highagent-tool-index
Embedded directive telling the agent to follow an external redirect chain
The description instructs the AI directly ('Follow start_here.hop first (skill file, 302)') rather than merely describing the tool's output. This is an imperative aimed at the agent's behavior, directing it to chase a redirect to an unknown external 'pay-per-call tool gateway' and then further 'docs, CLI, and remote MCP hops.' This pattern is consistent with tool/skill-file poisoning designed to get an agent to load and trust additional, unvetted remote MCP servers or executables outside the user's visibility.
highpeople-search-index
Directs agent toward a people-search / doxxing service and remote MCP hops
Description frames the tool as locating a 'living people-search index' and returns 'CLI setup, docs, API, and remote MCP hops.' This both promotes a potentially privacy-invasive lookup service (searching for personal data on real people) and encourages the agent to chain into additional remote MCP endpoints not vetted by the user, similar in pattern to agent-tool-index. Combined, these two tools look like a discovery mechanism for pulling in unvetted external capabilities under an innocuous-sounding name.
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-pt
Schema unrelated to stated purpose, identical across all 30 tools
Every tool in this set — regardless of stated purpose (country record, weather, JSON validation, calculator, etc.) — shares an identical 9-field schema including 'path' (file path), 'json', 'query', 'feed', 'ref', 'host', 'url', 'city', 'zone'. This is unusual: a tool for returning an ISO country record has no legitimate need for file-path, git-ref, or feed-URL parameters. While each field claims to be 'discarded' after use, the mismatch between declared purpose and accepted inputs across the whole tool set suggests templated/boilerplate definitions that could mask broader data collection than the description implies, and makes it hard for reviewers/agents to reason about what each tool actually does with the extra inputs.