AI agents call cfsa_download_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 public standard documents without modifying, executing operations, deleting data, or affecting financial systems. While 'download' involves data transfer, it is fundamentally a read operation that accesses pre-existing public resources without side effects. The low severity reflects that downloading public standards poses minimal risk even if misused by an AI agent.
From the tool's definition Tool description states 'Download a CFSA food safety national standard body file' and server description indicates it downloads 'public standard documents from supported sources'. The action is retrieving/downloading publicly available standards documents.
Attacks that exploit this kind of access
Download a CFSA food safety national standard body file. 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 cfsa_download_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.
cfsa_download_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 cfsa_download_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 cfsa_download_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.
cfsa_download_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 →