Show the explain of a query.
AI agents call show_explain_query to retrieve information from MySQL Managing MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
EXPLAIN/ANALYZE commands retrieve metadata about query execution plans but do not read, modify, or delete actual data. This is a diagnostic read operation with no side effects on the database state. The tool requires an already-formed query as input but does not execute it, merely analyzes it.
From the tool's definition Tool shows explain plans for queries (EXPLAIN output), which is a read-only analysis of query execution without executing the actual query. Name: 'show_explain_query' indicates display/analysis rather than data modification or execution.
Attacks that exploit this kind of access
Show the explain of a query. It is categorised as a Read tool in the MySQL Managing MCP MCP Server, which means it retrieves data without modifying state.
Register the MySQL Managing MCP server in PolicyLayer and add a rule for show_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 Managing MCP. Nothing to install.
show_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 show_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 show_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.
show_explain_query is provided by the MySQL Managing MCP server (lclpedro/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 →