# connect

连接到指定的 DG-Lab 设备。需先调用 scan 获取地址。可多次调用以连接多台不同设备；对已连接地址重复调用会报错。

Agent View of the PolicyLayer registry record for `connect`. HTML page: https://policylayer.com/tools/0xnullai-dg-mcp/connect

## Facts

- Tool: `connect`
- Server: DG-MCP (`0xnullai/dg-mcp`) — https://policylayer.com/tools/0xnullai-dg-mcp.md
- Homepage: https://github.com/0xNullAI/DG-MCP
- Risk category: Write (Medium risk)
- Registry record: grade D, 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": "connect",
    "arguments": {}
  }
}
```

## Why connect is rated Medium

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

## Use case

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

## Recommended policy (PolicyLayer)

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

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

## Other tools on DG-MCP (8)

- `emergency_stop` — Execute — https://policylayer.com/tools/0xnullai-dg-mcp/emergency-stop.md
- `load_waveforms` — Execute — https://policylayer.com/tools/0xnullai-dg-mcp/load-waveforms.md
- `get_sensor_state` — Read — https://policylayer.com/tools/0xnullai-dg-mcp/get-sensor-state.md
- `get_status` — Read — https://policylayer.com/tools/0xnullai-dg-mcp/get-status.md
- `list_connected_devices` — Read — https://policylayer.com/tools/0xnullai-dg-mcp/list-connected-devices.md
- `list_waveforms` — Read — https://policylayer.com/tools/0xnullai-dg-mcp/list-waveforms.md
- `scan` — Read — https://policylayer.com/tools/0xnullai-dg-mcp/scan.md
- `disconnect` — Write — https://policylayer.com/tools/0xnullai-dg-mcp/disconnect.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=0xnullai-dg-mcp · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/0xnullai-dg-mcp