plugin_unload_from_client · Overlord MCP Server MCP

WHAT IT DOES

What plugin_unload_from_client does on Overlord MCP Server

AI agents invoke plugin_unload_from_client to trigger actions in Overlord MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why plugin_unload_from_client needs a policy

Unloading a plugin from a client/agent triggers an external operation on a remote system (the C2 client/agent), modifying its runtime state by removing an active plugin. This is an Execute-category action as it triggers an external operational change on a live agent. While it could be partially reversible (plugin could be reloaded), the act of unloading affects the agent's active capabilities immediately.

From the tool's definition Unload a plugin from a specific client/agent

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

plugin_unload_from_client Rate-limited

plugin_unload_from_client stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "plugin_unload_from_client": {
      "limits": [
        {
          "counter": "plugin_unload_from_client_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Overlord MCP Server, so you can run agents against it safely.

FAQ

Questions about plugin_unload_from_client

What does the plugin_unload_from_client tool do? +

Unload a plugin from a specific client/agent. It is categorised as a Execute tool in the Overlord MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on plugin_unload_from_client? +

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

What risk level is plugin_unload_from_client? +

plugin_unload_from_client is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit plugin_unload_from_client? +

Yes. Add a rate_limit block to the plugin_unload_from_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 plugin_unload_from_client completely? +

Set action: deny in the PolicyLayer policy for plugin_unload_from_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 plugin_unload_from_client? +

plugin_unload_from_client is provided by the Overlord MCP Server MCP server (skeeminator/overlord-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.