AI agents call magento_find_api 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 is a semantic code search tool that queries an index to locate API definitions and their implementations. It performs information retrieval only—no side effects, state changes, code execution, or data destruction. The read-only nature is reinforced by the server's stated purpose (semantic code search) and the parallel tools which are similarly analytical (analyze_diff, ast_search, describe, error_parser).
From the tool's definition Tool 'magento_find_api' is described as finding and locating API endpoint definitions in webapi.xml and service class implementations.
Attacks that exploit this kind of access
Find REST and SOAP API endpoint definitions in webapi.xml and their service class implementations. See also: magento_find_config with configType=webapi, magento_find_class (service class). 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_api: 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_api 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_api 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_api. 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_api 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 →