Kensho website screenshot

Kensho

Kensho Technologies is the AI innovation hub of S&P Global, building machine learning and AI systems that structure, connect, and extract meaning from the world's financial and business data. Kensho's developer platform exposes a suite of production APIs: Scribe for speech-to-text transcription of audio and video, Extract for turning PDF documents into structured JSON, NERD for named-entity recognition and disambiguation against Wikimedia and S&P Capital IQ knowledge bases, and the LLM-ready API (kfinance) that connects LLMs, agents, and AI applications to S&P Global's trusted data through Adaptive Retrieval and a hosted, OAuth-secured Model Context Protocol (MCP) server. Authentication is bearer-token based, issued from Kensho's services platform via personal tokens or production key pairs, with OAuth 2.0 (authorization code, client credentials, and refresh token flows, PKCE, and dynamic client registration) for the MCP surface.

Kensho publishes 4 APIs on the APIs.io network. Tagged areas include Company, Artificial Intelligence, Machine-Learning, Financial Data, and Speech-to-Text.

The Kensho catalog on APIs.io includes 1 event-driven AsyncAPI specification.

Kensho’s developer surface includes documentation, API reference, getting-started guide, authentication, signup flow, support, changelog, and 21 more developer resources.

43.4/100 developing ▬ flat Agent 51/100 agent ready saas Full breakdown ↓
scored 2026-08-30 · rubric v0.17.2
AccessSelf serve
4 APIs 2 MCP Servers
CompanyArtificial IntelligenceMachine-LearningFinancial DataSpeech-to-TextTranscriptionDocument ExtractionNamed Entity RecognitionNatural Language ProcessingLLMMCPRetrievalS&P Global

Kin Score

Kin Score Kin Score How this is scored →
scored 2026-08-30 · rubric v0.17.2
Composite quality — 43.4/100 · developing
Contract Quality 10.7 / 25
Developer Ergonomics 13.8 / 20
Access Clarity 3.2 / 20
Operational Transparency 5.5 / 13
Contract Governance 2.2 / 12
Discoverability 8.2 / 10
Agent readiness — 51/100 · agent ready
Machine-Readable Contract 18 / 18
Agentic Access Contract 0 / 10
Documented Reversibility 0 / 6
MCP Server 12 / 12
Machine-Readable Auth 10 / 10
Idempotency 0 / 9
Stable Error Semantics 8 / 8
Request/Response Examples 0 / 7
Rate-Limit Signaling 0 / 7
Typed Event Surface 6 / 6
Agent Skills 5 / 5
Well-Known Catalog 0 / 4
Consent & Bot Identity 0 / 3
A2A Agent Card 0 / 8
Dry-Run / Simulate Mode 0 / 4
Delegated User Identity 6 / 6
Protected Resource Metadata 5 / 5
Registration Without a Human 6 / 6
Agentic Commerce Surface 0 / 5
Improve this rating by publishing the missing artifacts — every area above can be raised, and the full rubric is at apis.io/rating/. This rating is computed from github.com/api-evangelist/kensho: open an issue to ask a question, or submit a pull request to add artifacts. Want it done for you? Prioritized profiling — $2,500 →

APIs 4

Individual APIs this provider publishes, each with its own machine-readable definition.

Kensho Scribe

Asynchronous speech-to-text transcription API that turns audio and video into text with high accuracy. Supports batch, real-time, and human-in-the-loop transcription, multipart ...

Kensho Extract

Document intelligence API that transforms PDF documents into structured JSON, with hierarchical extraction, optical character recognition (OCR), enhanced table extraction, and b...

Kensho NERD

Named Entity Recognition and Disambiguation API that identifies and links concepts in text to knowledge bases (Wikimedia for general entities, S&P Capital IQ for financial organ...

Kensho LLM-ready API (kfinance)

LLM-ready API that connects LLMs, agents, and AI applications to S&P Global's trusted data through flexible retrieval, Adaptive Retrieval data agents, a Python library (kensho-k...

MCP Servers 2

Model Context Protocol servers that expose these APIs to AI agents.

Kensho MCP Server

MCP SERVER

Kensho MCP Server

Official hosted Model Context Protocol (MCP) server for the Kensho / S&P Global LLM-ready API (kfinance). Exposes S&P Global's trusted financial data to LLMs and agents. Verifie...

MCP SERVER

Event Specifications 1

AsyncAPI definitions for this provider's event-driven and streaming APIs.

Security Posture 3

Authentication, domain security, vulnerability disclosure, and trust-center signals.

Kensho Authentication

http/oauth2 · 4 schemes

SECURITY

Kensho Domain Security

TLSv1.3 · DMARC

SECURITY

Kensho Trust Center

SOC 2

SECURITY

Scopes 1

OAuth scopes governing access to this provider's APIs.

