Install Jentic One Beta

Connect the Noteboxd Public API to your agent

Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Noteboxd Public API, or any other public or private API you need. You set the rules, the agent never sees your credentials, and every call is logged.

Two steps, two machines. Install the instance in a safe environment, then register your agent from wherever it runs.

Step 1: Jentic One Host machine

# On the machine that will host your Jentic One instance:
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fnoteboxd.com%2Fnoteboxd" | sh

Step 2: Agent machine

# On the machine where your agent runs (keep this separate from the instance):
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fnoteboxd.com%2Fnoteboxd" | sh
jentic register       # connects your agent to your Jentic One instance

Jentic One is in public beta. The setup above keeps your agent separate from the instance, which is what you want before using real credentials: an agent running as the same OS user as Jentic One can read its stored keys directly. Just evaluating? A single local install is fine to start. See the secure deployment guide for the tiers.

Capabilities

What an agent can do with Noteboxd Public API.

Search across fragrances, notes, brands, perfumers, and collections with one query on GET /v1/search

Filter fragrances by brand, note, family, and a priceRange of BUDGET, MIDRANGE, or PREMIUM

Read a fragrance's full profile with notes, accords, score, and perfumer

Find similar fragrances by accord profile and read aggregate wearing data by season and mood

GET STARTED

Start building with Noteboxd Public API

Explore with Jentic One

View OpenAPI Document

Use Cases

Patterns agents use Noteboxd Public API for, with concrete tasks.

★ AI fragrance recommendation assistant

An AI shopping assistant helps a user find a new scent based on one they already own. Through Jentic the agent searches for 'find fragrances similar to one I like', gets the Noteboxd similar-fragrances operation with its input schema, and calls it for the user's fragrance id. It then reads each candidate's profile and wearing stats so its suggestions rest on real notes, accords, and seasons rather than guesses.

Call GET /v1/search with q=Baccarat Rouge 540 and type=fragrance to get its id, call GET /v1/fragrances/{id}/similar with limit=5, then call GET /v1/fragrances/{id}/wearing-stats for each result and recommend the ones worn in winter

Fragrance filtering by note and budget

A retail or content site wants listings of fragrances that match a note, family, or budget. GET /v1/fragrances filters by brand, note, family, and priceRange with cursor pagination, and POST /v1/fragrances/batch returns up to 50 fragrance profiles in a single call once the ids are known. The full profile carries notes, accords, score, and perfumer for each item.

Call GET /v1/fragrances with note=vanilla, family=amber, and priceRange=MIDRANGE, collect the ids, then call POST /v1/fragrances/batch with those ids to load the full profiles

Review summaries and head-to-head comparisons

A buyer choosing between two scents wants the trade-offs in plain language. GET /v1/fragrances/compare takes two fragrance ids, a and b, and returns shared and distinct notes, scores, and a grounded synthesis, while GET /v1/fragrances/{id}/review-digest summarises a fragrance's community reviews. These are the higher-priced endpoints, so an agent calls them only once it has narrowed the choice.

Call GET /v1/fragrances/compare with a and b set to two fragrance ids, then call GET /v1/fragrances/{id}/review-digest for the higher-scoring one and report the shared notes and the review summary

Brand, perfumer, and note research

A writer or analyst researching a house or a perfumer needs their full range in one place. GET /v1/brands/{slug} returns a brand profile with top fragrances and GET /v1/brands/{slug}/fragrances pages through every fragrance from the brand, GET /v1/perfumers/{slug} lists a perfumer's top creations, and GET /v1/notes/{slug} shows the fragrances that feature a note most.

Call GET /v1/perfumers/{slug} for a perfumer, then call GET /v1/notes/{slug} for the most frequent note in their top creations and list the other fragrances that feature it

Key Endpoints

19 endpoints — the noteboxd public api returns fragrance, brand, note, perfumer, and chart data from the noteboxd fragrance community.

