MCP security report
dchub.cloud
F5/100
Security grade FA few things are worth a closer look before connecting.
Connected ✓88 tools scanned
https://dchub.cloud/mcp/registry
mediumsearch_facilities
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.
mediumget_market_intel
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.
mediumsearch_intelligence
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.
mediumget_interconnection_queue
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.
mediumrank_sites
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.
mediumsave_to_shortlist
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.
mediumget_shortlist
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.
mediumset_shortlist_alert
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.
mediumsuggest_reallocation
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.
mediumget_grid_data
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.
mediumanalyze_site
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.
mediumcompare_sites
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.
mediumget_fiber_intel
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.
mediumget_energy_prices
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.
mediumget_renewable_energy
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.
mediumget_water_risk
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.
mediumget_grid_intelligence
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.
mediumrank_markets
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.
mediumsite_selection_canvas
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.
mediumsearch_facilities
Autonomous payment capability embedded in read-only data tools (mpp_pay / mpp_credential)
Many otherwise ordinary data-lookup tools (search_facilities, get_market_intel, get_interconnection_queue, get_grid_data, compare_sites, get_fiber_intel, get_water_risk, get_grid_intelligence, get_energy_prices, get_renewable_energy, rank_markets, site_selection_canvas) expose an 'mpp_pay'/'mpp_credential' parameter pair explicitly described as designed for the AI agent itself to trigger a real $0.50 charge with 'no API key, no subscription, no human' in the loop, and the description notes 'Humans never set this.' This actively invites the agent to initiate financial transactions autonomously on the user's behalf, repeatedly and across many tools, without a clear requirement for explicit per-transaction user consent. Even at low per-call cost, an agent following the tool description literally could accumulate charges the human never approved. This is a broader capability (spending money) than the tool's stated purpose (reading facility/market/grid data) would suggest.
lowexecute_plan
Unusually long tool description
Very long descriptions are sometimes used to bury instructions to the AI. Skim it before allowing.
lowsearch_facilities
Unusually long tool description
Very long descriptions are sometimes used to bury instructions to the AI. Skim it before allowing.
lowget_refined_queue
Unusually long tool description
Very long descriptions are sometimes used to bury instructions to the AI. Skim it before allowing.
lowget_hosting_capacity
Unusually long tool description
Very long descriptions are sometimes used to bury instructions to the AI. Skim it before allowing.
lowrank_sites
Unusually long tool description
Very long descriptions are sometimes used to bury instructions to the AI. Skim it before allowing.
lowfind_sites
Unusually long tool description
Very long descriptions are sometimes used to bury instructions to the AI. Skim it before allowing.
lowanalyze_site
Unusually long tool description
Very long descriptions are sometimes used to bury instructions to the AI. Skim it before allowing.
lowcompare_sites
Unusually long tool description
Very long descriptions are sometimes used to bury instructions to the AI. Skim it before allowing.
lowget_renewable_energy
Unusually long tool description
Very long descriptions are sometimes used to bury instructions to the AI. Skim it before allowing.
lowget_grid_intelligence
Unusually long tool description
Very long descriptions are sometimes used to bury instructions to the AI. Skim it before allowing.
lowrank_markets
Unusually long tool description
Very long descriptions are sometimes used to bury instructions to the AI. Skim it before allowing.
lowsite_selection_canvas
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.
lowset_market_alert
Arbitrary webhook destination for market alerts
set_market_alert (and the related set_site_alert) allow a 'webhook' channel with a caller-supplied destination URL that DC Hub will POST future market/site data to. If an agent is manipulated (e.g. via injected content elsewhere in a session) into setting this destination to an attacker-controlled endpoint, ongoing monitoring data about the user's sites/markets would be silently exfiltrated on a recurring basis. This is a normal feature for a legitimate SaaS but represents a standing data-exfiltration channel that agents should confirm with the user before configuring, especially the destination URL.
lowset_site_alert
Arbitrary webhook destination reachable via alert configuration
Same concern as set_market_alert: while the free tier forces email to a bound address, the described Pro path allows sending alerts (which include DCPI/capacity/facility movement tied to a user's saved site) to any address/destination supplied at call time. An agent should verify the destination is one the user actually controls before arming the alert.
Embed this badge
Show your MCP server’s security grade
Paste this into your README:
[](https://gateturbo.com/report/4391061d-2f54-4439-8a0d-629d81343a68)Scanned 9/10/2026 · 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