Usage Anomaly Investigation with Claude Code: MCP Tool Boundary
A production playbook for usage anomaly investigation in cross-industry operations using Claude Code: mcp tool boundary, run-scoped inputs, logs, typed results, and artifacts.
Audience: Growth and infra teams
The problem
Growth and infra teams need usage anomaly investigation to run repeatedly against usage exports, logs, billing events, and customer metadata. In cross-industry operations, the pain is not one good answer; it is repeatability, auditability, exception handling, and evidence that survives handoff.
Implementation path
Expose only the MCP tools needed for usage anomaly investigation, validate tool arguments, keep credentials in the owning service, and log each call outside the sandbox.
Tradeoffs and failure modes
Narrow tool boundaries reduce agent flexibility, but make the integration reviewable and supportable. For usage anomaly investigation, the practical test is whether a second run can be debugged, retried, and consumed by a product without reading the raw agent transcript.
Tool policy
tool: usage-anomaly-investigation_lookup
agent: Claude Code
input_scope: /skill/.argo/inputs
credential_owner: broker
log_arguments: true
network_policy: allowlisted
Run this on Argo