Retrieve detailed information for a specific trace by its trace ID. Returns the complete trace with all spans, including service names, operation names, timestamps, durations, tags, and any errors.
AI agents call get_trace to retrieve information from K8s Observability MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries observability data (distributed traces) from a Kubernetes cluster. It has no capability to modify, delete, execute code, or trigger actions. The blast radius of misuse is limited to information disclosure of trace telemetry, which in an observability context is typically non-sensitive operational metadata. No state changes occur.
From the tool's definition Tool description states 'Retrieve detailed information for a specific trace' — a read-only query operation with no side effects. Returns trace data (spans, service names, timestamps, durations, tags, errors) without modification or execution.
Attacks that exploit this kind of access
Retrieve detailed information for a specific trace by its trace ID. Returns the complete trace with all spans, including service names, operation names, timestamps, durations, tags, and any errors. It is categorised as a Read tool in the K8s Observability MCP MCP Server, which means it retrieves data without modifying state.
Register the K8s Observability MCP server in PolicyLayer and add a rule for get_trace: 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 K8s Observability MCP. Nothing to install.
get_trace 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_trace 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_trace. 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_trace is provided by the K8s Observability MCP server (martinimarcello00/k8s-observability-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 →