METHOD

PATH

DESCRIPTION

GET

/v1/search

Universal cross-entity search

GET

/v1/fragrances

Search and filter fragrances

GET

/v1/fragrances/{id}

Get a full fragrance profile

GET

/v1/fragrances/{id}/similar

Find similar fragrances

GET

/v1/fragrances/compare

Compare two fragrances

GET

/v1/fragrances/{id}/review-digest

Digest of community reviews

POST

/v1/fragrances/batch

Get up to 50 fragrances

GET

/v1/charts/{slug}

Get a chart leaderboard

GET

/v1/search

Universal cross-entity search

GET

/v1/fragrances

Search and filter fragrances

GET

/v1/fragrances/{id}

Get a full fragrance profile

GET

/v1/fragrances/{id}/similar

Find similar fragrances

GET

/v1/fragrances/compare

Compare two fragrances

GET

/v1/fragrances/{id}/review-digest

Digest of community reviews

POST

/v1/fragrances/batch

Get up to 50 fragrances

GET

/v1/charts/{slug}

Get a chart leaderboard

Why Jentic?

What agents get from Jentic-routed access to this vendor.

Setup

Wiring Noteboxd by hand means sending a bearer project key, tracking per-endpoint pricing against a prepaid balance, and paging fragrance lists by cursor. Through Jentic you install once, import Noteboxd from the API Directory, store the key once, and your agent calls it.

Permission scoping

Each Noteboxd operation has its own URL path, such as /v1/fragrances/{id}/similar or /v1/fragrances/compare, so a rule can bound your agent to the operations its task needs. You choose which ones it may call, so the higher-priced batch and enrich POSTs are not included unless you add them.

Credential isolation

Your Noteboxd API key is stored once, encrypted, by your own Jentic One instance and injected at execution time. It never enters the agent's prompt, logs, or context.

Intent-based discovery

Agents search Jentic by intent such as 'find fragrances similar to one I like' or 'compare two fragrances', and Jentic returns the matching Noteboxd operation with its input schema, including parameters like note, family, and priceRange, so the agent calls the right endpoint directly.

FAQs

Specific to using Noteboxd Public API through Jentic.

What authentication does the Noteboxd Public API use?

Per its OpenAPI spec, the Noteboxd Public API uses HTTP bearer authentication with a project API key in the nb_live_ format, issued from the Noteboxd developer portal and sent as Authorization: Bearer. Through Jentic the key is held by your own instance and injected at call time, so the agent never sees it.

How is the Noteboxd Public API priced?

Calls are billed per endpoint against a prepaid balance. The spec lists most lookups at 1 cent per call, similar fragrances and wearing stats at 2 cents, compare at 3 cents, review digests at 5 cents, enrich at 10 cents, and the batch endpoint at 25 cents per call.

What are the rate limits for the Noteboxd Public API?

The spec says calls share a per-account daily rate-limit pool and responses carry X-RateLimit-Limit headers, but it does not state a fixed number. Check the Noteboxd developer documentation at https://www.noteboxd.com/developers for your account's current limit.

Can I get everything about a fragrance in one call with the Noteboxd Public API?

Yes. POST /v1/fragrances/enrich takes a required id and returns notes, accords, reviews, and similar fragrances together, with optional similarLimit and reviewLimit fields. For several fragrances at once, POST /v1/fragrances/batch accepts up to 50 ids.

How do I find similar fragrances through Jentic?

Search Jentic for 'find fragrances similar to one I like', load the Noteboxd similar-fragrances operation, and call GET /v1/fragrances/{id}/similar with the fragrance id and a limit. Use GET /v1/search first if you only have the name. To run it on your own infrastructure, install Jentic One from its GitHub repo.

Is there a Noteboxd MCP server?

You do not need an MCP server to give your agent Noteboxd. Jentic connects it directly from the API Directory: import it, store your API key once, and your agent calls the search, profile, and review operations it needs on demand.

Can I limit what my agent is allowed to do with the Noteboxd Public API?

Yes. Because every call draws on your prepaid balance, write a rule that allows the 1-cent lookups such as GET /v1/search and GET /v1/fragrances/{id} and leaves out POST /v1/fragrances/batch and POST /v1/fragrances/enrich. The agent can still search and read profiles, and the calls it makes are logged for review.

