apply_update_card · Mochi MCP Server MCP: Risk & Policy

WHAT IT DOES

What apply_update_card does on Mochi MCP Server

AI agents use apply_update_card to create or update resources in Mochi MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mochi MCP Server environment.

WHY IT NEEDS A POLICY

Why apply_update_card needs a policy

This tool updates (modifies reversibly) existing flashcard data after a user has confirmed the changes through a preview step. It is Write rather than Destructive because updates are reversible—users can modify cards again. Severity is medium because careless bulk updates to flashcard content could corrupt study materials, but the two-phase confirmation and preview mechanism significantly mitigate risk.

From the tool's definition Tool description explicitly states it 'Execute[s] card update', confirming this modifies existing data. Related tools include 'create_card_preview', 'apply_create_card', and 'apply_tags_update', establishing a pattern where 'apply_*' tools commit changes…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

apply_update_card Rate-limited

apply_update_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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "apply_update_card": {
      "limits": [
        {
          "counter": "apply_update_card_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

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

FAQ

Questions about apply_update_card

What does the apply_update_card tool do? +

Execute card update after user confirms. It is categorised as a Write tool in the Mochi MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on apply_update_card? +

Register the Mochi MCP Server MCP server in PolicyLayer and add a rule for apply_update_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 Mochi MCP Server. Nothing to install.

What risk level is apply_update_card? +

apply_update_card is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit apply_update_card? +

Yes. Add a rate_limit block to the apply_update_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.

How do I block apply_update_card completely? +

Set action: deny in the PolicyLayer policy for apply_update_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.

What MCP server provides apply_update_card? +

apply_update_card is provided by the Mochi MCP Server MCP server (nz99/mochi-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.