# activate_deploy

Rollback / re-activate a previous deploy by id.

Agent View of the PolicyLayer registry record for `activate_deploy`. HTML page: https://policylayer.com/tools/9d9dev-mcp/activate-deploy

## Facts

- Tool: `activate_deploy`
- Server: 9d9dev (`@9d9dev/mcp`) — https://policylayer.com/tools/9d9dev-mcp.md
- Install: `npx -y @9d9dev/mcp`
- Homepage: https://www.npmjs.com/package/@9d9dev/mcp
- Risk category: Write (Medium risk)
- Registry record: grade C, identity unverified
- Server rate-limited: no
- Parameters: 2 (1 required)
- Recommended policy verdict: Rate-limited

## Parameters

| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `org_id` | string | no | Optional. Defaults to the org_id in this project's .9d9.json — only pass to override. |
| `deploy_id` | string | yes |  |

Parameters from the server's own tool schema.

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

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "activate_deploy",
    "arguments": {
      "deploy_id": "<deploy_id>"
    }
  }
}
```

## Why activate_deploy is rated Medium

An AI agent can call activate_deploy faster than any human can review: one bad instruction and it creates or modifies resources in 9d9dev by the hundred, each call as confident as the last.

## Use case

AI agents use activate_deploy to create or update resources in 9d9dev, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your 9d9dev environment.

## Recommended policy (PolicyLayer)

Verdict: **Rate-limited**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches 9d9dev:

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

## Other tools on 9d9dev (6)

- `get_config` — Read — https://policylayer.com/tools/9d9dev-mcp/get-config.md
- `get_status` — Read — https://policylayer.com/tools/9d9dev-mcp/get-status.md
- `list_deploys` — Read — https://policylayer.com/tools/9d9dev-mcp/list-deploys.md
- `attach_domain` — Write — https://policylayer.com/tools/9d9dev-mcp/attach-domain.md
- `save_api_key` — Write — https://policylayer.com/tools/9d9dev-mcp/save-api-key.md
- `update_brand` — Write — https://policylayer.com/tools/9d9dev-mcp/update-brand.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=9d9dev-mcp · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/9d9dev-mcp