Noteboxd Public API

AI ReadinessAI-Ready (A)88/100

See full scorecard

Official vendor OpenAPI document · agent-readyData EnrichmentData Transformationbearer19 EndpointsREST

For Agents

Search fragrances, notes, brands, and perfumers, read full scent profiles and community reviews, find similar fragrances, and compare two fragrances from Noteboxd data.

Use for: Find fragrances with vanilla and oud notes, Get the full note pyramid and accords for a fragrance, Recommend fragrances similar to one I already like, Compare two fragrances and explain how they differ

Not supported: Does not sell fragrances, process orders, or post reviews. Use for reading Noteboxd fragrance, brand, note, perfumer, review, and chart data only.

The Noteboxd Public API returns fragrance, brand, note, perfumer, and chart data from the Noteboxd fragrance community. A client can search across fragrances, notes, brands, perfumers, and collections, filter fragrances by brand, note, family, or price range, and open a full profile with its notes, accords, score, and perfumer. It also serves community reviews, aggregate wearing data by season and mood, similar fragrances by accord profile, and chart leaderboards. AI-generated comparisons of two fragrances and digests of a fragrance's reviews are available, and each call is billed per endpoint against a prepaid balance.

Jentic One on Github View OpenAPI Document

Show dimension breakdown

Foundational Compliance

Base layer of spec validity and structural soundness.

Grade: A-Signals: 4

94%

Lint Results

Aggregated quality score from linter diagnostics, weighted by severity.

100%

Resolution Completeness

Percentage of `$ref` references that resolve successfully.

Specification Validity

Checks whether the API description parses successfully and conforms to its declared specification (e.g., OpenAPI).

100%

Structural Integrity

Structural correctness score based on schema issues using logarithmic dampening.

100

Developer Experience & Jentic Compatibility

Clarity, completeness, and ingestion readiness for developers and tooling.

Grade: A+Signals: 4

100%

Example Density

How richly the API is illustrated with examples.

100%

Example Validity

Percentage of examples that conform to their schemas.

100%

Response Coverage

Percentage of operations with complete response definitions (success, client error, server error).

100%

Tooling Readiness

Health of API ingestion, bundling, and resolution within Jentic pipelines.

100

AI-Readiness & Agent Experience

Semantic breadth, depth, and agent comprehension for AI systems.

Grade: A+Signals: 4

100%

Description Coverage

Coverage of descriptions across API elements.

100%

Error Standardization

Coverage of RFC 9457 Problem Details for error responses.

100%

OperationId Quality

Coverage, uniqueness, and casing consistency of operationIds for AI inference.

100%

Summary Coverage

Coverage of summaries across operations/tags/info.

Agent Usability

Functional utility, complexity comfort, and AI orchestration readiness.

Grade: A+Signals: 1

94%

Complexity Comfort

Agent comfort level based on API operational and structural complexity.

100

Security

Trust, risk posture, and security compliance.

Grade: A+Signals: 1

100%

Authentication Strength

Average quality of security schemes based on authentication method strength (weakest link for OAuth2).

AI Discoverability

Findability, semantic richness, and reasoning readiness.

Grade: C+Signals: 1

60%

Descriptive Richness

Clarity and depth of descriptions across API elements.

Connect the Noteboxd Public API to your agent

Capabilities

Start building with Noteboxd Public API

Use Cases

Key Endpoints

Why Jentic?

Related APIs

FAQs

Noteboxd Public API

Jentic AI Readiness Score

Noteboxd Public API

Foundational Compliance

Lint Results

Resolution Completeness

Specification Validity

Structural Integrity

Developer Experience & Jentic Compatibility

Example Density

Example Validity

Response Coverage

Tooling Readiness

AI-Readiness & Agent Experience

Description Coverage

Error Standardization

OperationId Quality

Summary Coverage

Agent Usability

Complexity Comfort

Security

Authentication Strength

AI Discoverability

Descriptive Richness