Find DI preference overrides — which concrete class implements an interface or replaces another class via di.xml. See also: magento_find_class (implementation details), magento_find_config with configType=di.
AI agents call magento_find_preference to retrieve information from Magector without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool searches and retrieves information about Magento 2's dependency injection preferences from di.xml files. It does not modify, execute, delete, or create data—it only queries and returns information about class-to-interface mappings and DI overrides. The tool is analogous to 'magento_find_class' and 'magento_find_config' (sibling tools), which are semantic search operations.
From the tool's definition Tool name 'find_preference' and description 'Find DI preference overrides' indicate query/retrieval of dependency injection configuration.
Attacks that exploit this kind of access
Find DI preference overrides — which concrete class implements an interface or replaces another class via di.xml. See also: magento_find_class (implementation details), magento_find_config with configType=di. It is categorised as a Read tool in the Magector MCP Server, which means it retrieves data without modifying state.
Register the Magector MCP server in PolicyLayer and add a rule for magento_find_preference: 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 Magector. Nothing to install.
magento_find_preference is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the magento_find_preference 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 magento_find_preference. 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.
magento_find_preference is provided by the Magector MCP server (magector). 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 →