query_metric_data
AI agents call query_metric_data to retrieve information from OCI MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Metric data queries are read operations that retrieve monitoring or telemetry information without modifying state. Classified as Read rather than higher severity due to no apparent data modification, deletion, or command execution.
From the tool's definition Tool name 'query_metric_data' indicates retrieval of metric data. Empty description limits specificity, but the querying pattern and sibling tools (get_alarm_history, get_cost_usage_summary) suggest read-only data retrieval from OCI monitoring systems.
Attacks that exploit this kind of access
query_metric_data. It is categorised as a Read tool in the OCI MCP Server MCP Server, which means it retrieves data without modifying state.
Register the OCI MCP Server MCP server in PolicyLayer and add a rule for query_metric_data: 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 OCI MCP Server. Nothing to install.
query_metric_data 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 query_metric_data 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 query_metric_data. 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.
query_metric_data is provided by the OCI MCP Server MCP server (jopsis/mcp-server-oci). 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 →