AI agents call samr_search_standard_samples 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 'samr_search_standard_samples' indicates a search/query operation for standard samples. Despite the empty description, the naming convention and server context strongly suggest this retrieves or queries data without side effects, consistent with Read category tools. The confidence is slightly reduced due to the missing description, but contextual evidence from sibling tools and server purpose is clear.
From the tool's definition Tool name contains 'search' and is part of a server described as 'querying standards metadata and downloading public standard documents.' The 'search' verb indicates data retrieval without modification.
Attacks that exploit this kind of access
samr_search_standard_samples. 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 samr_search_standard_samples: 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.
samr_search_standard_samples 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 samr_search_standard_samples 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 samr_search_standard_samples. 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.
samr_search_standard_samples 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 →