Medium Risk

mcp_disable

Disable an MCP server

How to control mcp_disable ↓

AI agents use mcp_disable to create or update resources in 1MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your 1MCP Server environment.

Medium Risk

Disabling an MCP server modifies its configuration/state (turning it off), which is a reversible write operation. However, the blast radius is high because disabling a server could interrupt active AI assistant connections and workflows that depend on it. It does not permanently delete anything, so it falls under Write rather than Destructive.

From the tool's definition Disable an MCP server

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

PolicyLayer is an MCP gateway — it sits between your AI agents and 1MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for mcp_disable:

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

mcp_disable 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 1MCP 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.

Go deeper

What does the mcp_disable tool do? +

Disable an MCP server. It is categorised as a Write tool in the 1MCP 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 mcp_disable? +

Register the 1MCP Server MCP server in PolicyLayer and add a rule for mcp_disable: 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 1MCP Server. Nothing to install.

What risk level is mcp_disable? +

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

Can I rate-limit mcp_disable? +

Yes. Add a rate_limit block to the mcp_disable 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 mcp_disable completely? +

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

mcp_disable is provided by the 1MCP Server MCP server (1mcp-app/agent). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every 1MCP Server tool call.

Deterministic rules across all 17 1MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

17 1MCP Server tools catalogued and risk-classified — across an index of 42,500+ 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.