AI agents call select_data to retrieve information from Qtz Iris without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
limit | number | — | 限制返回行数（可选） |
where | string | — | WHERE 子句（可选） |
columns | array | — | 要查询的列，默认为 [*] |
orderBy | string | — | ORDER BY 子句（可选） |
tableName | string | Yes | 表名或类名 |
Parameters from the server's own tool schema.
This tool performs SELECT-style data retrieval with filtering and sorting capabilities. It has no stated side effects and is read-only in nature. However, confidence is slightly reduced because the sibling tool 'execute_sql' exists, suggesting raw SQL execution is separate, and 'select_data' appears constrained to querying only. Misuse risk is low as it only reads data.
From the tool's definition 从表中查询数据，支持 WHERE、ORDER BY 和 LIMIT — translates to 'query data from a table, supporting WHERE, ORDER BY, and LIMIT'
Attacks that exploit this kind of access
从表中查询数据，支持 WHERE、ORDER BY 和 LIMIT. It is categorised as a Read tool in the Qtz Iris MCP Server, which means it retrieves data without modifying state.
select_data accepts 5 parameters: limit, where, columns, orderBy, tableName. Required: tableName. The full parameter table on this page comes from the server's own tool schema.
Register the Qtz Iris MCP server in PolicyLayer and add a rule for select_data: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Qtz Iris. Nothing to install.
select_data is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the select_data rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for select_data. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
select_data is provided by the Qtz Iris MCP server (qtz-iris-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →