AI agents use write_query to create or update resources in MySQL-MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MySQL-MCP environment.
The tool's explicit purpose is to modify data through INSERT (create), UPDATE (modify), and DELETE (remove) operations. While DELETE is destructive in nature, the tool's primary design intent covers all three DML write operations. INSERT and UPDATE are clearly Write category operations.
From the tool's definition Tool description states 'Execute an INSERT, UPDATE, or DELETE query'. INSERT and UPDATE are reversible write operations; DELETE is listed but the tool is categorized as Write rather than Destructive because DELETE via this tool can potentially be undone with…
Attacks that exploit this kind of access
Execute an INSERT, UPDATE, or DELETE query. It is categorised as a Write tool in the MySQL-MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MySQL- MCP server in PolicyLayer and add a rule for write_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. Nothing to install.
write_query is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the write_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 write_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.
write_query is provided by the MySQL- MCP server (zajtools/zaj-mysql-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 →