Fermat website screenshot

Fermat

FERMÀT is an AI-native commerce platform that consolidates the shopper analytics, personalization, and experimentation stack into a single agentic system for direct-to-consumer and enterprise brands. It runs a closed loop — detect shopper behavior, recommend revenue-optimizing actions, generate adaptive storefront experiences and product pages, then feed performance signals back into detection — replacing tools like FullStory, Amplitude, Algolia, and Optimizely. FERMÀT integrates with ecommerce platforms including Shopify Plus, Salesforce Commerce Cloud, Adobe Commerce, and Oracle ATG via batch and streaming data syncs, and serves brands such as Glossier, GNC, Backcountry, AWAY, Travelpro, and TONAL. Surfaced as a portfolio company of Bain Capital Ventures, Greylock, and QED Investors.

Fermat publishes 1 API on the APIs.io network: Pixel v2. Tagged areas include Company, Commerce, E-Commerce, Personalization, and Analytics.

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

Fermat’s developer surface includes engineering blog, support, changelog, documentation, API reference, getting-started guide, authentication, and 25 more developer resources.

40.7/100 developing ▬ flat Agent 26/100 agent aware saas Full breakdown ↓
scored 2026-09-08 · rubric v0.20.0
2 APIs 1 MCP Servers
CompanyCommerceE-CommercePersonalizationAnalyticsConversion Rate OptimizationArtificial IntelligenceMerchandisingMCPAgentic CommerceSession ReplayExperimentationAttribution

Kin Score

Kin Score Kin Score How this is scored →
scored 2026-09-08 · rubric v0.20.0
Create-or-Update Ergonomics could not be measured. We hold no machine-readable contract for this provider to read, so there is nothing to measure a write surface against. Excluded rather than scored zero: never-measured and measured-empty are different facts. Publishing an OpenAPI is what makes this facet — and several others — scorable at all.
Improve this rating by publishing the missing artifacts — every area above can be raised, and the full rubric is at apis.io/rating/. Every facet and dimension name above is a link: it opens that measurement's own page — what it means, the exact checks that feed it, how the whole catalog distributes on it, and the providers at the top of it. This rating is computed from github.com/api-evangelist/fermat: open an issue to ask a question, or submit a pull request to add artifacts. Submit an artifact on GitHub — free → Manage your own listing — the Influence plan, $499/mo →

APIs 2

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

FERMAT Platform MCP Server

Remote Model Context Protocol server exposing 64 read-only tools over FERMAT commerce data — product catalog, funnel analytics, ad performance, destination insights, experiments...

FERMAT Pixel v2

First-party browser ES module (claire.mjs) a brand embeds to emit commerce telemetry to FERMAT. Exposes a window.fermat command queue with init, track and status methods, and si...

MCP Servers 1

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

Pricing Plans 1

Published pricing tiers and plan structures.

Fermat Plans Pricing

0 plans

PLANS

Rate Limits 1

Documented rate limits and quota policies.

Fermat Rate Limits

0 limits

RATE LIMITS

Event Specifications 1

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

FERMAT Pixel v2 Event Ingest

Browser-to-FERMAT commerce telemetry. A brand installs the FERMAT Pixel v2 and calls window.fermat({ method: "track", eventName, properties }) for each of the six documented com...

ASYNCAPI

Security Posture 2

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

Fermat Authentication

3 schemes

SECURITY

Fermat Domain Security

TLSv1.3 · HSTS · DNSSEC · DMARC

SECURITY

Resources

Get Started 2

Portal, sign-up, and the first successful call

Documentation 3

Reference material describing how the API behaves

Agent Surfaces 4

MCP servers, agent skills, and machine-readable catalogs

Design & Contract 6

Pagination, idempotency, versioning, errors, and events

Build 2

SDKs, sample code, and the tooling you integrate with

Access & Security 3

Authentication, authorization, and security posture

Operate 5

Status, limits, changes, and where to get help

Commercial 3

Pricing, plans, and the legal terms of use

Company 4

The organization behind the API

Source (apis.yml)

