AI-Ready Financial Data

Comprehensive income statements, balance sheets, and cash flow statements for 180,000+ public companies—standardized, historical, and as-reported data with direct links to source filings.

Consensus forecasts, analyst estimates, and company guidance for revenue, earnings, and key financial metrics across 60,000+ active and inactive companies. Track expectations vs. actuals across quarters and fiscal years.

Hard-to-find financial statements and key metrics for 60M+ private companies globally, enabling valuation, credit analysis, and target screening beyond public markets.

Earnings calls, presentations, and shareholder meetings in structured, speaker-tagged format, ready for sentiment analysis, keyword extraction, and AI summarization.

Detailed M&A, private equity, venture capital, and strategic investment data, including deal terms, valuations, advisors, and participants across global markets.

Ownership structures, subsidiaries, joint ventures, and key executive relationships. Map corporate hierarchies and operational connections between independent companies.

Business descriptions, competitors, alternative names, industry classifications, and company profiles—essential context for research, screening, and competitive analysis.

Real-time corporate events, announcements, and material changes—including leadership transitions, regulatory actions, strategic initiatives, and operational updates.

Detailed profiles of executives, board members, and key decision-makers—including career history, education, compensation, and board affiliations across public and private companies.

"Summarize the key takeaways from Alphabet's most recent earnings call, focusing on AI capex and cloud growth."

"What is the consensus EPS estimate for Apple's next 3 fiscal years?"

"Compare Netflix's Q4 2024 revenue: guidance vs. consensus estimate vs. actual. Where was the biggest gap?"

"What was Microsoft's EBITDA from 2022 through 2025, and what line items drove the biggest YoY changes?"

"Compare Tesla, Rivian, and Lucid's gross margins over the past 8 quarters."

"List all acquisitions completed by Nvidia since 2020. Which of them were over $5 billion?"

"How much total capital has Stripe raised across all funding rounds to date?"

“Which healthcare companies raised Series B funding in Q4 2025?"

"Pull the 2024 income statement for Cambridge Display Technology."

"Show me the 30-day price volatility for Tesla and compare it to other EV manufacturers."

"Find all mentions of 'tariffs' or 'trade policy' in Caterpillar's last 4 earnings transcripts and analyze the tone shift."

"What was the biggest single-day price drop for Alibaba in the last year?"

"Do Boeing and Lockheed Martin share any common competitors?"

"Compare Ford's 'Model E' (EV) segment revenue to their traditional 'Ford Blue' segment over the past 2 years."

"Show me Amazon's operating income by business segment over the last 4 quarters. Which segment is the margin engine?"

"What was the combined market cap of the Magnificent 7 at year end 2025?"

"Analyze Nvidia and TSMC stock price trends over the last 6 months—how correlated are they?"

"Plot Apple's total enterprise value for each of the past four fiscal quarters and identify any changes in shares outstanding."

The Kensho LLM-Ready API is a specialized data connection designed for seamless interaction with large language models (LLMs). It links S&P Global's financial datasets directly to LLMs like ChatGPT, Claude, and others.

The API is optimized for LLMs by offering structured, deterministic data with consistent schemas that support natural language queries and function calling patterns, eliminating the need for data preprocessing. It can be accessed through the Model Context Protocol (MCP) server or the kFinance Python library, which streamlines authentication and integration. Every query translates into traceable, reproducible function calls or code, connecting directly to S&P Global's database.

The Kensho LLM-Ready API uses pre-written SQL queries that activate when you ask natural language questions in ChatGPT, Claude, or any MCP-compatible AI platform. When you query "What was Apple's EBITDA in 2025?", the LLM selects the appropriate tool, the API executes a deterministic SQL query (no AI-generated code), and returns accurate S&P Global data with metadata and source document links—ensuring consistent, reliable financial intelligence.

Model Context Protocol (MCP) is an open standard developed by Anthropic that enables universal AI platform integration—like USB-C for financial data connections. Kensho's hosted MCP server allows S&P Global datasets to connect seamlessly to Claude, ChatGPT, Microsoft Copilot, Databricks, and any MCP-compatible platform without custom integrations, providing plug-and-play access to trusted financial intelligence across AI applications.

The Kensho LLM-Ready API currently includes:

• S&P Capital IQ Financials (income statements, balance sheets, cash flows)
• S&P Capital IQ Estimates (consensus forecasts, analyst estimates, guidance)
• Private Company Financials (revenue, profitability, and key metrics)
• Machine-Readable Transcripts (earnings calls, speaker-tagged)
• Transactions (M&A, PE/VC deals, valuations)
• Business Relationships (ownership structures)
• Company Intelligence (competitors, business descriptions)
• Key Developments (corporate events)
• Professionals (executive profiles, compensation data)

—all with source document links.

S&P Global Agent Skills are pre-built financial workflow templates for AI platforms like Claude Cowork—enabling automated company tearsheets, M&A target profiles, earnings previews, and competitive analysis using S&P Capital IQ data. Built on Model Context Protocol (MCP) and the LLM-Ready API, these skills combine structured prompts with deterministic data retrieval, allowing financial professionals to complete complex multi-step research tasks through natural language commands in ChatGPT, Claude, and other AI assistants.

For LLM integrations, accuracy depends on the specific model and architecture used. The API itself is deterministic, meaning it returns consistent results, but users can view and audit the Python code generated by the LLM. This allows verification of which steps were taken to retrieve the answer directly from the S&P Global database.

For the most accurate results when querying company data, we recommend using these identifier types in the following order:

• CapIQ Company ID (S&P Capital IQ identifier e.g. "C_<ciq_identifier>")
• Ticker symbol (for current public companies e.g., "AAPL", "MSFT")
• ISIN (International Securities Identification Number)
• CUSIP (Committee on Uniform Securities Identification Procedures number)
• Legal company name (e.g., "Apple Inc.", "Microsoft Corporation")

S&P Global does not receive or see natural language questions—only the code used to make API calls. This approach limits exposure of confidential information. For additional information about data privacy, please see the S&P Global Data Processing Policy.

No. The LLM-ready API is a data retrieval tool designed to be deployed in customer LLM applications or third-party applications. Kensho and S&P Global have no way to track users' prompts or other material non-public information (MNPI).