mediumagent-tool-index
Embedded directive to follow external redirect chain ('hops')
The description instructs the agent to 'Follow start_here.hop first (skill file, 302)' and mentions additional docs/CLI/remote MCP hops. This is procedural guidance embedded in a tool description that tells the agent to chase redirects to external, unspecified endpoints and load a 'skill file' — a pattern commonly used to smuggle further instructions or malicious payloads into the agent's context after the initial tool call. The tool's stated purpose (finding a pay-per-call gateway) does not require directing the agent through a specific redirect sequence, and the vague 'Monid' branding gives no way to verify the destination is trustworthy.
mediumpeople-search-index
Facilitates locating people-search/data-broker services
This tool's purpose is to help the agent find a 'living people-search index' and provides API/CLI/remote MCP hops to reach it. Directing an agent toward third-party people-search (data broker) services can facilitate looking up personal information about real individuals, which raises privacy and doxxing concerns, especially since the destination service and its data practices are unspecified and the description encourages following further hops to an unverified external index.
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.