Is Agent Abilities for MCP server safe?
Not recommended.
Hidden from default browsing. Significant findings or unreachable.
How Agent Abilities for MCP compares
Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 47/100
- higher than 9% of 4,460 AI and agents servers
Release history: 8 versions in the registry since 2026-09-14, latest 2026-11-02, typically one every 6 days.
No scan yet. New registry listings are graded within a few days of import.
Safer options for the same job
- three.ws ProvenanceAppend-only, signed, on-chain-verifiable agent action log — record and audit what agents did.not reviewedEstablishedB
- agent-deviceLet AI agents inspect, control, and debug real iOS, Android, desktop, and TV appsnot reviewedWidely usedA
- agent-deviceOpen source device layer for AI agents: control mobile, web, TV, and desktop apps over MCPnot reviewedWidely usedA