以 (dataset_id, natural_key) 取單筆完整資料。
AI agents call get_record to retrieve information from Healthcare OpenData MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a simple lookup query to retrieve one record from healthcare datasets. It has no side effects—it does not create, modify, delete, or execute arbitrary operations. While it accesses healthcare data (potentially sensitive), the tool itself is a basic read operation. The blast radius is limited to information disclosure if misused, not destruction or system compromise.
From the tool's definition Tool name is 'get_record' and description states it retrieves a single complete record by (dataset_id, natural_key).
Attacks that exploit this kind of access
以 (dataset_id, natural_key) 取單筆完整資料。. It is categorised as a Read tool in the Healthcare OpenData MCP MCP Server, which means it retrieves data without modifying state.
Register the Healthcare OpenData MCP server in PolicyLayer and add a rule for get_record: 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 Healthcare OpenData MCP. Nothing to install.
get_record 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_record 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_record. 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_record is provided by the Healthcare OpenData MCP server (trionnemesis/healthcare-opendata-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 →