apis.yml Raw ↑
aid: fermat
name: Fermat
description: FERMÀT is an AI-native commerce platform that consolidates the shopper analytics, personalization, and experimentation
  stack into a single agentic system for direct-to-consumer and enterprise brands. It runs a closed loop — detect shopper
  behavior, recommend revenue-optimizing actions, generate adaptive storefront experiences and product pages, then feed performance
  signals back into detection — replacing tools like FullStory, Amplitude, Algolia, and Optimizely. FERMÀT integrates with
  ecommerce platforms including Shopify Plus, Salesforce Commerce Cloud, Adobe Commerce, and Oracle ATG via batch and streaming
  data syncs, and serves brands such as Glossier, GNC, Backcountry, AWAY, Travelpro, and TONAL. Surfaced as a portfolio company
  of Bain Capital Ventures, Greylock, and QED Investors.
url: https://raw.githubusercontent.com/api-evangelist/fermat/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: contact-sales
  onboarding: sales-gated
  trial: false
  try_now: false
  public: false
  label: Customer only
  confidence: high
  source:
  - https://www.fermatcommerce.com/pricing (301 to root)
  - https://help.fermatcommerce.com/en/articles/14431099-fermat-mcp-connect-your-commerce-data-to-ai-tools
  - https://help.fermatcommerce.com/en/articles/14280269-fermat-pixel-v2-installation-guide-direct-script-google-tag-manager
  generated: '2026-08-13'
  method: searched
  note: No public pricing and no self-serve sign-up. MCP access requires an existing FERMAT platform account; Pixel IDs are
    issued by a FERMAT representative.
image: https://www.fermatcommerce.com/assets/marketing/brand/open-graph.png
x-type: company
x-source: vc-portfolio
x-backed-by:
- bain-capital-ventures
- greylock
- qed-investors
x-tier: enriched
x-tier-reason: live remote MCP server (64 published tools) + first-party browser pixel with a documented event schema
specificationVersion: '0.23'
created: '2026-07-17'
modified: '2026-08-13'
tags:
- Company
- Commerce
- E-Commerce
- Personalization
- Analytics
- Conversion Rate Optimization
- Artificial Intelligence
- Merchandising
- MCP
- Agentic Commerce
- Session Replay
- Experimentation
- Attribution
tags_raw:
- Company
- Commerce
- Ecommerce
- Personalization
- Analytics
- Conversion Rate Optimization
- AI
- Merchandising
- MCP
- Agentic Commerce
- Session Replay
- Experimentation
- Attribution
apis:
- name: FERMAT Platform MCP Server
  description: 'Remote Model Context Protocol server exposing 64 read-only tools over FERMAT commerce data — product catalog,
    funnel analytics, ad performance, destination insights, experiments, session and behavioral data, anomaly and friction
    detection, branding, offers, bundles, product pages, and Pierre, FERMAT''s natural-language BI agent. Streamable HTTP
    (POST only), protected by OAuth 2.1 authorization-code + PKCE with dynamic client registration. Customer-only: an anonymous
    tools/list returns JSON-RPC -32001. External access is read-only; the provider states write capability is coming.'
  humanURL: https://help.fermatcommerce.com/en/articles/14431099-fermat-mcp-connect-your-commerce-data-to-ai-tools
  baseURL: https://mcp.fermatcommerce.com/mcp/fermat-mcp
  tags:
  - MCP
  - Commerce
  - Analytics
  - Artificial Intelligence
  - Agentic Commerce
  tags_raw:
  - MCP
  - Commerce
  - Analytics
  - AI
  - Agentic Commerce
  properties:
  - type: MCPServer
    url: mcp/fermat-mcp.yml
  - type: Documentation
    url: https://help.fermatcommerce.com/en/articles/14431099-fermat-mcp-connect-your-commerce-data-to-ai-tools
  - type: APIReference
    url: https://mcp.fermatcommerce.com/mcp/fermat-mcp
  - type: Authentication
    url: authentication/fermat-authentication.yml
  - type: ErrorCatalog
    url: errors/fermat-problem-types.yml
  - type: AgentSkill
    url: skills/_index.yml
- name: FERMAT Pixel v2
  description: First-party browser ES module (claire.mjs) a brand embeds to emit commerce telemetry to FERMAT. Exposes a window.fermat
