AI agents use submit_reviews to create or update resources in MCP-AnkiConnect — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP-AnkiConnect environment.
The tool creates or modifies review records and updates card scheduling state, characteristic of Write operations. While it affects learning data, it does not irreversibly delete data (Destructive) nor execute arbitrary code (Execute).
From the tool's definition submit_reviews submits answers for reviewed cards, which modifies card review state and scheduling data in Anki.
Documented attack patterns abuse exactly the kind of access submit_reviews 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 submit_reviews:
{
"version": "1",
"default": "deny",
"tools": {
"submit_reviews": {
"limits": [
{
"counter": "submit_reviews_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}submit_reviews 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.
Submit answers for reviewed cards. It is categorised as a Write tool in the MCP-AnkiConnect MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP-AnkiConnect MCP server in PolicyLayer and add a rule for submit_reviews: 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.
submit_reviews 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 submit_reviews 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 submit_reviews. 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.
submit_reviews 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.