Case ID 및 메타데이터 조회
AI agents call get_case_ids to retrieve information from PerfDog to Tableau 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 identifiers and metadata—a read-only query operation with no side effects. The blast radius is minimal: disclosing case IDs and their metadata presents low information security risk in the context of a performance data pipeline, and cannot alter system state or trigger external actions.
From the tool's definition Tool name 'get_case_ids' and description indicate retrieval of case IDs and metadata ('Case ID 및 메타데이터 조회' = 'Query Case ID and metadata'). No modification, deletion, or execution capability described.
Attacks that exploit this kind of access
Case ID 및 메타데이터 조회. It is categorised as a Read tool in the PerfDog to Tableau MCP Server MCP Server, which means it retrieves data without modifying state.
Register the PerfDog to Tableau MCP Server MCP server in PolicyLayer and add a rule for get_case_ids: 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 PerfDog to Tableau MCP Server. Nothing to install.
get_case_ids 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_ids 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_ids. 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_ids is provided by the PerfDog to Tableau MCP Server MCP server (kimjeonghyun225-cpu/perfdog_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 →