Kensho LLM-Ready API

What it does

The Kensho LLM-ready API turns natural-language requests from a large language model into function calls against S&P Global datasets, returning financial data such as company information, financial statements, historical market data, and securities information. It is a REST API with a Python client called kFinance, and it can also be reached through a Model Context Protocol (MCP) server.

Teams use it to connect an LLM of their choice to S&P Global data for tasks such as company research, pitch book preparation, and due-diligence briefs with comps tables and peer benchmarking. The service includes no AI model of its own; customers bring their own LLM, orchestration layer, and user interface, or use a third-party platform. Because kFinance supplies the functions an LLM needs, each query is translated into traceable, reproducible function calls or code. It can also be used without an LLM as a plain Python SDK.

The API is aimed at engineering, product, and business teams in financial services building LLM solutions on S&P Global data. Access requires a trial or subscription, with Okta-based login and an email activation invitation. Production workflows should use public-private keypair authentication rather than refresh tokens or browser login, which the docs advise against for production use.

What it can do

• Translates natural-language questions into function calls against S&P Global datasets via the kFinance Python client
• Exposes data retrieval through a Model Context Protocol (MCP) server for MCP-compatible GenAI applications
• Retrieves company information, financial statements, historical market data, and global securities data
• Provides access to S&P Capital IQ Financials, Market Data, Business Relationships, Earnings Call Transcripts, Company Intelligence, and M&A Transactions
• Supports authentication via browser login, refresh token, or public-private keypair
• Can be used with or without an LLM as a Python SDK for S&P Global datasets

Works with

• Model Context Protocol (MCP) server for MCP-compatible GenAI applications
• Python Package Index distribution of the kFinance client

Example workflows

Financial research brief

Input: a natural-language request for a company's financials and peer set through an LLM connected to kFinance. Steps: the LLM calls kFinance functions to pull financial statements and business relationships, then assembles them. Output: retrieved data the user can fold into a research report or pitch book.

Comps table from a Python script

Input: a list of company identifiers in a Python script using the kFinance client. Steps: authenticate with a keypair, call the client to retrieve financials and market data for each company, and write results to a table. Output: a dataset ready for comparative analysis, produced without an LLM.

Before you choose

• Prompts are not visible to S&P Global, but customers should handle confidential and material non-public information within their own LLM application.
• Refresh tokens expire after two weeks and are not recommended for production use.
• Supported LLM vendors and the interface layer are the customer's responsibility; the product supplies no model.

Listed under

• Data

Get started

Click Request More Information on the Marketplace listing or email [email protected] for a trial.

1. Request access through the Kensho LLM-ready API listing on the S&P Global Marketplace or email [email protected] for a trial.
2. Obtain Okta credentials and activate the account from the email invitation.
3. Install the kFinance Python client and authenticate, using public-private keypair authentication for production workflows.

Contact [email protected] to start a trial or explore purchasing. Rates and plan terms are confirmed directly.

We couldn’t find published prices for Kensho LLM-Ready API. See their pricing page ↗

Sources for this overview

Product pages, documentation, and pricing checked 29 Oct 2026. Each source supports part of the overview; availability and prices can change.

• Overview: LLM-ready API & MCP Server | Kensho Docs ↗docs.kensho.com
• Frequently Asked Questions | Kensho Docs ↗docs.kensho.com
• Authentication | Kensho Docs ↗docs.kensho.com
• Support | Kensho Docs ↗docs.kensho.com

Company website

spglobal.com: product, pricing and policy pages

Web archive

When the site first appeared

YC directory mirror

Batch and company name

Web search

Confirms the official site

Social accounts

Accounts the company links, and its posts on X

Human review

Checked by a person

Last checked 29 Oct 2026. Every field keeps its source and date; unknown means we couldn’t confirm it.