执行SQL查询并返回结果集（仅支持SELECT语句）
AI agents call query_sql to retrieve information from MySQL MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool is restricted to SELECT queries, which retrieve data without modification, deletion, or side effects. This is a classic Read category tool. The explicit constraint to SELECT statements eliminates Execute and Destructive risks. Low severity due to read-only nature and limited blast radius if misused by an agent.
From the tool's definition Tool description explicitly states 'Enables safe interaction with MySQL databases through SELECT queries' and '仅支持SELECT语句' (only supports SELECT statements). Server description emphasizes 'read-only access to query data and examine database metadata.'
Attacks that exploit this kind of access
执行SQL查询并返回结果集（仅支持SELECT语句）. It is categorised as a Read tool in the MySQL MCP Server MCP Server, which means it retrieves data without modifying state.
Register the MySQL MCP Server MCP server in PolicyLayer and add a rule for query_sql: 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 MySQL MCP Server. Nothing to install.
query_sql 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 query_sql 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 query_sql. 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.
query_sql is provided by the MySQL MCP Server MCP server (jeweis/jewei-mysql-mcp-server). 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 →