update_assistant · RunWhen Platform MCP: Risk & Policy

WHAT IT DOES

What update_assistant does on RunWhen Platform MCP

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

WHY IT NEEDS A POLICY

Why update_assistant needs a policy

This tool creates or modifies assistant data reversibly without deleting it or executing external code. It belongs in Write rather than Execute because it operates on configuration/metadata rather than triggering arbitrary operations. Severity is medium because misconfiguration of an assistant could affect workspace automation, but the impact is typically reversible via another update call.

From the tool's definition Tool name 'update_assistant' indicates modification of an assistant configuration or state. The server description mentions 'create_assistant' and 'delete_assistant' as sibling tools, establishing that assistants are mutable resources.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

update_assistant Rate-limited

update_assistant 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_assistant": {
      "limits": [
        {
          "counter": "update_assistant_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 RunWhen Platform MCP, so you can run agents against it safely.

FAQ

Questions about update_assistant

What does the update_assistant tool do? +

update_assistant. It is categorised as a Write tool in the RunWhen Platform MCP 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_assistant? +

Register the RunWhen Platform MCP server in PolicyLayer and add a rule for update_assistant: 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 RunWhen Platform MCP. Nothing to install.

What risk level is update_assistant? +

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

Can I rate-limit update_assistant? +

Yes. Add a rate_limit block to the update_assistant 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_assistant completely? +

Set action: deny in the PolicyLayer policy for update_assistant. 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_assistant? +

update_assistant is provided by the RunWhen Platform MCP server (runwhen-contrib/runwhen-platform-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.