19 tools. 7 can modify or destroy data without limits.
1 destructive tool with no built-in limits. Policy required.
Last updated:
Financial operations (create_payment_qrcode) can move real money. An agent caught in a loop could drain accounts before anyone notices.
Write operations (submit_task, sync_generate_image, sync_generate_video) modify state. Without rate limits, an agent can make hundreds of changes in seconds — faster than any human can review or revert.
Execute tools (parse_video) trigger processes with side effects. Builds, notifications, workflows — all fired without throttling.
create_payment_qrcode:
rules:
- action: deny Financial tools should be explicitly enabled per use case, not open by default.
submit_task:
rules:
- rate_limit: 30/hour Prevents bulk unintended modifications from agents caught in loops.
daily_check_in:
rules:
- rate_limit: 60/minute Controls API costs and prevents retry loops from exhausting upstream rate limits.
Yes. The xSkill AI server exposes 1 financial tools including create_payment_qrcode. Without a policy, an autonomous agent can call these with no spend caps, no rate limits, and no approval flow. Intercept lets you block financial tools by default or set per-tool rate limits.
The xSkill AI server has 5 write tools including submit_task, sync_generate_image, sync_generate_video. Set rate limits in your policy file -- for example, rate_limit: 10/hour prevents an agent from making more than 10 modifications per hour. Intercept enforces this at the transport layer.
19 tools across 4 categories: Execute, Financial, Read, Write. 12 are read-only. 7 can modify, create, or delete data.
One line change. Instead of running the xSkill AI server directly, prefix it with Intercept: intercept -c hexiaochun-xskill-ai.yaml -- npx -y @hexiaochun/xskill-ai. Download a pre-built policy from policylayer.com/policies/hexiaochun-xskill-ai and adjust the limits to match your use case.
Starter policies available for each. Same risk classification, same one-command setup.
Deterministic policy on every MCP tool call. Per-identity grants. Full audit log.