// SCAN REPORT

MCP_3

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

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

Last updated: 4 Jul 2026

1 can modify or destroy data

5 read-only

6 tools total

Community server · catalogue entry verified 04/07/2026

How to control MCP_3 ↓

TOOL MAP

What MCP_3 exposes to your agents

Read (5) Write / Execute (1) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous MCP_3 tools

Write · Medium add 将两个整数相加并返回结果。

1 of MCP_3's 6 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control MCP_3

PolicyLayer is an MCP gateway — it sits between your AI agents and MCP_3, and nothing reaches the server without passing your rules. These are the rules we recommend:

Rate limit write operations

{
  "add": {
    "limits": [
      {
        "counter": "add_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "extract_info": {
    "limits": [
      {
        "counter": "extract_info_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 MCP_3 — 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 MCP_3 →

Instant setup, no code required.

FULL CATALOGUE

All 6 MCP_3 tools

WRITE 1 tools

Write add 将两个整数相加并返回结果。

READ 5 tools

Read extract_info 在所有话题目录中搜索特定论文的信息。 Read get_alerts 获取美国各州的天气警报。 Read get_forecast 获取指定位置的天气预报。 Read get_weather 获取指定城市的天气信息。 Read search_papers 基于话题topic和它的存储信息在arxiv上搜索相关论文。

FAQ

Questions about MCP_3

How do I prevent bulk modifications through MCP_3? +

The MCP_3 server has 1 write tools including add. 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 MCP_3.

How many tools does the MCP_3 MCP server expose? +

6 tools across 2 categories: Read, Write. 5 are read-only. 1 can modify, create, or delete data.

How do I enforce a policy on MCP_3? +

Register the MCP_3 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 MCP_3 tool call.

Deterministic rules across all 6 MCP_3 tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON MCP_3 →

Instant setup, no code required.

6 MCP_3 tools catalogued and risk-classified — across an index of 43,000+ MCP servers.