# mcp_disable

Disable an MCP server

Agent View of the PolicyLayer registry record for `mcp_disable`. HTML page: https://policylayer.com/tools/1mcp-app-agent/mcp-disable

## Facts

- Tool: `mcp_disable`
- Server: 1MCP Server (`1mcp-app/agent`) — https://policylayer.com/tools/1mcp-app-agent.md
- Homepage: https://github.com/1mcp-app/agent
- Risk category: Write (Medium risk)
- Registry record: grade F, identity unverified
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Rate-limited

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "mcp_disable",
    "arguments": {}
  }
}
```

## Why mcp_disable is rated Medium

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 own definition: "Disable an MCP server"

## Use case

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.

## Recommended policy (PolicyLayer)

Verdict: **Rate-limited**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches 1MCP Server:

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

## Other tools on 1MCP Server (16)

- `mcp_uninstall` — Destructive — https://policylayer.com/tools/1mcp-app-agent/mcp-uninstall.md
- `mcp_install` — Execute — https://policylayer.com/tools/1mcp-app-agent/mcp-install.md
- `mcp_reload` — Execute — https://policylayer.com/tools/1mcp-app-agent/mcp-reload.md
- `tool_invoke` — Execute — https://policylayer.com/tools/1mcp-app-agent/tool-invoke.md
- `mcp_info` — Read — https://policylayer.com/tools/1mcp-app-agent/mcp-info.md
- `mcp_list` — Read — https://policylayer.com/tools/1mcp-app-agent/mcp-list.md
- `mcp_registry_info` — Read — https://policylayer.com/tools/1mcp-app-agent/mcp-registry-info.md
- `mcp_registry_list` — Read — https://policylayer.com/tools/1mcp-app-agent/mcp-registry-list.md
- `mcp_registry_status` — Read — https://policylayer.com/tools/1mcp-app-agent/mcp-registry-status.md
- `mcp_search` — Read — https://policylayer.com/tools/1mcp-app-agent/mcp-search.md
- `mcp_status` — Read — https://policylayer.com/tools/1mcp-app-agent/mcp-status.md
- `tool_list` — Read — https://policylayer.com/tools/1mcp-app-agent/tool-list.md
- `tool_schema` — Read — https://policylayer.com/tools/1mcp-app-agent/tool-schema.md
- `mcp_edit` — Write — https://policylayer.com/tools/1mcp-app-agent/mcp-edit.md
- `mcp_enable` — Write — https://policylayer.com/tools/1mcp-app-agent/mcp-enable.md
- `mcp_update` — Write — https://policylayer.com/tools/1mcp-app-agent/mcp-update.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=1mcp-app-agent · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/1mcp-app-agent