update_client · Rize MCP: Risk & Policy

WHAT IT DOES

What update_client does on Rize

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

WHY IT NEEDS A POLICY

Why update_client needs a policy

This tool modifies existing client records but does not delete them (which would be Destructive) nor does it execute arbitrary code (Execute) or move money (Financial). Updating client information is a standard data modification operation. Severity is medium because incorrect updates could affect project billing or team visibility, but changes are reversible via subsequent updates.

From the tool's definition Tool name 'update_client' and description 'Update an existing client' indicate modification of existing data. The tool creates reversible changes to client information within the Rize time tracking system.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

update_client Rate-limited

update_client 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_client": {
      "limits": [
        {
          "counter": "update_client_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 Rize, so you can run agents against it safely.

FAQ

Questions about update_client

What does the update_client tool do? +

Update an existing client. It is categorised as a Write tool in the Rize 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_client? +

Register the Rize MCP server in PolicyLayer and add a rule for update_client: 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 Rize. Nothing to install.

What risk level is update_client? +

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

Can I rate-limit update_client? +

Yes. Add a rate_limit block to the update_client 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_client completely? +

Set action: deny in the PolicyLayer policy for update_client. 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_client? +

update_client is provided by the Rize MCP server (rize-io/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.