AI agents call get_model_names to retrieve information from Anki MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a query operation that retrieves metadata about existing note type models. It does not create, modify, delete, or execute any operations on data. The blast radius of misuse is minimal, as listing available models poses no risk to data integrity or user operations. Classification as Read with low severity is appropriate.
From the tool's definition Tool description states it 'Lists all available Anki note type/model names' - a pure retrieval operation with no modifications or side effects.
Documented attack patterns abuse exactly the kind of access get_model_names gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Anki MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for get_model_names:
{
"version": "1",
"default": "deny",
"tools": {
"get_model_names": {}
}
}get_model_names is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Lists all available Anki note type/model names. It is categorised as a Read tool in the Anki MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Anki MCP Server MCP server in PolicyLayer and add a rule for get_model_names: 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 MCP Server. Nothing to install.
get_model_names is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_model_names 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 get_model_names. 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.
get_model_names is provided by the Anki MCP Server MCP server (nietus/anki-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 22 Anki MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
22 Anki MCP Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.