Kensho Scopes

2 scopes · authorizationCode/clientCredentials/refreshToken

2 scopes

SCOPES

Resources

Get Started 3

Portal, sign-up, and the first successful call

Documentation 2

Reference material describing how the API behaves

Agent Surfaces 4

MCP servers, agent skills, and machine-readable catalogs

Design & Contract 5

Pagination, idempotency, versioning, errors, and events

Build 3

SDKs, sample code, and the tooling you integrate with

Access & Security 6

Authentication, authorization, and security posture

Operate 4

Status, limits, changes, and where to get help

Company 1

The organization behind the API

Source (apis.yml)

apis.yml Raw ↑
aid: kensho
name: Kensho
description: 'Kensho Technologies is the AI innovation hub of S&P Global, building machine learning and AI systems that structure,
  connect, and extract meaning from the world''s financial and business data. Kensho''s developer platform exposes a suite
  of production APIs: Scribe for speech-to-text transcription of audio and video, Extract for turning PDF documents into structured
  JSON, NERD for named-entity recognition and disambiguation against Wikimedia and S&P Capital IQ knowledge bases, and the
  LLM-ready API (kfinance) that connects LLMs, agents, and AI applications to S&P Global''s trusted data through Adaptive
  Retrieval and a hosted, OAuth-secured Model Context Protocol (MCP) server. Authentication is bearer-token based, issued
  from Kensho''s services platform via personal tokens or production key pairs, with OAuth 2.0 (authorization code, client
  credentials, and refresh token flows, PKCE, and dynamic client registration) for the MCP surface.'
url: https://raw.githubusercontent.com/api-evangelist/kensho/refs/heads/main/apis.yml
deliveryModel:
  model: saas
  open_source: false
  commercial: true
  callable_host: false
  label: Hosted service · you call their endpoint
  confidence: medium
  source:
  - pricing
  generated: '2026-08-28'
  method: derived
accessModel:
  pricing: unknown
  onboarding: self-serve
  trial: false
  try_now: false
  public: false
  label: Self-serve signup
  confidence: medium
  source:
  - authentication
  generated: '2026-07-22'
  method: derived
image: https://services.kensho.com/icons/favicon-32x32.png
x-type: company
x-source: vc-portfolio
x-backed-by:
- general-catalyst
x-parent: sp-global
x-tier: enriched
x-tier-reason: portfolio-lead-enriched
specificationVersion: '0.23'
created: '2026-07-17'
modified: '2026-07-19'
tags:
- Company
- Artificial Intelligence
- Machine-Learning
- Financial Data
- Speech-to-Text
- Transcription
- Document Extraction
- Named Entity Recognition
- Natural Language Processing
- LLM
- MCP
- Retrieval
- S&P Global
tags_raw:
- Company
- Artificial Intelligence
- Machine Learning
- Financial Data
- Speech to Text
- Transcription
- Document Extraction
- Named Entity Recognition
- Natural Language Processing
- LLM
- Model Context Protocol
- Retrieval
- S&P Global
apis:
- name: Kensho Scribe
  description: Asynchronous speech-to-text transcription API that turns audio and video into text with high accuracy. Supports
    batch, real-time, and human-in-the-loop transcription, multipart and remote-URL submission, HEAD polling for completion,
    and webhook callbacks.
  humanURL: https://docs.kensho.com/scribe/v2/developer-guide
  baseURL: https://scribe.kensho.com
  tags:
  - Speech-to-Text
  - Transcription
  - Audio
  tags_raw:
  - Speech to Text
  - Transcription
  - Audio
  properties:
  - type: Documentation
    url: https://docs.kensho.com/scribe/v2/developer-guide
  - type: APIReference
    url: https://docs.kensho.com/scribe/v2/batch-api-specification
- name: Kensho Extract
  description: Document intelligence API that transforms PDF documents into structured JSON, with hierarchical extraction,
    optical character recognition (OCR), enhanced table extraction, and bounding-box locations. Supports both direct upload
    and a presigned upload/download URL flow for large documents.
  humanURL: https://docs.kensho.com/extract/home
  baseURL: https://extract.kensho.com
  tags:
  - Document Extraction
  - PDF
  - OCR
  properties:
  - type: Documentation
    url: https://docs.kensho.com/extract/home
  - type: APIReference
    url: https://docs.kensho.com/extract/api
- name: Kensho NERD
  description: Named Entity Recognition and Disambiguation API that identifies and links concepts in text to knowledge bases
    (Wikimedia for general entities, S&P Capital IQ for financial organizations and people), returning entity positions, IDs,
