)Scanned 10/2/2026 · 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