AI agents call itu_search_recommendations 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.
Search operations retrieve and query data without modifying or deleting anything. The 'search' verb combined with a standards metadata query server indicates this retrieves recommendations without side effects. Empty description prevents verification of edge cases, but the preponderance of evidence points to Read category with low severity.
From the tool's definition Tool name 'itu_search_recommendations' indicates a search operation. The server's purpose is 'querying standards metadata and downloading public standard documents,' and sibling tools include multiple search functions (cfsa_search_standards,…
Attacks that exploit this kind of access
itu_search_recommendations. 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_search_recommendations: 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_search_recommendations 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_search_recommendations 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_search_recommendations. 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_search_recommendations 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 →