Preview which documentation scenarios have OPDSTAR-curated NHI-safe phrasing patterns for a given specialty (e.g. dermatology + 抗生素) — returns scenario name, high-risk wording to avoid, the key difference, and the first sentence of the safe-phrasing example. Up to 5 scenarios per call. Use when a...
AI agents call get_safe_phrases to retrieve information from Opdstar Nhi without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves curated documentation patterns and guidelines from the NHI system without modifying any data or triggering external operations. It is purely consultative—helping draft and review phrasing before submission. The blast radius of misuse is minimal: the tool cannot approve submissions, alter records, or commit transactions.
From the tool's definition Tool returns preview/lookup data: 'returns scenario name, high-risk wording to avoid, the key difference, and the first sentence of the safe-phrasing example.' No modifications, deletions, executions, or financial transactions occur.
Attacks that exploit this kind of access
Preview which documentation scenarios have OPDSTAR-curated NHI-safe phrasing patterns for a given specialty (e.g. dermatology + 抗生素) — returns scenario name, high-risk wording to avoid, the key difference, and the first sentence of the safe-phrasing example. Up to 5 scenarios per call. Use when an agent is helping draft SOAP wording and needs to flag risky phrasing before submission. Don. It is categorised as a Read tool in the Opdstar Nhi MCP Server, which means it retrieves data without modifying state.
Register the Opdstar Nhi MCP server in PolicyLayer and add a rule for get_safe_phrases: 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 Opdstar Nhi. Nothing to install.
get_safe_phrases 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 get_safe_phrases 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 get_safe_phrases. 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.
get_safe_phrases is provided by the Opdstar Nhi MCP server (tatsuju/opdstar-nhi-mcp). 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 →