Create an index using a full CREATE INDEX SQL statement
AI agents use create-index to create or update resources in Mysql Multi — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mysql Multi environment.
Creating an index modifies database schema by adding a new index structure. This is a Write operation—it creates new metadata and structures but is reversible (unlike Destructive operations). The severity is medium because index creation can impact query performance and consume disk space, but doesn't destroy data and can be undone.
From the tool's definition Tool name is 'create-index' and description states it 'Create an index using a full CREATE INDEX SQL statement'. Index creation is a reversible schema modification (indexes can be dropped via drop-index).
Attacks that exploit this kind of access
Create an index using a full CREATE INDEX SQL statement. It is categorised as a Write tool in the Mysql Multi MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mysql Multi MCP server in PolicyLayer and add a rule for create-index: 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 Multi. Nothing to install.
create-index 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-index 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-index. 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-index is provided by the Mysql Multi MCP server (pchimbolo/mysql-multi-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 →