Read find.md and generate Adobe Commerce support reply using Cursor LLM.
AI agents call generate_support_reply to retrieve information from Adobe Commerce Support MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool reads a markdown file (find.md) and uses an LLM to generate a support reply. The primary action is reading a file and producing text, with no apparent side effects like writing, executing commands, or modifying data. The generated reply itself is output, not an action taken.
From the tool's definition 'Read find.md and generate Adobe Commerce support reply' — the tool reads a file and generates text output
Attacks that exploit this kind of access
Read find.md and generate Adobe Commerce support reply using Cursor LLM. It is categorised as a Read tool in the Adobe Commerce Support MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Adobe Commerce Support MCP Server MCP server in PolicyLayer and add a rule for generate_support_reply: 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 Adobe Commerce Support MCP Server. Nothing to install.
generate_support_reply 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 generate_support_reply 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 generate_support_reply. 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.
generate_support_reply is provided by the Adobe Commerce Support MCP Server MCP server (kavingas/mcp_support_server). 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 →