Pull Request Review with Claude Code: MCP Tool Boundary

A production playbook for pull request review in cross-industry operations using Claude Code: mcp tool boundary, run-scoped inputs, logs, typed results, and artifacts.

Audience: Developer tools teams

The problem

Developer tools teams need pull request review to run repeatedly against diffs, CI logs, ownership maps, and review policy. 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 pull request review, 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 pull request review, 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: pull-request-review_lookup
agent: Claude Code
input_scope: /skill/.argo/inputs
credential_owner: broker
log_arguments: true
network_policy: allowlisted

Run this on Argo