// SCAN REPORT

Superman

3 tools. 1 can modify or destroy data without limits.

1 write tool that can modify data. Rate limits recommended.

Last updated: 29 Jun 2026

1 can modify or destroy data

2 read-only

3 tools total

Community server · catalogue entry verified 29/06/2026

How to control Superman ↓

TOOL MAP

What Superman exposes to your agents

Read (2) Write / Execute (1) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Superman tools

Write · Medium send_message 接收文本和可选图片，返回简单确认

1 of Superman's 3 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Superman

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

Rate limit write operations

{
  "send_message": {
    "limits": [
      {
        "counter": "send_message_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "ask_question": {
    "limits": [
      {
        "counter": "ask_question_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 Superman — 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 SUPERMAN →

Instant setup, no code required.

FULL CATALOGUE

All 3 Superman tools

WRITE 1 tools

Write send_message 接收文本和可选图片，返回简单确认

READ 2 tools

Read ask_question 向用户提问，获取用户输入 Read check_messages 【持续对话】获取用户通过插件发送的消息。助手正文应只在 Cursor 对话里输出。

FAQ

Questions about Superman

How do I prevent bulk modifications through Superman? +

The Superman server has 1 write tools including send_message. 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 Superman.

How many tools does the Superman MCP server expose? +

3 tools across 2 categories: Read, Write. 2 are read-only. 1 can modify, create, or delete data.

How do I enforce a policy on Superman? +

Register the Superman 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 Superman tool call.

Deterministic rules across all 3 Superman tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON SUPERMAN →

Instant setup, no code required.

3 Superman tools catalogued and risk-classified — across an index of 43,000+ MCP servers.