
Irfan Hussain
The financial services industry is undergoing a transformation, where AI is being embedded into traditional workflow and API-driven software, and where humans collaborate seamlessly with chat and agent-based AI systems.
Generative AI models and agent-based systems are transforming how data and analytics are consumed within financial workflows. AI no longer simply calls an API – it reasons with it, using data and calculations as tools to shape its actions, to adapt, and to iteratively pursue complex goals.
For this transformation to be successful, the depth, breadth, quality and accessibility of data is a pre-requisite. That’s why LSEG is pioneering AI Ready Content and delivering it through open standards such as the Model Context Protocol (MCP) on top of our 33 petabytes of unparalleled data with history stretching back decades.
Barriers to scaling AI in financial services
Despite major advances in AI, scaling it across financial services presents several hurdles:
- Finance specific context: Large Language Models (LLMs) struggle to correctly interpret specialised language and data structures across asset classes
- Accurate calculations: Financial calculations demand accuracy and precision, not probabilistic approximation or pattern matching
- Governance and rights: Data use must respect entitlements and rights, and be underpinned by data provenance and lineage
LSEG’s AI Ready Content aims to address these challenges head on – delivering financial data with a semantic data model, deterministic calculations, scalable lineage and robust rights management. We champion MCP and other tools to operationalise consistent and scalable access to LSEG’s vast 33-petabyte multi-asset content – structured and unstructured, spanning private and public markets, from intraday to multi-year history. Our AI Ready Content and MCP server are essential enablers for our customers to build their own AI solutions safely, with faster time to market, and with appropriate rights and entitlements.
Key features of LSEG's AI Ready Content
1) Semantic data model
For LLMs to reason effectively in the financial domain, they require contextual grounding in specialised vocabulary across fixed income, equities, indices, private markets, and beyond.
LSEG’s semantic model provides that foundation – defining, for example:
- Entities and identifiers: Issuers, instruments, venues, benchmarks, curves
- Relationships and hierarchies: Parent / child, corporate actions, mappings, risk measures in pricing
- Time semantics: Point in time views, effective dates, revision flags, versioning
- Financial context attributes: Annotations, units, calendars, market conventions, quote types
As an example, the attribute value “USD 3M SOFR” encodes currency, rate type, and tenor, implying conventions and calendars.
This common semantic model removes ambiguity, ensuring that every query or calculation has the same meaning across desks, systems, and AI models.
2) Accurate calculations
Financial calculations must be accurate, precise, auditable, and reproducible. Current LLMs, by contrast, calculate probabilistically with pattern matching. We address this barrier by pairing them with access to LSEG’s deterministic calculations: our AI Ready Content has explicit inputs, outputs and embedded metadata across various financial workflows, supporting both LSEG and user-defined derived calculations. This enables a range of capabilities – including:
- Deterministic algorithms and pinned conventions (e.g. corporate bond pricing)
- Typed parameters with validation and defaults (e.g. payouts schemas for different types of structured products)
- Structured outputs with provenance (e.g. what curves are used in pricing a forward instrument)
With AI Ready Content, we bridge the gap between reasoning and rigour and enable AI to use financially correct data in its responses.
3) Operations, entitlements and runtime guardrails
AI in the financial services industry must be traceable, reproducible and auditable at scale. LSEG has controls for AI Ready Content which support:
- Existing licensing and content entitlement SLAs, and resiliency to ensure latency, retries and more
- Data tracing and lineage
- Data metering and usage monitoring
With our AI Ready Content, LLM data consumption is attributable, metered, and compliant with data rights. This gives customers control over what data is used, in what context and where.
The differentiating power of MCP
MCP is a key component of LSEG’s AI integration strategy. Through LSEG-managed MCP servers, clients access a consistent, structured interface to the full depth of LSEG content. Our governed and deterministic data enables safe, scalable, and explainable AI.
Pioneered as an open standard, MCP is a method for AI models to discover, invoke, and reason with enterprise APIs and data sources. This open interface for agents and LLMs allows for a consistent experience across a variety of platforms and providers. We will continue to support more open standards as they emerge.
Example use cases for LSEG’s AI Ready Content
- Fixed income analytics: “Price this bond and show my DV01 under a 25-bps shift.” The MCP server resolves term-sheets, conventions, and curves, returning a deterministic result ready to book.
- Macroeconomic data: “What was today’s CPI print vs consensus?” The MCP server handles revision flags, time zones, and data freshness before the model interprets results.
- Estimates and earnings: “Summarise ACME’s Q2 margin expectations and recent revisions.” The MCP server enforces issuer normalisation, entitlements, and links to underlying analyst notes.
