AI agents invoke wp_db_query to trigger actions in Wp Cli. 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.
This tool executes arbitrary raw SQL against a live WordPress database. Although described as intended for SELECT queries, it explicitly acknowledges support for INSERT, UPDATE, DELETE, and by extension DROP or other destructive DDL. An AI agent could misuse it to exfiltrate data, corrupt records, or destroy tables.
From the tool's definition 'Execute a raw SQL query against the WordPress database' and 'WARNING: Write queries (INSERT, UPDATE, DELETE) can damage the database'
Attacks that exploit this kind of access
Execute a raw SQL query against the WordPress database. Use for read-only SELECT queries. WARNING: Write queries (INSERT, UPDATE, DELETE) can damage the database — use with caution. It is categorised as a Execute tool in the Wp Cli MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Wp Cli MCP server in PolicyLayer and add a rule for wp_db_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 Wp Cli. Nothing to install.
wp_db_query 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 wp_db_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 wp_db_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.
wp_db_query is provided by the Wp Cli MCP server (mvtandas/wp-cli-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 →