Search Magento codebase semantically — find any PHP class, method, XML config, PHTML template, JS file, or GraphQL schema by describing what you need in natural language. Use this as a general-purpose search when no specialized tool fits. Works best for Magento core and popular vendor modules. Fo...
AI agents call magento_search 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 performs semantic search and retrieval of code elements within a Magento codebase. It queries existing data (classes, methods, configurations, templates, schemas) without creating, modifying, executing, or deleting anything. The mention of alternatives like 'magento_grep' for searching confirms this is purely a read/lookup operation. No side effects or state changes are produced by using this tool.
From the tool's definition Tool description states 'Search Magento codebase semantically' and 'find any PHP class, method, XML config, PHTML template, JS file, or GraphQL schema'. The verb 'search' and 'find' indicate retrieval operations with no modification or execution of code.
Attacks that exploit this kind of access
Search Magento codebase semantically — find any PHP class, method, XML config, PHTML template, JS file, or GraphQL schema by describing what you need in natural language. Use this as a general-purpose search when no specialized tool fits. Works best for Magento core and popular vendor modules. For small/custom project-specific modules (e.g. proprietary modules not widely known to the embedding model), use magento_grep instead — semantic search may return 0 results for these. See also: magento_find_class, magento_find_method, magento_find_config for targeted searches. 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_search: 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_search 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_search 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_search. 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_search 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 →