mediumsubscribe
References secrets or data exfiltration
The tool text references credentials, environment variables, or sending data elsewhere. This can be legitimate, but review what this tool actually accesses.
mediumai_visibility_check
References secrets or data exfiltration
The tool text references credentials, environment variables, or sending data elsewhere. This can be legitimate, but review what this tool actually accesses.
mediumscan_competitor_ai_presence
References secrets or data exfiltration
The tool text references credentials, environment variables, or sending data elsewhere. This can be legitimate, but review what this tool actually accesses.
mediumai_visibility_check
Tool accepts and forwards a raw API key
The `_apiKey` parameter asks the agent to pass a plaintext Anthropic API key (sk-ant-...) through this third-party MCP tool so it can be 'passed straight through to api.anthropic.com'. Any MCP server that handles this argument sees the user's live credential in cleartext; there is no way for the calling agent/user to verify the key is actually only forwarded to Anthropic and not logged, cached, or exfiltrated elsewhere. Tools should not require callers to hand over secret credentials as call arguments — a redirect/OAuth flow or server-side stored key would avoid this exposure.
mediumscan_competitor_ai_presence
Tool accepts and forwards a raw API key
Same issue as ai_visibility_check: the `_apiKey` field takes the user's Anthropic API key directly as a tool argument and states it is 'passed to api.anthropic.com per probe.' This pattern lets any MCP-server-side logging or compromise capture live user credentials; a bring-your-own-key workflow should not require transmitting the secret through the calling agent/tool-call surface at all.
lowdeep_research
Unusually long tool description
Very long descriptions are sometimes used to bury instructions to the AI. Skim it before allowing.
lowcompany_facts
Unusually long tool description
Very long descriptions are sometimes used to bury instructions to the AI. Skim it before allowing.
lowbet_research
Unusually long tool description
Very long descriptions are sometimes used to bury instructions to the AI. Skim it before allowing.
lowpolymarket_arbitrage
Unusually long tool description
Very long descriptions are sometimes used to bury instructions to the AI. Skim it before allowing.
lowpolymarket_edges
Unusually long tool description
Very long descriptions are sometimes used to bury instructions to the AI. Skim it before allowing.
lowpolymarket_kalshi_spread
Unusually long tool description
Very long descriptions are sometimes used to bury instructions to the AI. Skim it before allowing.
lowkalshi_weather_edge
Unusually long tool description
Very long descriptions are sometimes used to bury instructions to the AI. Skim it before allowing.
lowrelease_calendar_markets
Unusually long tool description
Very long descriptions are sometimes used to bury instructions to the AI. Skim it before allowing.
lowgeorgia_heritage_search
Unusually long tool description
Very long descriptions are sometimes used to bury instructions to the AI. Skim it before allowing.
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.
lowask_pipeworx
Directive language biases the agent's tool selection beyond describing functionality
Phrases like 'PREFER OVER WEB SEARCH', 'START HERE for most questions — this is the default entry point', and instructing the agent to use this tool for a huge range of query types read as an attempt to steer the agent's general tool-choice policy (not just describe this tool's function), which could crowd out more appropriate tools (including the user's own web search or other MCP servers) even when they'd serve the user better. This is a soft manipulation pattern rather than a stated capability description.
lowask_pipeworx_beta
Inherits directive 'use this by default' framing
Description tells the agent to 'use it exactly like ask_pipeworx when you want the newest routing,' reinforcing the same broad default-tool-selection push seen in ask_pipeworx, encouraging routine use of an explicitly labeled experimental/beta router for production answers.