AI agents call itu_download_recommendation 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 and downloads publicly available ITU-T Recommendation documents. While 'download' involves data transfer, the action is fundamentally a read operation—it retrieves existing public data without creating, modifying, or deleting anything. There is no code execution, destructive action, or financial implication.
From the tool's definition Tool name and description indicate 'download' of 'public' documents. The context shows this is a query/retrieval server for standards metadata and 'downloading public standard documents from supported sources.' Downloading read-only public documents is a…
Attacks that exploit this kind of access
Download a public ITU-T Recommendation English PDF. 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 itu_download_recommendation: 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.
itu_download_recommendation 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 itu_download_recommendation 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 itu_download_recommendation. 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.
itu_download_recommendation 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 →