    types, and confidence scores (ner_score and ned_score).
  humanURL: https://docs.kensho.com/nerd/overview
  baseURL: https://nerd.kensho.com
  tags:
  - Named Entity Recognition
  - Entity Linking
  - NLP
  properties:
  - type: Documentation
    url: https://docs.kensho.com/nerd/overview
  - type: APIReference
    url: https://docs.kensho.com/nerd/api
- name: Kensho LLM-ready API (kfinance)
  description: LLM-ready API that connects LLMs, agents, and AI applications to S&P Global's trusted data through flexible
    retrieval, Adaptive Retrieval data agents, a Python library (kensho-kfinance), and a hosted, OAuth-secured Model Context
    Protocol (MCP) server.
  humanURL: https://docs.kensho.com/llmreadyapi/overview
  baseURL: https://kfinance.kensho.com
  tags:
  - LLM
  - Retrieval
  - MCP
  - Financial Data
  tags_raw:
  - LLM
  - Retrieval
  - Model Context Protocol
  - Financial Data
  properties:
  - type: Documentation
    url: https://docs.kensho.com/llmreadyapi/overview
  - type: APIReference
    url: https://docs.kensho.com/llmreadyapi/api
  - type: MCPServer
    url: https://kfinance.kensho.com/integrations/mcp
common:
- type: Website
  url: https://kensho.com/
- type: DeveloperPortal
  url: https://docs.kensho.com/
- type: Documentation
  url: https://docs.kensho.com/
- type: APIReference
  url: https://docs.kensho.com/llmreadyapi/api
- type: GettingStarted
  url: https://docs.kensho.com/authentication/personal-token
- type: Authentication
  url: authentication/kensho-authentication.yml
- type: OAuthScopes
  url: scopes/kensho-scopes.yml
- type: SignUp
  url: https://services.kensho.com/free-trial
- type: Support
  url: https://docs.kensho.com/llmreadyapi/support
- type: ChangeLog
  url: https://docs.kensho.com/llmreadyapi/release-notes
- type: GitHubOrganization
  url: https://github.com/kensho-technologies
- type: StatusPage
  url: https://status.kensho.com/
- type: TrustCenter
  url: https://trust.kensho.com/
- type: Compliance
  url: https://trust.kensho.com/
- type: MCPServer
  url: mcp/kensho-mcp.yml
- type: WellKnown
  url: well-known/kensho-well-known.yml
- type: SecurityTxt
  url: well-known/kensho-well-known.yml
- type: Packages
  url: packages/kensho-packages.yml
- type: SDKs
  url: packages/kensho-packages.yml
- type: Conventions
  url: conventions/kensho-conventions.yml
- type: Conformance
  url: conformance/kensho-conformance.yml
- type: Lifecycle
  url: lifecycle/kensho-lifecycle.yml
- type: ChangeLog
  url: changelog/kensho-changelog.yml
- type: Webhooks
  url: asyncapi/kensho-scribe-webhooks.yml
- type: AgentSkill
  url: skills/_index.yml
- type: ErrorCatalog
  url: errors/kensho-problem-types.yml
- type: LLMsTxt
  url: llms/kensho-llms.txt
- type: DomainSecurity
  url: security/kensho-domain-security.yml
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com
- FN: APIs.json
  email: info@apis.io
x-enrichment:
  date: '2026-07-19'
  status: backfilled
  pass: local-v1
  note: backfilled from .gitignore signal + verified work evidence

Work with this as data

Every provider here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for providers

9 MCP tools reach this
  • find_providersBrowse and filter every provider in the catalog.
  • get_provider_artifactsEvery artifact this provider publishes, grouped by type.
  • get_provider_operationsEvery operation across all of their OpenAPIs — one call instead of parsing every spec.
  • get_provider_toolsEvery MCP tool they ship, with the operation each wraps.
  • get_provider_evidenceHow each part of their score was established. Free — the basis for a claim should not sit behind it.
  • get_provider_ratingPRO — composite, band, trend and facet scores.
  • apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
  • resolveTurn a domain, URL or GitHub org into the provider it belongs to.
  • find_cohortsEvery scored population of providers in the catalog.
All 92 tools →

Call it yourself

curl for this page
This provider
curl "https://apis.io/api/v1/providers/kensho"
All providers
curl "https://apis.io/api/v1/providers?limit=25"
Every operation they expose
curl "https://apis.io/api/v1/providers/kensho/operations?limit=25"
How their score was established
curl "https://apis.io/api/v1/providers/kensho/evidence"

Discovery needs no key. Ratings and market analysis are Pro.

Get an API key

Free tier, no email required.

A second provider on the same verified email joins the account you already have.