AI agents call nhc_get_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 queries and retrieves metadata and documents from a standards database. It accepts a URL parameter and returns standard details—a pure read operation. No data is modified, deleted, executed, or created. The blast radius of misuse is minimal; an attacker could only access or exfiltrate existing standard documents that may be publicly available. This aligns clearly with the Read category.
From the tool's definition The tool name 'nhc_get_standard' uses the verb 'get', and the description states it retrieves 'health/medical standard detail by detail URL or attachment URL'.
Attacks that exploit this kind of access
Get NHC health/medical standard detail by detail URL or attachment URL. 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 nhc_get_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.
nhc_get_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 nhc_get_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 nhc_get_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.
nhc_get_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 →