Life Sciences: Adverse Event Triage with Claude Code: MCP Tool Boundary

A production playbook for adverse event triage in life sciences operations using Claude Code: mcp tool boundary, run-scoped inputs, logs, typed results, and artifacts.

Audience: Pharmacovigilance teams

The problem

Pharmacovigilance teams need adverse event triage to run repeatedly against case narratives, intake forms, medical history, and reporting rules. In life sciences 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 adverse event triage, 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 adverse event triage, 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: pharma-adverse-event-triage_lookup
agent: Claude Code
input_scope: /skill/.argo/inputs
credential_owner: broker
log_arguments: true
network_policy: allowlisted

Run this on Argo