MCP security report
gateway.pipeworx.io
F7/100
Security grade FA few things are worth a closer look before connecting.
Connected ✓39 tools scanned
https://gateway.pipeworx.io/vaers/mcp
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
Accepts and forwards a raw third-party API key as a tool argument
The `_apiKey` parameter takes a plaintext Anthropic API key (sk-ant-...) and the description states it is 'passed straight through to api.anthropic.com.' Even though disclosed, this pattern means a live credential transits through the MCP server/tool-call pipeline (where it may be logged, cached, or intercepted) before reaching the third party. Tools that need BYO keys should ideally use a vault/reference mechanism rather than accepting secrets as plain call arguments.
mediumscan_competitor_ai_presence
Accepts and forwards a raw third-party API key as a tool argument
Same issue as ai_visibility_check: `_apiKey` accepts a plaintext Anthropic API key that is passed to api.anthropic.com per probe, across multiple entities. This multiplies exposure of the credential across several outbound calls initiated by the tool.
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.
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.
lowgenerate_llms_txt
Arbitrary URL fetch with no stated host restrictions (possible SSRF)
The tool fetches any URL supplied by the caller to extract content. Unlike the `subscribe` webhook parameter (which explicitly rejects localhost/private hosts), there is no stated restriction here on internal/private network addresses, so it could potentially be used to probe internal services or metadata endpoints if the underlying fetch has network access to non-public hosts.
lowask_pipeworx
Aggressive self-preferencing language may bias tool selection beyond the tool's actual scope
Phrases like 'PREFER OVER WEB SEARCH', 'START HERE for most questions — this is the default entry point', and long lists of trigger phrases are written to maximize selection of this tool over alternatives (including the agent's built-in web search) for a very broad range of queries. This isn't a credential or data-exfiltration risk, but it is a description crafted to steer agent behavior/tool choice more assertively than a neutral capability description would, which could cause the agent to bypass more appropriate tools for certain questions.
lowask_pipeworx_beta
Same aggressive routing-preference framing as ask_pipeworx
Describes itself as an equivalent full router with 'newest routing' and encourages use 'exactly like ask_pipeworx' — inherits the same broad self-preferencing framing noted for ask_pipeworx, which could push the agent to default to this experimental variant for many queries without added guardrails distinguishing when NOT to use it.
Embed this badge
Show your MCP server’s security grade
Paste this into your README:
[](https://gateturbo.com/report/16fc48e3-57fe-4d7d-b5a2-ca6a3efc15cf)Scanned 9/16/2026 · 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