Creates a new model (note type). Returns the created model object.
AI agents use createModel to create or update resources in Anki — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Anki environment.
Creating a model is a write operation that adds a new note type definition to Anki's schema. This is reversible (the model can be deleted) and has no destructive side effects. The severity is medium because while it modifies the system's structure, it does not delete data, execute arbitrary code, or affect financial systems. Misuse could clutter the database with unwanted models but poses limited blast radius.
From the tool's definition Tool description states it 'Creates a new model (note type)' — a create operation that modifies the Anki database by adding a new reversible data structure.
Documented attack patterns abuse exactly the kind of access createModel 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 createModel:
{
"version": "1",
"default": "deny",
"tools": {
"createModel": {
"limits": [
{
"counter": "createmodel_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}createModel 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.
Creates a new model (note type). Returns the created model object. It is categorised as a Write tool in the Anki MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Anki MCP server in PolicyLayer and add a rule for createModel: 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.
createModel 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 createModel 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 createModel. 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.
createModel 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.