Retrieve fake internal product information by product ID.
AI agents call get_product_info to retrieve information from Rabobank MCP Training Demo without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read operation that queries and retrieves product data. The severity is medium rather than low because even though this is read-only, it accesses internal banking product information which could be sensitive if misused at scale (e.g., enumerating all products, discovering non-public offerings, competitive intelligence).
From the tool's definition Tool name 'get_product_info' and description 'Retrieve fake internal product information by product ID' indicate data retrieval with no modification or deletion capability.
Attacks that exploit this kind of access
Retrieve fake internal product information by product ID. It is categorised as a Read tool in the Rabobank MCP Training Demo MCP Server, which means it retrieves data without modifying state.
Register the Rabobank MCP Training Demo MCP server in PolicyLayer and add a rule for get_product_info: 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 Rabobank MCP Training Demo. Nothing to install.
get_product_info 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 get_product_info 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 get_product_info. 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.
get_product_info is provided by the Rabobank MCP Training Demo MCP server (remseymailjard/rabobank-mcp-training). 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 →