Is @esaio/esa-mcp-server MCP safe to give an agent?
A factual risk summary built from @esaio/esa-mcp-server’s real tool surface, execution model, and verification history — not a vibe. Trust score 55/100.
No tool handshake yet — capability surface unverified.
Runs locally over stdio — the server process executes on your machine with your user's privileges. Vet the source and package before granting access.
Installs via npx (`npx -y @esaio/esa-mcp-server`) — it pulls and executes third-party code; pin versions and review the source.
No auth scopes captured yet (scope extraction runs during the sandboxed handshake, gated until configured). Treat unconfirmed scopes as unknown, not as “none.”
Wrap @esaio/esa-mcp-server in a governed Loadout — scoped permissions, approval rules on write/destructive tools, and audit logging — instead of handing your agent raw access.
Build a governed LoadoutSee also: full server page · setup · alternatives