Create models for all tables in the database
AI agents use phalcon_create_all_models to create or update resources in Phalcon MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Phalcon MCP Server environment.
This tool creates model files based on database tables, which modifies the project codebase by adding new files. While reversible (files can be deleted), it represents a Write operation that alters project state.
From the tool's definition Tool name and description indicate it 'Create models for all tables in the database' — a generative action that creates multiple new files/code artifacts in the project structure.
Attacks that exploit this kind of access
Create models for all tables in the database. It is categorised as a Write tool in the Phalcon MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Phalcon MCP Server MCP server in PolicyLayer and add a rule for phalcon_create_all_models: 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 Phalcon MCP Server. Nothing to install.
phalcon_create_all_models 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 phalcon_create_all_models 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 phalcon_create_all_models. 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.
phalcon_create_all_models is provided by the Phalcon MCP Server MCP server (xindong888999/phalcon-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 →