View per-card state for given card IDs or note IDs. Sparse-fieldset selection via the properties list: any of identity, state, scheduling, timestamps, history, fields, or all (default: ["identity", "state", "scheduling"]). The legacy include_history=true flag is still accepted as an alias.
AI agents call inspect_cards to retrieve information from MCP-AnkiConnect without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays flashcard state information without creating, modifying, or deleting any data. It is purely informational, allowing users to examine card properties for review purposes. No side effects or data mutations are possible with this tool.
From the tool's definition Tool description explicitly states 'View per-card state' and offers 'Sparse-fieldset selection' of various properties like identity, state, scheduling, timestamps, history, and fields.
Documented attack patterns abuse exactly the kind of access inspect_cards gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP-AnkiConnect, and nothing reaches the server without passing your rules. This is the rule we recommend for inspect_cards:
{
"version": "1",
"default": "deny",
"tools": {
"inspect_cards": {}
}
}inspect_cards 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.
View per-card state for given card IDs or note IDs. Sparse-fieldset selection via the properties list: any of identity, state, scheduling, timestamps, history, fields, or all (default: ["identity", "state", "scheduling"]). The legacy include_history=true flag is still accepted as an alias. It is categorised as a Read tool in the MCP-AnkiConnect MCP Server, which means it retrieves data without modifying state.
Register the MCP-AnkiConnect MCP server in PolicyLayer and add a rule for inspect_cards: 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 MCP-AnkiConnect. Nothing to install.
inspect_cards 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 inspect_cards 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 inspect_cards. 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.
inspect_cards is provided by the MCP-AnkiConnect MCP server (samefarrar/mcp-ankiconnect). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MCP-AnkiConnect, 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.
10 MCP-AnkiConnect tools catalogued and risk-classified — across an index of 43,000+ MCP servers.