EXPLAIN 单条 SELECT
AI agents call explain_query 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.
EXPLAIN SELECT is a diagnostic query that returns metadata about how MySQL would execute a SELECT statement. It has no side effects, does not retrieve user data, and cannot modify or delete anything. This is purely informational and falls squarely in the Read category with low severity even if misused by an agent.
From the tool's definition Tool name 'explain_query' with description 'EXPLAIN 单条 SELECT' indicates it runs MySQL EXPLAIN on a SELECT statement only. EXPLAIN is a read-only introspection command that analyzes query execution plans without modifying data.
Attacks that exploit this kind of access
EXPLAIN 单条 SELECT. 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 explain_query: 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.
explain_query 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 explain_query 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 explain_query. 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.
explain_query is provided by the MySQL MCP Server MCP server (yclenove/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 →