update_plugin · CustomGPT MCP Server MCP: Risk & Policy

WHAT IT DOES

What update_plugin does on CustomGPT MCP Server

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

WHY IT NEEDS A POLICY

Why update_plugin needs a policy

This tool modifies plugin settings for an agent, which is a Write operation (data modification without permanent deletion). The severity is medium because while plugin updates affect agent behavior and could introduce malicious plugins or alter functionality, the changes are reversible and typically scoped to specific agent configurations.

From the tool's definition Tool name 'update_plugin' and description 'Update a plugin for an agent' indicate modification of existing plugin configuration or settings. The action is reversible—updates can be modified or reverted—distinguishing it from destructive operations.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

update_plugin Rate-limited

update_plugin 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_plugin": {
      "limits": [
        {
          "counter": "update_plugin_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 CustomGPT MCP Server, so you can run agents against it safely.

FAQ

Questions about update_plugin

What does the update_plugin tool do? +

Update a plugin for an agent. It is categorised as a Write tool in the CustomGPT 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 update_plugin? +

Register the CustomGPT MCP Server MCP server in PolicyLayer and add a rule for update_plugin: 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 CustomGPT MCP Server. Nothing to install.

What risk level is update_plugin? +

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

Can I rate-limit update_plugin? +

Yes. Add a rate_limit block to the update_plugin 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_plugin completely? +

Set action: deny in the PolicyLayer policy for update_plugin. 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_plugin? +

update_plugin is provided by the CustomGPT MCP Server MCP server (poll-the-people/customgpt-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.