AI agents call search_sfcc_classes to retrieve information from Sfcc Dev without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries class information from Salesforce Commerce Cloud development environment. It has no side effects—it only searches and returns matching classes. The incomplete description prevents certainty that this performs any write, execute, or destructive operations. Classified as Read category with high confidence.
From the tool's definition Tool name 'search_sfcc_classes' and description 'Find SFCC classes by partial name or keyword' indicate a search/query operation. The description is cut off ('Use when you don') but the primary function is clearly information retrieval without modification.
Attacks that exploit this kind of access
Find SFCC classes by partial name or keyword. Use when you don. It is categorised as a Read tool in the Sfcc Dev MCP Server, which means it retrieves data without modifying state.
Register the Sfcc Dev MCP server in PolicyLayer and add a rule for search_sfcc_classes: 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 Sfcc Dev. Nothing to install.
search_sfcc_classes 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 search_sfcc_classes 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 search_sfcc_classes. 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.
search_sfcc_classes is provided by the Sfcc Dev MCP server (sfcc-dev-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 →