AI agents call foodmate_get_standard to retrieve information from GBMCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves food standard information from the FoodMate source. It queries existing data using identifiers (URL or itemid) and returns details without creating, modifying, deleting, or executing operations. This is a straightforward read operation with minimal security risk—typical of metadata retrieval in a standards catalogue server.
From the tool's definition Tool name 'foodmate_get_standard' and description 'Get FoodMate food-standard detail by detail URL or itemid' indicate retrieval of metadata/details.
Attacks that exploit this kind of access
Get FoodMate food-standard detail by detail URL or itemid. It is categorised as a Read tool in the GBMCP MCP Server, which means it retrieves data without modifying state.
Register the GB MCP server in PolicyLayer and add a rule for foodmate_get_standard: 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 GBMCP. Nothing to install.
foodmate_get_standard 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 foodmate_get_standard 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 foodmate_get_standard. 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.
foodmate_get_standard is provided by the GB MCP server (loydgik/gbmcp). 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 →