AI agents call mem_search_standards 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.
The tool name strongly suggests a search function ('search_standards'), which retrieves and queries data without modification or deletion. The empty description lowers confidence slightly, but the naming convention aligns with sibling search tools (cfsa_search_standards, doc88_search_documents) which are clearly Read-category operations. No evidence of write, execute, destructive, or financial capabilities.
From the tool's definition Tool name 'mem_search_standards' indicates a search operation. The server's stated purpose is 'querying standards metadata and downloading public standard documents.' Search operations are read-only queries with no side effects.
Attacks that exploit this kind of access
mem_search_standards. 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 mem_search_standards: 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.
mem_search_standards 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 mem_search_standards 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 mem_search_standards. 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.
mem_search_standards 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 →