Critical Risk →

uncollect_character

Remove a character from the current user's collection.

How to control uncollect_character ↓

What uncollect_character does on Bangumi TV MCP Service

AI agents call uncollect_character to permanently remove resources in Bangumi TV MCP Service — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.

Critical Risk

Why uncollect_character needs a policy

This tool irreversibly removes a character from a user's collection. While it may be reversible by re-adding the character, deletion/removal operations are classified as Destructive. The blast radius is medium as it only affects the current user's collection data.

From the tool's definition Remove a character from the current user's collection

Documented attack patterns abuse exactly the kind of access uncollect_character gives an agent:

How to control uncollect_character

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 uncollect_character:

policy.json
{
  "version": "1",
  "default": "deny",
  "hide": [
    "uncollect_character"
  ]
}

uncollect_character disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.

  1. Create a free account and register Bangumi TV MCP Service — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
RESTRICT THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about uncollect_character

What does the uncollect_character tool do? +

Remove a character from the current user's collection. It is categorised as a Destructive tool in the Bangumi TV MCP Service MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.

How do I enforce a policy on uncollect_character? +

Register the Bangumi TV MCP Service MCP server in PolicyLayer and add a rule for uncollect_character: 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.

What risk level is uncollect_character? +

uncollect_character is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.

Can I rate-limit uncollect_character? +

Yes. Add a rate_limit block to the uncollect_character 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.

How do I block uncollect_character completely? +

Set action: deny in the PolicyLayer policy for uncollect_character. 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.

What MCP server provides uncollect_character? +

uncollect_character 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.

Enforce policy on every Bangumi TV MCP Service tool call.

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.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.