Large language models are fluent, confident, and perfectly willing to invent a P/E ratio or cite a filing that doesn't exist. In regulated finance, that isn't a quirk — it's disqualifying. This talk shares the open-source patterns I developed building MCP (Model Context Protocol) servers that connect AI agents to primary financial sources: SEC EDGAR filings, XBRL fundamentals, FRED macro data, insider and congressional trades.

The core idea is verification before interpretation. I'll walk through concrete, reusable patterns: grounding every model claim against a primary source before it reaches a user; failing closed when a figure can't be tied to a document; designing the model layer to be swappable so no single provider is load-bearing; and structuring tool outputs so an agent reasons over cited facts rather than its own memory.

Attendees will leave with practical architectural patterns for building trustworthy agentic finance tools on open standards — applicable whether you're deploying internally or contributing to open projects. Code and server examples are public.