// SCAN REPORT

DG-MCP

9 tools. 4 can modify or destroy data without limits.

4 write tools that can modify data. Rate limits recommended.

Last updated: 24 Jul 2026

4 can modify or destroy data

5 read-only

9 tools total

Community server · catalogue entry checked 24/07/2026

How to control DG-MCP ↓

TOOL MAP

What DG-MCP exposes to your agents

Read (5) Write / Execute (4) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous DG-MCP tools

Execute · Medium load_waveforms This tool loads waveform/pulse pattern files from disk (a file path) and makes them available for use on a DG-Lab Coyote electrostimulation device. Execute · Medium emergency_stop 紧急停止：所有已连接设备的强度/振动输出归零。 Write · Medium 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。 Write · Medium disconnect 断开设备连接。指定 address 则只断开该设备，省略则断开全部已连接设备。

4 of DG-MCP's 9 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control DG-MCP

PolicyLayer is an MCP gateway — it sits between your AI agents and DG-MCP, and nothing reaches the server without passing your rules. These are the rules we recommend:

Rate limit write operations

{
  "connect": {
    "limits": [
      {
        "counter": "connect_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "get_sensor_state": {
    "limits": [
      {
        "counter": "get_sensor_state_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register DG-MCP — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON DG-MCP →

Instant setup, no code required.

FULL CATALOGUE

All 9 DG-MCP tools

EXECUTE 2 tools

Execute emergency_stop 紧急停止：所有已连接设备的强度/振动输出归零。 Execute load_waveforms 从指定路径加载 .pulse 文件或包含 .pulse 的 .zip。

WRITE 2 tools

Write 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。 Write disconnect 断开设备连接。指定 address 则只断开该设备，省略则断开全部已连接设备。

READ 5 tools

Read get_sensor_state 查询已连接的爪印 / 灵猫边缘控制传感器的最新读数（事件流缓存的最近一次上报）。可选 address 只查询单个设备。 Read get_status 查询所有已连接设备的状态（连接状态 / 强度或振动 / 波形 / 电池等，按设备类型而定）。 Read list_connected_devices 列出当前已连接的全部设备：{ address, deviceKind, connected }。 Read list_waveforms 列出当前波形库中的所有波形（内置 + 已导入）。 Read scan 扫描附近的 DG-Lab 设备（郊狼 / 爪印 / 灵猫边缘控制 / 负鼠）。返回包含 address / name / rssi / deviceKind 的列表。

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about DG-MCP

How do I prevent bulk modifications through DG-MCP? +

The DG-MCP server has 2 write tools including connect, disconnect. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach DG-MCP.

How many tools does the DG- MCP server expose? +

9 tools across 3 categories: Execute, Read, Write. 5 are read-only. 4 can modify, create, or delete data.

How do I enforce a policy on DG-MCP? +

Register the DG- MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every DG-MCP tool call.

Deterministic rules across all 9 DG-MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON DG-MCP →

Instant setup, no code required.

9 DG-MCP tools catalogued and risk-classified — across an index of 46,500+ MCP servers.

// WHERE THIS COMES FROM

These policies come from DG-'s registry record.

The record behind this page: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.

Teams ship this data inside their own products. See what a licence covers →