AI agents use update_subject_collection to create or update resources in Bangumi TV MCP Service — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Bangumi TV MCP Service environment.
This tool appears to modify user collection state (e.g., adding/removing anime from a watchlist or collection), which is a Write operation. It is reversible (user can undo the collection change), so not Destructive.
From the tool's definition Tool name 'update_subject_collection' indicates modification of a collection state associated with a subject.
Documented attack patterns abuse exactly the kind of access update_subject_collection gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Bangumi TV MCP Service, and nothing reaches the server without passing your rules. This is the rule we recommend for update_subject_collection:
{
"version": "1",
"default": "deny",
"tools": {
"update_subject_collection": {
"limits": [
{
"counter": "update_subject_collection_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}update_subject_collection 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.
update_subject_collection. It is categorised as a Write tool in the Bangumi TV MCP Service MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Bangumi TV MCP Service MCP server in PolicyLayer and add a rule for update_subject_collection: 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 Bangumi TV MCP Service. Nothing to install.
update_subject_collection 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_subject_collection 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_subject_collection. 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_subject_collection is provided by the Bangumi TV MCP Service MCP server (ukenn2112/bangumimcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Bangumi TV MCP Service, 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.
46 Bangumi TV MCP Service tools catalogued and risk-classified — across an index of 43,000+ MCP servers.