--- title: "Bloomberg Launches Enterprise MCP to Connect Financial Data with AI Agents" summary: "Bloomberg has launched Bloomberg Enterprise Model Context Protocol (MCP), an AI access layer for its Data License Plus offering that enables client AI agents to discover, understand, and retrieve licensed Bloomberg data across more than 100 million securities and over 50,000 fields via a standardized interface." url: "https://theauthority.report/articles/bloomberg-launches-enterprise-mcp-to-connect-financial-data-with-ai-agents-e23505dd" publisher: "The Authority Report" section: "AI Discovery" author: "The Authority Desk" datePublished: "2026-10-04T16:50:20.762Z" dateModified: "2026-10-04T16:50:20.762Z" sources: - title: "Bloomberg Launches Enterprise MCP to Seamlessly Connect Bloomberg Data with Clients' Enterprise AI Applications" url: "https://martechseries.com/predictive-ai/ai-platforms-machine-learning/bloomberg-launches-enterprise-mcp-to-seamlessly-connect-bloomberg-data-with-clients-enterprise-ai-applications/" --- # Bloomberg Launches Enterprise MCP to Connect Financial Data with AI Agents *Bloomberg has launched Bloomberg Enterprise Model Context Protocol (MCP), an AI access layer for its Data License Plus offering that enables client AI agents to discover, understand, and retrieve licensed Bloomberg data across more than 100 million securities and over 50,000 fields via a standardized interface.* Bloomberg announced on 29 September 2026 the launch of Bloomberg Enterprise Model Context Protocol (MCP), described as an AI access layer for Data License Plus (DL+), the company's next-generation data licensing product. The system is designed to allow clients' AI agents to work with Bloomberg financial data through a standardized interface, with the stated goal of helping firms move from AI experimentation to live production workflows. According to Bloomberg, the product enables AI agents to discover, understand, and retrieve licensed Bloomberg data across more than 100 million securities and over 50,000 fields through a standardized MCP interface. The company said the offering is built specifically for what it characterizes as the agentic AI era. Tony McManus, Global Head of Enterprise Data and Indices at Bloomberg, framed the problem the product is intended to address. As generative AI adoption in financial services has grown, the bottleneck facing financial institutions has shifted from model capability to data readiness, he said. McManus added that agents capable of complex reasoning have still failed at basic tasks because of insufficient data context: We've seen agents that reason well but still can't answer a basic question about a position, because the data reaching them carries no indication of what it actually represents. Bloomberg said the core challenge it is trying to solve is the lack of semantic context attached to raw data values. The company stated that On its own, a last price doesn't say what currency it's in or what kind of price it is. Enterprise MCP is built to supply the metadata and context agents need to correctly interpret financial data, with McManus noting: Connections were never the hard part. Readiness is, and that's what we built Enterprise MCP to solve. The product combines several components, according to Bloomberg. AI-ready metadata describes each field's meaning, calculation method, and applicable qualifiers such as exchange, currency, price type, and as-of date. Semantic search tools allow agents to identify the correct data field by describing what they need in natural language rather than using data mnemonics. Entity resolution maps names, tickers, or descriptions to specific instruments. Bloomberg also said the product includes what it calls Workflow Skills — reusable procedures for tasks such as point-in-time universe retrieval, corporate action adjustment, and revision history. The initial release is described as including skills to identify outliers in a set of tickers, review trades that breach accepted price deviation thresholds and assess securities and trades for potential sanctions exposure, with additional workflow-focused Skills to come. On scope, Bloomberg said the product provides access to pricing and reference data across asset classes, company fundamentals and structure, economics and alternative data spanning across DL+ Live and the Qube Datastore (QDS). The company said new content arrives as new capabilities for already connected agents, rather than requiring a new integration. Regarding data governance, Bloomberg said it validates a firm's entitlements before returning data on any agent request, under standard Data License rights, and that tool-level limits cap the securities and fields returned in a single call. Bloomberg hosts and manages Enterprise MCP, while clients retain control over the AI agents and applications that connect to it, including models, prompts, and instructions. The announcement was distributed via PR Newswire and republished by Martech Series on 29 September 2026. No independent assessment of the product's claims was available in the source material. ## Sources - [Bloomberg Launches Enterprise MCP to Seamlessly Connect Bloomberg Data with Clients' Enterprise AI Applications](https://martechseries.com/predictive-ai/ai-platforms-machine-learning/bloomberg-launches-enterprise-mcp-to-seamlessly-connect-bloomberg-data-with-clients-enterprise-ai-applications/) *Cite as: The Authority Report, "Bloomberg Launches Enterprise MCP to Connect Financial Data with AI Agents", https://theauthority.report/articles/bloomberg-launches-enterprise-mcp-to-connect-financial-data-with-ai-agents-e23505dd (as of 2026-10-04).*