Laurence

Laurence is a New York City based Y Combinator (Winter 2026) company that automates Amazon advertising and marketplace management for brands. The platform applies quantitative-trading methodology — hierarchical Bayesian bid optimization over Amazon Marketing Stream data landed in ClickHouse — to maximize contribution margin after margin and ad spend rather than optimizing to rules-of-thumb ACOS targets. Laurence ingests Amazon Advertising and Seller Central data, prices every keyword auction, and exposes the resulting data to customers through Ask Laurence and a hosted, OAuth-protected Model Context Protocol server that brings Amazon Ads data into Claude Code, Cursor, and Codex. The company raised a $5.8M seed round led by Susa Ventures and Box Group with participation from Y Combinator.

Laurence publishes 1 API on the APIs.io network. Tagged areas include Company, Advertising, Amazon, E-Commerce, and Marketing.

Laurence’s developer surface includes authentication, documentation, engineering blog, signup flow, support, and 14 more developer resources.

🌐 Visit website 📡 Source on GitHub

23.1/100 emerging ▬ flat Agent 25/100 agent aware Full breakdown ↓
scored 2026-07-27 · rubric v0.5

AccessSelf serve

1 APIs 1 MCP Servers

CompanyAdvertisingAmazonE-CommerceMarketingMachine LearningRetail MediaMCP

Kin Score

Kin Score How this is scored →
scored 2026-07-27 · rubric v0.5

Composite quality — 23.1/100 · emerging

Contract Quality 0.0 / 25

Developer Ergonomics 7.0 / 20

Commercial Clarity 6.8 / 20

Operational Transparency 0.0 / 13

Governance 0.0 / 12

Discoverability 9.3 / 10

Agent readiness — 25/100 · agent aware

Machine-Readable Contract 0 / 18

Agentic Access Contract 0 / 15

MCP Server 12 / 12

Machine-Readable Auth 10 / 10

Idempotency 0 / 9

Stable Error Semantics 0 / 8

Request/Response Examples 0 / 7

Rate-Limit Signaling 0 / 7

Typed Event Surface 0 / 6

Agent Skills 0 / 5

Well-Known Catalog 4 / 4

Consent & Bot Identity 0 / 3

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/laurence: 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 1

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

Laurence MCP

Laurence MCP is a hosted, remote Model Context Protocol server that exposes a read-only set of nine tools over a customer's Amazon Advertising and Amazon Marketing Stream data —...

MCP Servers 1

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

Scopes 1

OAuth scopes governing access to this provider's APIs.

Laurence Scopes

OAuth 2.0 · no documented scopes

0 scopes

SCOPES

Resources

Get Started 1

Portal, sign-up, and the first successful call

SignUp

SignUp

Documentation 1

Reference material describing how the API behaves

Documentation

Documentation

Agent Surfaces 3

MCP servers, agent skills, and machine-readable catalogs

WellKnown

WellKnown

LLMsTxt

LLMsTxt

MCPServer

MCPServer

Design & Contract 2

Pagination, idempotency, versioning, errors, and events

Conformance

Conformance

Conventions

Conventions

Access & Security 3

Authentication, authorization, and security posture

Authentication

Authentication

OAuthScopes

OAuthScopes

DomainSecurity

DomainSecurity

Operate 1

Status, limits, changes, and where to get help

Support

Support

Commercial 2

Pricing, plans, and the legal terms of use

TermsOfService

TermsOfService

PrivacyPolicy

PrivacyPolicy

Company 5

The organization behind the API

Website

Website

Blog

Blog

BlogRSS

BlogRSS

LinkedIn

Twitter

Twitter

Other 1

Properties that don't map to a standard resource type

Sitemap

Sitemap

Source (apis.yml)

aid: laurence
name: Laurence
description: Laurence is a New York City based Y Combinator (Winter 2026) company that automates Amazon advertising and marketplace
  management for brands. The platform applies quantitative-trading methodology — hierarchical Bayesian bid optimization over
  Amazon Marketing Stream data landed in ClickHouse — to maximize contribution margin after margin and ad spend rather than
  optimizing to rules-of-thumb ACOS targets. Laurence ingests Amazon Advertising and Seller Central data, prices every keyword
  auction, and exposes the resulting data to customers through Ask Laurence and a hosted, OAuth-protected Model Context Protocol
  server that brings Amazon Ads data into Claude Code, Cursor, and Codex. The company raised a $5.8M seed round led by Susa
  Ventures and Box Group with participation from Y Combinator.
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://www.laurence.com/icon.png
url: https://raw.githubusercontent.com/api-evangelist/laurence/refs/heads/main/apis.yml
x-type: company
x-source: vc-portfolio
x-backed-by:
- y-combinator
- susa-ventures
- box-group
x-tier: profiled
x-tier-reason: hosted-mcp-server
specificationVersion: '0.20'
created: '2026-07-17'
modified: '2026-07-19'
tags:
- Company
- Advertising
- Amazon
- E-Commerce
- Marketing
- Machine Learning
- Retail Media
- MCP
apis:
- aid: laurence:mcp
  name: Laurence MCP
  description: Laurence MCP is a hosted, remote Model Context Protocol server that exposes a read-only set of nine tools over
    a customer's Amazon Advertising and Amazon Marketing Stream data — allowed ads profiles, daily sales, campaigns, ad groups,
    keywords, negative keywords, bid observations, hourly and daily stream metrics, and search term reports. It is available
    to Laurence customers, is authenticated with OAuth 2.0 (RFC 9728 protected resource, PKCE S256, dynamic client registration),
    and every tool call is scoped to the Amazon Ads profiles the signed-in user belongs to.
  humanURL: https://www.laurence.com/blog/laurence-mcp-launch
  baseURL: https://laurence-ai-68564--ask-laurence-agent-mcp-server.modal.run/mcp
  tags:
  - MCP
  - Amazon Ads
  - Advertising
  - Reporting
  properties:
  - type: MCPServer
    url: mcp/laurence-mcp.yml
  - type: Authentication
    url: authentication/laurence-authentication.yml
  - type: OAuthScopes
    url: scopes/laurence-scopes.yml
  - type: Documentation
    url: https://www.laurence.com/blog/laurence-mcp-launch
common:
- type: WellKnown
  url: well-known/laurence-well-known.yml
- type: LLMsTxt
  url: llms/laurence-llms.txt
- type: MCPServer
  url: mcp/laurence-mcp.yml
- type: Authentication
  url: authentication/laurence-authentication.yml
- type: OAuthScopes
  url: scopes/laurence-scopes.yml
- type: Conformance
  url: conformance/laurence-conformance.yml
- type: Conventions
  url: conventions/laurence-conventions.yml
- type: DomainSecurity
  url: security/laurence-domain-security.yml
- type: Website
  url: https://www.laurence.com
- type: Documentation
  url: https://www.laurence.com/how-it-works
- type: Blog
  url: https://www.laurence.com/blog
- type: BlogRSS
  url: https://www.laurence.com/blog/feed.xml
- type: SignUp
  url: https://www.laurence.com/audit
- type: TermsOfService
  url: https://www.laurence.com/eula
- type: PrivacyPolicy
  url: https://www.laurence.com/privacy
- type: Support
  url: https://www.laurence.com/demo
- type: Sitemap
  url: https://www.laurence.com/sitemap.xml
- type: LinkedIn
  url: https://www.linkedin.com/company/laurence-ai
- type: Twitter
  url: https://x.com/trylaurence
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