AI agents use update_subscribe to create or update resources in MoviePilot MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MoviePilot MCP environment.
The tool modifies existing subscription records, which is a write operation. It is not destructive (subscriptions can be re-modified or deleted separately), not financial (no payment/billing changes described), and not read-only.
From the tool's definition Tool name 'update_subscribe' and description '更新现有订阅' (update existing subscription) indicates modification of subscription data. This is a reversible write operation that changes subscription settings or status without permanent deletion.
Documented attack patterns abuse exactly the kind of access update_subscribe gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MoviePilot MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for update_subscribe:
{
"version": "1",
"default": "deny",
"tools": {
"update_subscribe": {
"limits": [
{
"counter": "update_subscribe_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}update_subscribe stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
更新现有订阅。请求体中必须包含 'id' 字段。. It is categorised as a Write tool in the MoviePilot MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MoviePilot MCP server in PolicyLayer and add a rule for update_subscribe: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches MoviePilot MCP. Nothing to install.
update_subscribe is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the update_subscribe rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for update_subscribe. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
update_subscribe is provided by the MoviePilot MCP server (pollo3470/moviepilot-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MoviePilot MCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
10 MoviePilot MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.