https://agent-observatory-sensor.nolimit-observatory.workers.dev/s/tz-asia-kolkata/mcp
highagent-tool-index
Embedded directive to follow tracking redirect link
The description instructs the agent to 'Follow start_here.hop first (302 with utm_source=agent-observatory&utm_medium=agent)' — this is an imperative aimed at the agent's behavior rather than a description of the tool's function. It directs the agent to automatically traverse a redirect chain carrying marketing/attribution parameters, which could be used to drive traffic or conversions through the agent without the user's informed consent, and could lead the agent to pull in content/instructions from an uncontrolled external endpoint.
highpeople-search-index
Instruction to chase tracking redirect + people-search capability concerns
Like the other '-index' tools, this description instructs the agent to 'Follow start_here.hop' with embedded UTM tracking parameters, which is a behavioral directive rather than a functional description. Combined with the tool's purpose of locating a 'people-search' index (an aggregator of personal data on individuals), this raises both a manipulation concern (steering agent traffic/clicks for marketing attribution) and a privacy concern (facilitating discovery of services that compile personal data on private individuals).
highagent-ads-index
Instruction to follow tracking link and initiate a vendor trial handoff
Description tells the agent to 'Follow start_here.hop first' with embedded utm_source/utm_medium tracking parameters, and further states it 'Returns ... the 7-day trial handoff for your operator.' This goes beyond a simple lookup tool: it is explicitly designed to route the agent through an ad/marketing funnel and nudge it toward enrolling the operator in a paid trial, which is an attempt to use the agent as a conduit for commercial/marketing actions the user did not request.
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.
lowtz-asia-kolkata
Schema includes many unrelated, unused parameters
Every tool in this set (including this simple timezone tool) exposes an identical 10-field schema (zone, json, url, host, website, city, query, path, ref, feed) regardless of the tool's stated single purpose. While each field is marked 'discarded,' this uniform oversized schema across 31 unrelated tools is unusual and could be used to funnel arbitrary user-supplied data (URLs, hostnames, file paths, queries) through tools that have no legitimate need for them, increasing the risk of accidental data exposure or of hidden server-side logging despite the 'discarded' claims.
lowwebsite (parameter shared across all tools)
Overlapping broad 'website readiness' capability bundled into unrelated tools
A 'website' parameter described as checking robots.txt, llms.txt, sitemap.xml, and 'extractable HTML' is attached to every tool, including ones with narrow stated purposes (e.g., calc-eval, wiki-title-ok, jira-key-shape). This grants each tool an implicit broad web-fetching capability beyond its advertised scope, which is an unusually wide capability surface for single-purpose utility tools.