Healthcare: Medical Record Summarization with Claude Code: MCP Tool Boundary

A production playbook for medical record summarization in healthcare operations using Claude Code: mcp tool boundary, run-scoped inputs, logs, typed results, and artifacts.

Audience: Healthcare admin teams preparing case reviews

The problem

Healthcare admin teams preparing case reviews need medical record summarization to run repeatedly against clinical notes, discharge summaries, lab reports, and referral documents. In healthcare 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 medical record summarization, 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 medical record summarization, 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: healthcare-medical-record-summarization_lookup
agent: Claude Code
input_scope: /skill/.argo/inputs
credential_owner: broker
log_arguments: true
network_policy: allowlisted

Run this on Argo