- Intraday pricing: “Summarise price movements across my top 10 corporate bonds in the past day and explain drivers”. The MCP server normalises instruments, validates priority, and returns clean, attributed data.
These use cases illustrate how agents and humans can use LSEG’s AI Ready Content to reduce operational friction, strengthen governance, and dramatically cut time to insight.
Conclusion: Scaling AI in finance with AI Ready Content and MCP
The breadth and depth of LSEG’s data is unparalleled: 19 million fixed income securities, 1.3 million indexes, 140 billion OTC ticks per year, and an average of 220 billion market updates daily. Additionally, LSEG provides data on 27 million private companies, processes 250,000 estimate revisions daily, 3.7 million company events annually, over 65 million company filings and approximately 90,000 deals transactions each year with 50 years of history. This extensive collection of structured and unstructured data is underscored by LSEG’s commitment to delivering data that can be trusted.
This AI Ready Content accelerates insight, reduces ambiguity, and enhances reproducibility. MCP extends these benefits by enabling standardised, governable, and interoperable AI-to-data communication. LSEG-managed MCP servers provide the foundation for secure, reliable, and up-to-date financial intelligence.
Users must refer to their applicable LSEG data licensing agreement, which sets out rights and obligations with regard to LSEG data usage.
Legal Disclaimer
Republication or redistribution of LSE Group content is prohibited without our prior written consent.
The content of this publication is for informational purposes only and has no legal effect, does not form part of any contract, does not, and does not seek to constitute advice of any nature and no reliance should be placed upon statements contained herein. Whilst reasonable efforts have been taken to ensure that the contents of this publication are accurate and reliable, LSE Group does not guarantee that this document is free from errors or omissions; therefore, you may not rely upon the content of this document under any circumstances and you should seek your own independent legal, investment, tax and other advice. Neither We nor our affiliates shall be liable for any errors, inaccuracies or delays in the publication or any other content, or for any actions taken by you in reliance thereon.
Copyright © 2025 London Stock Exchange Group. All rights reserved.
The content of this publication is provided by London Stock Exchange Group plc, its applicable group undertakings and/or its affiliates or licensors (the “LSE Group” or “We”) exclusively.
Neither We nor our affiliates guarantee the accuracy of or endorse the views or opinions given by any third party content provider, advertiser, sponsor or other user. We may link to, reference, or promote websites, applications and/or services from third parties. You agree that We are not responsible for, and do not control such non-LSE Group websites, applications or services.
The content of this publication is for informational purposes only. All information and data contained in this publication is obtained by LSE Group from sources believed by it to be accurate and reliable. Because of the possibility of human and mechanical error as well as other factors, however, such information and data are provided "as is" without warranty of any kind. You understand and agree that this publication does not, and does not seek to, constitute advice of any nature. You may not rely upon the content of this document under any circumstances and should seek your own independent legal, tax or investment advice or opinion regarding the suitability, value or profitability of any particular security, portfolio or investment strategy. Neither We nor our affiliates shall be liable for any errors, inaccuracies or delays in the publication or any other content, or for any actions taken by you in reliance thereon. You expressly agree that your use of the publication and its content is at your sole risk.
To the fullest extent permitted by applicable law, LSE Group, expressly disclaims any representation or warranties, express or implied, including, without limitation, any representations or warranties of performance, merchantability, fitness for a particular purpose, accuracy, completeness, reliability and non-infringement. LSE Group, its subsidiaries, its affiliates and their respective shareholders, directors, officers employees, agents, advertisers, content providers and licensors (collectively referred to as the “LSE Group Parties”) disclaim all responsibility for any loss, liability or damage of any kind resulting from or related to access, use or the unavailability of the publication (or any part of it); and none of the LSE Group Parties will be liable (jointly or severally) to you for any direct, indirect, consequential, special, incidental, punitive or exemplary damages, howsoever arising, even if any member of the LSE Group Parties are advised in advance of the possibility of such damages or could have foreseen any such damages arising or resulting from the use of, or inability to use, the information contained in the publication. For the avoidance of doubt, the LSE Group Parties shall have no liability for any losses, claims, demands, actions, proceedings, damages, costs or expenses arising out of, or in any way connected with, the information contained in this document.
LSE Group is the owner of various intellectual property rights ("IPR”), including but not limited to, numerous trademarks that are used to identify, advertise, and promote LSE Group products, services and activities. Nothing contained herein should be construed as granting any licence or right to use any of the trademarks or any other LSE Group IPR for any purpose whatsoever without the written permission or applicable licence terms.