Solution pairs AI-ready metadata and semantic context with workflow-focused Skills, giving clients’ AI agents what they need to interpret Bloomberg data correctly and use it across financial workflows.

Bloomberg announced the launch of Bloomberg Enterprise Model Context Protocol (MCP), an AI access layer for Data License Plus (DL+), Bloomberg’s next-generation Data License offering. Built for the agentic AI era, the solution enables clients’ 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, helping firms move quickly and easily from AI experimentation to live production workflows.

Most tools can retrieve data points. Fewer can tell an agent what that data point means, how it was calculated, or whether it’s the right one for the task at hand. Bloomberg Enterprise MCP is built to close that gap, combining semantic context, AI-ready metadata, and workflow-focused Skills that will give agents the information they need to interpret results correctly and act on them with confidence, across research, portfolio, risk, and operations.

Marketing Technology News: MarTech Interview with Mark Listes, CEO @ Pendulum Intelligence

In practice, this changes how fast investors in the global capital markets can get from a question to an answer. Instead of first hunting for the right dataset and then reconciling identifiers by hand, or filing a request and waiting, users can simply ask for what they need in plain language and get back data that already carries the context to trust it: what currency it’s in, when it was priced, what it connects to. This shift, from time-consuming manual lookup to an answer you can act on immediately, is what moves generative AI from a pilot into something a firm can run in production every day.

“As generative AI adoption in financial services has grown, the bottleneck facing financial institutions has shifted from model capability to data readiness,” said Tony McManus, Global Head of Enterprise Data and Indices at Bloomberg. “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. On its own, a last price doesn’t say what currency it’s in or what kind of price it is. Connections were never the hard part. Readiness is, and that’s what we built Enterprise MCP to solve.”

Marketing Technology News: How MarTech Is Enabling Autonomous Brand Engagement Across Channels?

Key Features of Bloomberg Enterprise MCP

• AI-ready metadata and context: Bloomberg’s metadata describes what each field means, how it was calculated and when it applies, along with the qualifiers needed to make a number interpretable, such as the exchange, currency, price type, period, as-of date. A standalone number is meaningless to an agent; the metadata is what tells it what the value actually is and when it can be relied on.
• Semantic interfaces over that metadata: That same metadata is exposed via semantic search tools, so agents find the right field by describing what they need in natural language, instead of guessing mnemonics. Entity resolution does the same on the security side, mapping a name, ticker or description to the right instrument and its relationships to the issuing company — so agents don’t hard-code identifier lists. Metadata makes the data understandable; the semantic interface makes it findable.
• Breadth of content. Access Data License content through one interface: pricing and reference data across asset classes, company fundamentals and structure, economics and alternative data spanning across DL+ Live and the Qube Datastore (QDS). New content arrives as new capabilities for already connected agents, not as a new integration.
• Task-specific tool design: A single security discovery tool and a single field discovery tool cover the content set, rather than separate tools per asset class.
• Workflow Skills: Reusable procedures covering point-in-time universe retrieval, corporate action adjustment and revision history, which clients will be able to adopt and extend. The initial release will include 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.
• Entitlements and audit: Bloomberg validates a firm’s entitlements before returning data on any agent request, under standard Data License rights. Requests resolve against the Operational Datastore (ODS), and tool-level limits cap the securities and fields returned in a single call.
• Client-controlled execution: Bloomberg hosts and manages Enterprise MCP, while clients control the AI agents and applications that connect to it, including the models, prompts, instructions and other steering context used in their workflows.