AlphaCreek Blog
Latest Posts
All Categories
announcements
AlphaCreek Brings Citation-Grade SEC Filing Intelligence to Perplexity
AlphaCreek is an SEC filing retrieval layer for AI agents, and it is now available as a connector inside Perplexity Computer. With one connection, Perplexity users can access filings across 6,000+ US tickers and UK FCA National Storage Mechanism disclosures across 380 Official List issuers, then return answers with links to the specific source passage behind each claim. This post explains what that changes for financial research, what you can ask today, and where AlphaCreek is going next.
FCA NSM Filings for AI Agents: Same MCP as SEC
AlphaCreek now supports UK FCA National Storage Mechanism filings through the same hosted connection as SEC EDGAR, with answers you can trace to the original disclosure.
product-comparisons
SEC EDGAR API vs MCP for AI Investment Research Products
The SEC EDGAR API is strong for XBRL numbers and filing lists. It does not return filing narrative. For qualitative analysis you can parse 10-K HTML yourself — or use hosted MCP that already cites passages.
SEC EDGAR MCP Servers (2026): Open Source vs Hosted
Compare sec-edgar-mcp, EdgarTools, edgar.tools, and AlphaCreek. Pick self-hosted or hosted SEC EDGAR MCP by job: XBRL, signals, or cited passages.
sec-filing-analysis
AlphaCreek Powers Citation-Backed SEC Research in FlexReport
FlexReport Finance now uses AlphaCreek so AI equity research can open every material SEC claim to the exact filing passage behind it.
AlphaCreek brings citation-grade SEC filings intelligence inside OpenBB
AlphaCreek is now available as an MCP server inside OpenBB Workspace, accessible from the App Marketplace. Connect it once, and OpenBB Copilot can read, navigate, and quote the full text of SEC filings — every 10-K, 10-Q, 20-F, 6-K, and 8-K — with a clickable link back to the exact paragraph behind every number.
benchmarks
development
How to Build an SEC Filing Agent Without Naive RAG
Build a navigation-first SEC agent that selects the right filing, inspects its TOC, reads exact sections, and returns passage-level citations.
How to Parse SEC 10-K Filings Into Sections for AI Agents
Style-based parsing turns a 10-K into titled sections an agent can read. On NVIDIA’s FY2026 filing, 1,211 flat HTML blocks become 534 AlphaCreek nodes — including Our Businesses with a live citation URL.
SEC Filing AI: Naive RAG vs Structured RAG vs Navigation
Compare three retrieval architectures for 10-K and 10-Q agents. See where each fails—and why navigation-first retrieval produces verifiable answers.