update_card · Privacy MCP: Risk & Policy

WHAT IT DOES

What update_card does on Privacy

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

WHY IT NEEDS A POLICY

Why update_card needs a policy

The update_card tool modifies existing virtual card records reversibly (card settings, limits, status), which is characteristic of Write operations. It does not delete data (Destructive) nor move money (Financial), though it operates in a financial context.

From the tool's definition Tool name is 'update_card' on a Privacy.com virtual card management server. The sibling tools include 'create_card' and 'pausing cards' mentioned in server description, indicating this tool modifies card state.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

update_card Rate-limited

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": {
    "update_card": {
      "limits": [
        {
          "counter": "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 Privacy, so you can run agents against it safely.

FAQ

Questions about update_card

What does the update_card tool do? +

update_card. It is categorised as a Write tool in the Privacy MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on update_card? +

Register the Privacy MCP server in PolicyLayer and add a rule for 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 Privacy. Nothing to install.

What risk level is update_card? +

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

Can I rate-limit update_card? +

Yes. Add a rate_limit block to the 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 update_card completely? +

Set action: deny in the PolicyLayer policy for 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 update_card? +

update_card is provided by the Privacy MCP server (richardadonnell/privacy-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.