Create a NEW flashcard in Anki for the user. ONLY use this for creating NEW cards, NOT for updating existing ones. Will throw an error if the card already exists. For updating existing cards, use update_note_fields with the noteId instead. Must use HTML formatting only. IMPORTANT FORMATTING RULES...
AI agents use add_card to create or update resources in Anki MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Anki MCP Server environment.
The tool creates new flashcard entries in Anki, which is a Write operation—data modification that can be reversed (cards can be deleted). It has low severity because flashcard creation is non-destructive, localized to the user's study data, and easily undoable.
From the tool's definition Tool description explicitly states 'Create a NEW flashcard' and 'ONLY use this for creating NEW cards, NOT for updating existing ones'. This is a reversible create operation on user data (flashcards in Anki).
Documented attack patterns abuse exactly the kind of access add_card 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 add_card:
{
"version": "1",
"default": "deny",
"tools": {
"add_card": {
"limits": [
{
"counter": "add_card_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}add_card 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.
Create a NEW flashcard in Anki for the user. ONLY use this for creating NEW cards, NOT for updating existing ones. Will throw an error if the card already exists. For updating existing cards, use update_note_fields with the noteId instead. Must use HTML formatting only. IMPORTANT FORMATTING RULES:\n1. Must use HTML tags for ALL formatting - NO markdown\n2. Use <br> for ALL line breaks\n3. For code blocks, use <pre> with inline CSS styling\n4. Example formatting:\n - Line breaks: <br>\n - Code: <pre style=. It is categorised as a Write tool in the Anki MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Anki MCP Server MCP server in PolicyLayer and add a rule for add_card: 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.
add_card 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 add_card 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 add_card. 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.
add_card 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.