Generate LLM-powered natural language descriptions for di.xml files using Claude Sonnet via the Anthropic API. Requires ANTHROPIC_API_KEY env var. Descriptions are cached and automatically attached to search results for di.xml files.
AI agents call magento_describe 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 reads di.xml files, processes them through an LLM to generate descriptive metadata, and caches those descriptions for attachment to search results. The operation is non-destructive and produces no side effects beyond creating cached metadata. While it calls an external API (Anthropic), it only reads and describes existing code, making it fundamentally a Read operation.
From the tool's definition Tool generates 'natural language descriptions' for di.xml files and 'descriptions are cached and automatically attached to search results'. The core action is retrieval and description generation with no modification to underlying code or data.
Attacks that exploit this kind of access
Generate LLM-powered natural language descriptions for di.xml files using Claude Sonnet via the Anthropic API. Requires ANTHROPIC_API_KEY env var. Descriptions are cached and automatically attached to search results for di.xml files. 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_describe: 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_describe 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_describe 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_describe. 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_describe 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 →