// SCAN REPORT

Qtz Iris

12 tools. 2 can modify or destroy data without limits.

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

Last updated: 5 Jul 2026

2 can modify or destroy data

10 read-only

12 tools total

Verified server · catalogue entry verified 05/07/2026 · full schemas captured for 10 of 12 tools

How to control Qtz Iris ↓

TOOL MAP

What Qtz Iris exposes to your agents

Read (10) Write / Execute (2) Destructive / Financial (0)

Running more than one server? Check your whole stack →

CONTEXT-WINDOW COST

What Qtz Iris costs in tokens

671 tokens of tool definitions, loaded on every request

0.3% of a 200k context window

134 heaviest tool: select_data

Full per-tool breakdown → Model it in the token calculator →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Qtz Iris tools

Execute · Critical execute_sql Although the description only mentions 'return results', the tool name and function indicate it executes SQL queries without restriction. Execute · Medium reconnect_database This tool triggers an external operation — re-establishing a database connection — which has side effects beyond simple data retrieval.

2 of Qtz Iris's 12 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Qtz Iris

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

Cap read operations

{
  "count_records": {
    "limits": [
      {
        "counter": "count_records_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 Qtz Iris — 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 QTZ IRIS →

Instant setup, no code required.

FULL CATALOGUE

All 12 Qtz Iris tools

EXECUTE 2 tools

Execute execute_sql 执行 SQL 查询并返回结果 Execute reconnect_database 重新连接到 IRIS 数据库。当数据库连接断开或需要刷新连接时使用此工具。

READ 10 tools

Read count_records 统计表中的记录数 Read get_class_details 获取类的详细信息 Read get_class_methods 获取类的所有方法 Read get_class_properties 获取类的所有属性 Read get_document 获取文档内容（如 .cls, .mac, .inc 文件） Read get_table_structure 获取表或类的结构信息 Read list_documents 列出命名空间中的文档 Read list_packages 列出数据库中的所有包 Read search_classes 搜索 IRIS 数据库中的类 Read select_data 从表中查询数据，支持 WHERE、ORDER BY 和 LIMIT

EXPLORE

Related servers

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

FAQ

Questions about Qtz Iris

Is the Qtz Iris MCP server safe to use without restrictions? +

The Qtz Iris server is primarily read-only with 10 read tools. While it cannot modify data, an agent in a retry loop can make thousands of API calls per minute, exhausting rate limits and running up costs. Rate limiting is still recommended.

How many tools does the Qtz Iris MCP server expose? +

12 tools across 3 categories: Execute, Read, Write. 10 are read-only. 2 can modify, create, or delete data.

How do I enforce a policy on Qtz Iris? +

Register the Qtz Iris 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 Qtz Iris tool call.

Deterministic rules across all 12 Qtz Iris tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON QTZ IRIS →

Instant setup, no code required.

12 Qtz Iris tools catalogued and risk-classified — across an index of 43,000+ MCP servers.