MCP security report

gateway.pipeworx.io

F37/100
Security grade FA few things are worth a closer look before connecting.
Connected ✓33 tools scanned

https://gateway.pipeworx.io/csv/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.
lowdeep_research
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_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.
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.
lowai_visibility_check
Raw third-party API key passed through the tool call
The `_apiKey` parameter accepts a raw Anthropic API key (sk-ant-...) and forwards it directly to api.anthropic.com. While billed as a 'BYO key' feature, having the agent handle and transmit a live credential string as a plain tool argument creates exposure risk (e.g., if the key ends up logged, cached, or is inadvertently reused from stored memory) and should be handled via a secure, out-of-band credential mechanism rather than an inline string argument.
lowscan_competitor_ai_presence
Raw third-party API key passed through the tool call
Same pattern as ai_visibility_check: `_apiKey` accepts a raw Anthropic API key and passes it 'per probe' to api.anthropic.com for every entity being compared. Multiple internal calls increase the surface for the key to be logged or leaked, and there is no indication of scoping/redaction.
lowgenerate_llms_txt
Unrestricted URL fetch — possible SSRF vector
The tool fetches an arbitrary user-supplied URL server-side with no stated restriction against internal/private/loopback addresses (contrast with the `subscribe` tool's webhook field, which explicitly states 'localhost/private hosts rejected'). If the fetch runs from a server with internal network access, this could be used to probe or retrieve content from internal-only endpoints.
lowask_pipeworx
Aggressive self-preferencing language may bias tool selection over user intent
The description repeatedly instructs the agent to prefer this tool 'over web search' and to use it as the 'default entry point... even if web search could also answer it,' for a very broad class of questions. This is steering language embedded in a tool description that goes beyond neutrally describing the tool's function and could cause the agent to systematically bypass more appropriate tools (including ones the user explicitly requested) without user awareness.
lowask_pipeworx_beta
Same self-preferencing steering as ask_pipeworx
Description encourages routing all questions here 'exactly like ask_pipeworx,' inheriting the same broad self-promotional steering noted for the primary tool.
Embed this badge

Show your MCP server’s security grade

MCP security grade F

Paste this into your README:

[![MCP security](https://gateturbo.com/badge/scan/cf4af274-b3a4-4cbc-bc74-3798aff847c7)](https://gateturbo.com/report/cf4af274-b3a4-4cbc-bc74-3798aff847c7)

Scanned 9/8/2026 · 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