anki-request · Anki Connect MCP Server MCP: Risk & Policy

WHAT IT DOES

What anki-request does on Anki Connect MCP Server

AI agents invoke anki-request to trigger actions in Anki Connect MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why anki-request needs a policy

Because this tool allows arbitrary RPC requests to AnkiConnect, it spans multiple risk categories. Per the rules, the most severe applicable category must be chosen. An arbitrary request could trigger destructive actions (deleting decks/notes), write actions, or execute-style operations.

From the tool's definition 'Submit an arbitrary request through Anki connect' — the word 'arbitrary' indicates this tool can invoke any AnkiConnect API action, which may include destructive operations (delete deck, remove notes), write operations, or other side effects depending on the…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

anki-request Rate-limited

anki-request stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "anki-request": {
      "limits": [
        {
          "counter": "anki-request_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Anki Connect MCP Server, so you can run agents against it safely.

FAQ

Questions about anki-request

What does the anki-request tool do? +

Submit an arbitrary request through Anki connect. It is categorised as a Execute tool in the Anki Connect MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on anki-request? +

Register the Anki Connect MCP Server MCP server in PolicyLayer and add a rule for anki-request: 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 Connect MCP Server. Nothing to install.

What risk level is anki-request? +

anki-request is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit anki-request? +

Yes. Add a rate_limit block to the anki-request 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.

How do I block anki-request completely? +

Set action: deny in the PolicyLayer policy for anki-request. 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.

What MCP server provides anki-request? +

anki-request is provided by the Anki Connect MCP Server MCP server (sergey-mamulchenko/anki-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.