从指定表安全查询。order_by 项可用前缀 '-' 表示 DESC。db 省略时自动推断。
AI agents call select_rows to retrieve information from Yooztech Mcp Mysql without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs read-only SELECT queries on a MySQL database. The server explicitly states it provides 'secure read-only access' with built-in safety features. The tool name 'select_rows' and description of 'safe querying' confirm no write or destructive operations are possible. Severity is low due to read-only nature and additional security controls like whitelisting and rate limiting.
From the tool's definition '安全查询' (safe query), server description states 'read-only access', 'SELECT' implied by tool name 'select_rows', with 'parameterized queries, whitelisting, and rate limiting'
Attacks that exploit this kind of access
从指定表安全查询。order_by 项可用前缀 '-' 表示 DESC。db 省略时自动推断。. It is categorised as a Read tool in the Yooztech Mcp Mysql MCP Server, which means it retrieves data without modifying state.
Register the Yooztech Mcp Mysql MCP server in PolicyLayer and add a rule for select_rows: 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 Yooztech Mcp Mysql. Nothing to install.
select_rows 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_rows 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_rows. 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_rows is provided by the Yooztech Mcp Mysql MCP server (yooztech/mcp_mysql). 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 →