{"slug": "federal-reserve-launches-fred-mcp-connector-to-plug-ai-agents-into-economic-data", "title": "Federal Reserve launches FRED MCP Connector to plug AI agents into economic data", "summary": "Federal Reserve Board Governor Christopher J. Waller announced the FRED MCP Connector on October 1, 2026 at FRED Con, hosted by the Federal Reserve Bank of St. Louis, letting AI agents query the St. Louis Fed's FRED economic database directly via the Model Context Protocol. Waller said AI agents now generate approximately 50% of FRED's traffic, which is growing at an annual rate of 150%, and that the connector at mcp.stlouisfed.org requires no separate API key and works with tools such as Claude. Waller cautioned that AI-driven data interpretation carries risks including inaccuracies, hallucinations, and source misattribution.", "body_md": "# Federal Reserve launches FRED MCP Connector to plug AI agents into economic data\n\nGovernor Christopher Waller says nearly half of FRED's traffic now comes from AI agents, and the database is being redesigned to serve them\n\nThe Federal Reserve’s most popular data tool is getting an AI upgrade. Its users already got there first.\n\nOn October 1, 2026, Federal Reserve Board Governor Christopher J. Waller announced the FRED MCP Connector at FRED Con, a conference hosted by the Federal Reserve Bank of St. Louis. The tool lets AI agents connect directly to FRED, the St. Louis Fed’s economic database. According to Waller, those agents now account for nearly half of the site’s traffic.\n\n## What the FRED MCP Connector actually does\n\nFRED holds more than 850,000 economic data series. It pulls its numbers from sources including the Bureau of Economic Analysis, the Bureau of Labor Statistics, and the Census Bureau.\n\nThe new connector runs on the Model Context Protocol, or MCP. Think of MCP as a universal power adapter for AI. Instead of every AI tool needing a custom cable to reach every database, MCP gives them a shared plug.\n\nIn practice, a user’s AI assistant can query FRED directly. It can find a series, pull the figures, and work with them without the user hunting through menus.\n\nThe connector is available at mcp.stlouisfed.org. It works with AI tools such as Claude, and it does not require a separate API key.\n\nThe connector also supports what the St. Louis Fed calls BYOAI, short for “Bring Your Own AI.” Users pick the assistant they already like, and FRED meets them there.\n\n### AI, tech, and the markets they move—in one daily briefing.\n\nDaily. Free. Join 34,000+ readers across crypto, finance, and policy.\n\n## Why the Fed is redesigning around bots\n\nThe numbers explain the urgency. FRED’s traffic is growing at an annual rate of 150%, and AI agents make up approximately 50% of it.\n\nWaller’s announcement framed the connector as a response to that shift. AI tools had previously struggled to interpret FRED’s data and to cite it correctly. A chatbot might grab the wrong series, mislabel a figure, or credit the wrong source.\n\nWaller said FRED’s human-centric design needs to evolve into something AI systems can use reliably. That means more precision and stronger documentation as automated queries multiply across economic research.\n\nBeyond the connector, Waller indicated that FRED will add AI tools to improve how users access, visualize, and interpret data. Natural-language search and more interactive features are part of that picture.\n\n## The caveats Waller put on the table\n\nWaller did not pitch this as a magic box. He cautioned that AI-driven data interpretation carries risks, including inaccuracies and hallucinations.\n\nHe also flagged source misattribution as a concern. An AI that pulls a correct number but credits it to the wrong agency still creates confusion downstream.\n\nWaller’s announcement also referenced growth challenges. When traffic grows at 150% a year, keeping systems fast and accurate becomes its own engineering puzzle.\n\n**Disclosure:** This article was edited by Diego Almada Lopez. For more information on how we create and review content, see our\n\n[Editorial Policy](https://cryptobriefing.com/editorial-policy/).", "url": "https://wpnews.pro/news/federal-reserve-launches-fred-mcp-connector-to-plug-ai-agents-into-economic-data", "canonical_source": "https://cryptobriefing.com/federal-reserve-fred-mcp-connector-ai/", "published_at": "2026-10-02 13:25:01+00:00", "updated_at": "2026-10-02 13:37:33.081808+00:00", "lang": "en", "topics": ["artificial-intelligence", "ai-agents", "agent-protocols", "ai-tools"], "entities": ["Federal Reserve", "Christopher J. Waller", "FRED", "FRED MCP Connector", "Federal Reserve Bank of St. Louis", "Model Context Protocol", "Claude", "Bureau of Labor Statistics"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/federal-reserve-launches-fred-mcp-connector-to-plug-ai-agents-into-economic-data", "markdown": "https://wpnews.pro/news/federal-reserve-launches-fred-mcp-connector-to-plug-ai-agents-into-economic-data.md", "text": "https://wpnews.pro/news/federal-reserve-launches-fred-mcp-connector-to-plug-ai-agents-into-economic-data.txt", "jsonld": "https://wpnews.pro/news/federal-reserve-launches-fred-mcp-connector-to-plug-ai-agents-into-economic-data.jsonld"}}