Liest ein einzelnes Produkt aus Xentral per Produkt-ID.
AI agents call xentral_get_product to retrieve information from Xentral MCP HTTP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a simple query/fetch operation to retrieve product information from the Xentral ERP system by ID. It has no capability to modify, delete, or execute operations—purely a read operation with minimal blast radius if misused by an AI agent.
From the tool's definition Tool name 'xentral_get_product' and description 'Liest ein einzelnes Produkt aus Xentral per Produkt-ID' (retrieves a single product from Xentral by product ID) indicate a data retrieval operation with no modification or side effects.
Attacks that exploit this kind of access
Liest ein einzelnes Produkt aus Xentral per Produkt-ID. It is categorised as a Read tool in the Xentral MCP HTTP Server MCP Server, which means it retrieves data without modifying state.
Register the Xentral MCP HTTP Server MCP server in PolicyLayer and add a rule for xentral_get_product: 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 Xentral MCP HTTP Server. Nothing to install.
xentral_get_product 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 xentral_get_product 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 xentral_get_product. 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.
xentral_get_product is provided by the Xentral MCP HTTP Server MCP server (matthiashuebner/xentral-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 →