Medium Risk

disable_plugin

Disables a FiftyOne plugin, removing its

How to control disable_plugin ↓

What disable_plugin does on FiftyOne MCP Server

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

Medium Risk

Why disable_plugin needs a policy

Disabling a plugin modifies the plugin's active state and removes it from use, but does not permanently delete the plugin or its data. This is reversible—the plugin can be re-enabled. Therefore it qualifies as Write (modification) rather than Destructive (irreversible). The severity is medium because disabling a plugin could impact dataset analysis workflows, but the action is recoverable.

From the tool's definition Tool name 'disable_plugin' and description 'Disables a FiftyOne plugin, removing its' indicate a modification action. The description is incomplete but the verb 'disables' and 'removing' clearly show state change rather than deletion.

Documented attack patterns abuse exactly the kind of access disable_plugin gives an agent:

How to control disable_plugin

PolicyLayer is an MCP gateway — it sits between your AI agents and FiftyOne MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for disable_plugin:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "disable_plugin": {
      "limits": [
        {
          "counter": "disable_plugin_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

disable_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.

  1. Create a free account and register FiftyOne MCP Server — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
LIMIT THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about disable_plugin

What does the disable_plugin tool do? +

Disables a FiftyOne plugin, removing its. It is categorised as a Write tool in the FiftyOne 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 disable_plugin? +

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

What risk level is disable_plugin? +

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

Can I rate-limit disable_plugin? +

Yes. Add a rate_limit block to the disable_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 disable_plugin completely? +

Set action: deny in the PolicyLayer policy for disable_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 disable_plugin? +

disable_plugin is provided by the FiftyOne MCP Server MCP server (voxel51/fiftyone-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every FiftyOne MCP Server tool call.

Start from FiftyOne MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

Free to start. No card required.

47 FiftyOne MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.