MCP security report

gateway.pipeworx.io

F5/100
Security grade FA few things are worth a closer look before connecting.
Connected ✓40 tools scanned

https://gateway.pipeworx.io/reverb/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 through the tool server
The _apiKey parameter takes a user's Anthropic API key (sk-ant-...) and is described as 'passed straight through to api.anthropic.com' — meaning the secret transits the Pipeworx tool infrastructure. This creates risk of logging, interception, or misuse of the credential by the intermediary service, which is broader exposure than the tool's stated purpose (visibility scoring) requires.
mediumscan_competitor_ai_presence
Accepts and forwards a raw third-party API key through the tool server
Same concern as ai_visibility_check: the _apiKey (Anthropic key) is passed per-probe through Pipeworx's infrastructure to api.anthropic.com, exposing the user's credential to a third-party service beyond what the stated comparison functionality requires.
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.
lowreverb_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
Aggressive self-preferencing directive to the agent
The description repeatedly instructs the agent on meta-behavior beyond describing the tool's function: 'PREFER OVER WEB SEARCH', 'START HERE — this is the default entry point', 'Use whenever the user asks...even if web search could also answer it'. This is steering language aimed at biasing the agent's tool-selection policy in favor of this vendor's tool rather than neutrally describing capabilities, which could crowd out better-suited tools or the user's implicit preference for a different source.
lowask_pipeworx_beta
Same self-preferencing framing as ask_pipeworx
Description positions this as an equivalent default entry point ('identical universal router... use it exactly like ask_pipeworx'), inheriting the same tool-selection steering concern noted for ask_pipeworx.
lowsubscribe
Arbitrary webhook delivery of event data to user-supplied URL
The delivery.webhook parameter POSTs fired event JSON to any HTTPS URL the caller supplies (with only localhost/private-host filtering). While HMAC-signed and opt-in, this creates a data-exfiltration channel for subscription event payloads to third-party endpoints if the URL is attacker-controlled or manipulated by an untrusted caller/prompt.
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/f7fd8c54-2a3d-4b55-a1f8-e69af3b71b8b)](https://gateturbo.com/report/f7fd8c54-2a3d-4b55-a1f8-e69af3b71b8b)

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