执行MySQL数据库查询（只读模式）
AI agents call query_mysql to retrieve information from Database Query MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves data from MySQL databases without side effects. The read-only mode restriction and safety mechanisms ensure queries cannot modify, delete, or execute arbitrary code. The primary risk is unauthorized information disclosure, which is lower severity than write/execute/destructive operations.
From the tool's definition Tool name 'query_mysql' and description states '执行MySQL数据库查询（只读模式）' (Execute MySQL database query in read-only mode). Server description explicitly states it 'blocks any data modification operations for safety' and is 'secure read-only querying.'
Attacks that exploit this kind of access
执行MySQL数据库查询（只读模式）. It is categorised as a Read tool in the Database Query MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Database Query MCP Server MCP server in PolicyLayer and add a rule for query_mysql: 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 Database Query MCP Server. Nothing to install.
query_mysql 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_mysql 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_mysql. 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_mysql is provided by the Database Query MCP Server MCP server (xuejike/coding-db-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 →