Create a new database with full control.
AI agents use create_database to create or update resources in MCP MySQL Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP MySQL Server environment.
Creating a new database is a Write operation—it modifies the database system state by adding a new persistent data container. While not immediately destructive or irreversible in the sense that the database can be dropped later, it is a significant structural change that affects system configuration and requires administrative privileges.
From the tool's definition Tool name 'create_database' and description 'Create a new database with full control' indicates irreversible creation of a database structure.
Attacks that exploit this kind of access
Create a new database with full control. It is categorised as a Write tool in the MCP MySQL Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP MySQL Server MCP server in PolicyLayer and add a rule for create_database: 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 MySQL Server. Nothing to install.
create_database 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 create_database 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 create_database. 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.
create_database is provided by the MCP MySQL Server MCP server (kami2k1/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 →