Document Classification with Claude Code: MCP Tool Boundary
A production playbook for document classification in cross-industry operations using Claude Code: mcp tool boundary, run-scoped inputs, logs, typed results, and artifacts.
Audience: Operations teams routing large file intake
The problem
Operations teams routing large file intake need document classification to run repeatedly against mixed PDFs, emails, attachments, and routing labels. 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 document classification, 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 document classification, 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: document-classification_lookup
agent: Claude Code
input_scope: /skill/.argo/inputs
credential_owner: broker
log_arguments: true
network_policy: allowlisted
Run this on Argo