Create a new table
AI agents use db_create_table to create or update resources in Database MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Database MCP Server environment.
Creating a table is a write operation that adds new data structures to the database. While reversible via DROP TABLE, it commits schema changes that could affect application behavior if executed incorrectly. It is not destructive because the table creation itself can be undone, and it does not delete existing data.
From the tool's definition Tool name and description indicate table creation: 'Create a new table'. This is a data structure creation operation that modifies the database schema reversibly.
Attacks that exploit this kind of access
Create a new table. It is categorised as a Write tool in the Database MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Database MCP Server MCP server in PolicyLayer and add a rule for db_create_table: 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 Database MCP Server. Nothing to install.
db_create_table 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 db_create_table 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 db_create_table. 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.
db_create_table is provided by the Database MCP Server MCP server (roilanrodriguez55/database-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 →