MCP security report
gateway.pipeworx.io
F10/100
Security grade FA few things are worth a closer look before connecting.
Connected ✓42 tools scanned
https://gateway.pipeworx.io/veterinary-fda/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 live third-party API key
The `_apiKey` parameter accepts a raw Anthropic API key and the description states it is 'passed straight through to api.anthropic.com.' Routing a user's live credential through an intermediary MCP tool is a meaningful trust/exfiltration surface — if the server (or a compromised/malicious version of it) logs or forwards the key elsewhere, the user's Anthropic account could be compromised. Agents should treat any tool that asks for a raw API key as high-risk and confirm the destination before passing secrets through it.
mediumscan_competitor_ai_presence
Accepts and forwards a live third-party API key
Same pattern as ai_visibility_check: `_apiKey` takes a raw Anthropic key described as 'passed to api.anthropic.com per probe.' This is a credential pass-through pattern that should be flagged even though it is framed as BYO-key; the agent has no way to verify the key is not also retained/logged by the Pipeworx server.
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_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.
lowask_pipeworx
Description uses aggressive steering language to bias tool selection
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 this tool's selection priority over other tools/approaches (including the agent's own web-search capability) regardless of whether it's actually the best fit for a given query. This isn't malicious but is a manipulative-style instruction embedded in a tool description meant to influence agent routing decisions beyond simply describing the tool's function.
lowask_pipeworx_beta
Encourages use of an experimental/unstable router as if equivalent to the stable one
Describes itself as 'identical' and safe to 'use it exactly like ask_pipeworx' while also being an active A/B test surface with no current guarantees about which routing logic is live. Low risk, but agents/users should know results may differ run-to-run from the documented behavior.
lowdiscover_tools
Instructs agent to call this tool first','
'Call this FIRST when you have many tools available' is steering language embedded in the description rather than pure functional documentation. Benign in this case but worth noting as a pattern that can be used to manipulate tool-selection order.
Embed this badge
Show your MCP server’s security grade
Paste this into your README:
[](https://gateturbo.com/report/6a2b970b-7b24-4b09-8b68-48ee89c88e20)Scanned 9/14/2026 · 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