AI agents call modelFieldRemove to permanently remove resources in Anki — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Removing a field from a model in Anki is destructive because it permanently deletes the field schema, causing data loss for all associated notes. This operation cannot be reversed and has significant blast radius—an agent could accidentally remove critical fields from shared decks. While not as severe as account-level destruction, it meets the Destructive threshold for irreversible data loss.
From the tool's definition Tool name 'modelFieldRemove' and description 'Removes a field from an existing model' indicate irreversible deletion of a model field, which cannot be undone and will affect all notes using that model.
Documented attack patterns abuse exactly the kind of access modelFieldRemove gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Anki, and nothing reaches the server without passing your rules. This is the rule we recommend for modelFieldRemove:
{
"version": "1",
"default": "deny",
"hide": [
"modelFieldRemove"
]
}modelFieldRemove disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.
Free to start. No card required.
Removes a field from an existing model. It is categorised as a Destructive tool in the Anki MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Anki MCP server in PolicyLayer and add a rule for modelFieldRemove: 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 Anki. Nothing to install.
modelFieldRemove is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the modelFieldRemove 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 modelFieldRemove. 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.
modelFieldRemove is provided by the Anki MCP server (ujisati/anki-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Anki, 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.
40 Anki tools catalogued and risk-classified — across an index of 43,000+ MCP servers.