특정 케이스의 정보를 가져옵니다 (사용 가능한 트랙 목록 등)
AI agents call get_case_info to retrieve information from VitalDB MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves metadata and information about medical cases with no side effects. It does not create, modify, delete, or execute external operations. The severity is low because accessing case information from a medical database, while sensitive, has minimal blast radius when used by an AI agent—it cannot alter records or trigger financial/destructive actions.
From the tool's definition Tool name 'get_case_info' and description indicating it retrieves information about a specific case (including available track lists).
Attacks that exploit this kind of access
특정 케이스의 정보를 가져옵니다 (사용 가능한 트랙 목록 등). It is categorised as a Read tool in the VitalDB MCP Server MCP Server, which means it retrieves data without modifying state.
Register the VitalDB MCP Server MCP server in PolicyLayer and add a rule for get_case_info: 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 VitalDB MCP Server. Nothing to install.
get_case_info 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_case_info 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_case_info. 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_case_info is provided by the VitalDB MCP Server MCP server (yejelim/vitaldb-mcp-server). 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 →