Project not found.

Data Flow: gdocs-daily-mcp-remote

arch-dataflow-gdocs-daily-mcp-remote Architecture

architecture draft

Project

Component	Purpose	Connection
Claude.ai iOS	User interface — sends MCP tool calls	HTTPS to MCP remote via Tailscale funnel
gdocs-daily-mcp-remote	MCP server — translates tool calls to Google API requests	Starlette/Uvicorn on port 8000 in k8s
mcp-remote-auth	OAuth proxy — manages 3-party token dance	Library imported by the server (not a separate service)
Google Drive API	File search — finds documents by title	HTTPS to googleapis.com, authenticated via OAuth access_token
Google Docs API	Document retrieval — fetches document content	HTTPS to googleapis.com, authenticated via OAuth access_token
TokenStore (PVC)	Encrypted token persistence	Local file on PersistentVolumeClaim at /app/data

Two Google APIs, not one. Google Drive API for search (files.list can filter by name and mimeType), Google Docs API for content retrieval (documents.get returns the structured body). Drive is the index, Docs is the content store.
mcp-remote-auth is a library, not a sidecar. It's pip-installed and runs in-process. No inter-service communication for auth — it's all in the same pod.
Token refresh is transparent. The setup_client_for_request callback refreshes the Google access_token using the stored refresh_token before every tool call. Claude never sees token expiry.
MCP access_token is long-lived (1 year). The token Claude.ai stores doesn't expire frequently — it's our own token, not Google's. Google's refresh_token is managed server-side.