Runs any single SQL statement against the selected LocalWP site
AI agents invoke mysql_execute to trigger actions in LocalWP MCP. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
The tool executes arbitrary SQL statements with no restrictions mentioned. While SQL can be read-only (Read), write (Write), or destructive (Destructive), the absence of limitations in the description means an AI agent could run DROP TABLE, DELETE, or INSERT statements.
From the tool's definition Tool description states it 'Runs any single SQL statement against the selected LocalWP site' — this permits arbitrary SQL execution including DDL, DML, and DCL operations.
Attacks that exploit this kind of access
Runs any single SQL statement against the selected LocalWP site. It is categorised as a Execute tool in the LocalWP MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the LocalWP MCP server in PolicyLayer and add a rule for mysql_execute: 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 LocalWP MCP. Nothing to install.
mysql_execute is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the mysql_execute 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 mysql_execute. 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.
mysql_execute is provided by the LocalWP MCP server (kazimshah39/localwp-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 →