    command queue with init, track and status methods, and six documented events — page_view, view_product, add_to_cart, remove_from_cart,
    begin_checkout and purchase — each with a published field schema. Lazily loads a session recorder for replay, heatmaps
    and scroll-depth analysis when recording is enabled in the pixel config. Installed via a direct script tag or Google Tag
    Manager; Shopify stores use a separate native path.
  humanURL: https://help.fermatcommerce.com/en/articles/14280269-fermat-pixel-v2-installation-guide-direct-script-google-tag-manager
  baseURL: https://e.clairedefermat.com
  tags:
  - E-Commerce
  - Analytics
  - Session Replay
  - Attribution
  - Personalization
  tags_raw:
  - Ecommerce
  - Analytics
  - Session Replay
  - Attribution
  - Personalization
  properties:
  - type: AsyncAPI
    url: asyncapi/fermat-pixel-asyncapi.yml
  - type: Documentation
    url: https://help.fermatcommerce.com/en/articles/14280269-fermat-pixel-v2-installation-guide-direct-script-google-tag-manager
  - type: GettingStarted
    url: https://help.fermatcommerce.com/en/articles/14280269-fermat-pixel-v2-installation-guide-direct-script-google-tag-manager
  - type: Components
    url: components/fermat-components.yml
  - type: SDKs
    url: packages/fermat-packages.yml
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com
- FN: APIs.json
  email: info@apis.io
common:
- type: Website
  url: https://www.fermatcommerce.com/
- type: About
  url: https://www.fermatcommerce.com/about
- type: Blog
  url: https://www.fermatcommerce.com/resources
- type: Newsroom
  url: https://www.fermatcommerce.com/newsroom
- type: Support
  url: https://help.fermatcommerce.com/en/
- type: HelpCenter
  url: https://help.fermatcommerce.com/en/
- type: Login
  url: https://app.fermatcommerce.com
- type: TermsOfService
  url: https://www.fermatcommerce.com/terms
- type: PrivacyPolicy
  url: https://www.fermatcommerce.com/privacy
- type: ChangeLog
  url: https://help.fermatcommerce.com/en/articles/11588666-what-s-new-at-fermat-product-features-and-updates
- type: ChangeLog
  name: Fermat changelog (structured)
  url: changelog/fermat-changelog.yml
- type: Compliance
  url: https://www.fermatcommerce.com/subprocessor-list
- type: Conformance
  url: conformance/fermat-conformance.yml
- type: DomainSecurity
  url: security/fermat-domain-security.yml
- type: Documentation
  url: https://help.fermatcommerce.com/en/
- type: APIReference
  name: FERMAT Platform MCP server — published 64-tool reference
  url: https://mcp.fermatcommerce.com/mcp/fermat-mcp
- type: GettingStarted
  url: https://help.fermatcommerce.com/en/articles/14431099-fermat-mcp-connect-your-commerce-data-to-ai-tools
- type: MCPServer
  url: mcp/fermat-mcp.yml
- type: AgentSkill
  url: skills/_index.yml
- type: WellKnown
  url: well-known/fermat-well-known.yml
- type: Authentication
  url: authentication/fermat-authentication.yml
- type: ErrorCatalog
  url: errors/fermat-problem-types.yml
- type: Conventions
  url: conventions/fermat-conventions.yml
- type: Lifecycle
  url: lifecycle/fermat-lifecycle.yml
- type: Plans
  url: plans/fermat-plans-pricing.yml
- type: RateLimits
  url: rate-limits/fermat-rate-limits.yml
- type: Packages
  url: packages/fermat-packages.yml
- type: SDKs
  url: packages/fermat-packages.yml
- type: Components
  url: components/fermat-components.yml
- type: DataModel
  url: data-model/fermat-data-model.yml
- type: AsyncAPI
  url: asyncapi/fermat-pixel-asyncapi.yml
- type: LLMsTxt
  url: llms/fermat-llms.txt
x-enrichment:
  date: '2026-08-13'
  status: enriched
  artifacts_added: 20
  pass: local-v1

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/fermat"
All providers
curl "https://apis.io/api/v1/providers?limit=25"
Every operation they expose
curl "https://apis.io/api/v1/providers/fermat/operations?limit=25"
How their score was established
curl "https://apis.io/api/v1/providers/fermat/evidence"

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

Get an API key

Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.

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