create_tool
AI agents use create_tool to create or update resources in AutoMCP-SQL — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your AutoMCP-SQL environment.
This tool creates or inserts data into database tables, which is a reversible Write operation. It is not Destructive (no irreversible deletion), not Execute (not running arbitrary code—it's a generated typed tool), and not Financial. Severity is medium because misuse could corrupt data or violate data integrity constraints, but changes are theoretically reversible via update_tool or delete_tool.
From the tool's definition Tool name 'create_tool' combined with sibling tools 'delete_tool', 'get_tool', and 'update_tool' indicates CRUD operations. Server description states tools allow 'database interaction' on SQLite without exposing raw SQL.
Attacks that exploit this kind of access
create_tool. It is categorised as a Write tool in the AutoMCP-SQL MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the AutoMCP-SQL MCP server in PolicyLayer and add a rule for create_tool: 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 AutoMCP-SQL. Nothing to install.
create_tool 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_tool 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_tool. 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_tool is provided by the AutoMCP-SQL MCP server (mav977/automcp-sql). 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 →