Run EXPLAIN for a single SELECT query and return the query plan.
AI agents call explain_query to retrieve information from MCP Server MySQL without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
EXPLAIN returns metadata about how a query will execute (indexes used, rows examined, etc.) but does not retrieve actual data or modify the database. This is a diagnostic/informational tool with no side effects, fitting the Read category. Severity is low because misuse poses minimal risk—an AI agent cannot cause data loss, corruption, or unintended modifications through query planning analysis alone.
From the tool's definition The tool runs EXPLAIN on a SELECT query to return the query plan. EXPLAIN is a read-only operation that analyzes query execution without modifying data. The description explicitly limits it to SELECT queries, which are non-destructive reads.
Attacks that exploit this kind of access
Run EXPLAIN for a single SELECT query and return the query plan. It is categorised as a Read tool in the MCP Server MySQL MCP Server, which means it retrieves data without modifying state.
Register the MCP Server MySQL 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 MCP Server MySQL. 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 MCP Server MySQL MCP server (nilsir/mcp-server-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 →