Install Jentic One Beta

Connect the Open Food Facts API (public) to your agent

Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Open Food Facts API (public), 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%2Fopenfoodfacts.org%2Fopenfoodfacts" | 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%2Fopenfoodfacts.org%2Fopenfoodfacts" | 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 Open Food Facts API (public) API.

Look up a food product by barcode and read its attributes

Search products by name, brand, category, and other criteria

Read nutrition facts, ingredients, and labels returned for a product

Choose the version 2 or version 3 product and search endpoints

Use Cases

Patterns agents use Open Food Facts API (public) API for, with concrete tasks.

GET STARTED

Start building with Open Food Facts API (public) API

Explore with Jentic One

View OpenAPI Document

Nutrition and Ingredient Data

Pull nutrition and ingredient details for packaged foods. A barcode lookup returns the product's nutrition facts, ingredient list, and labels, so a diet or health app can present accurate information for a scanned item.

Retrieve a product by barcode and extract its nutrition facts and ingredient list

Product Search and Discovery

Find products without a barcode in hand. The search endpoints match products by name, brand, and category, so an app can surface options and let a user pick the right item before reading its details.

Search for products by brand and category and return the matching items with their barcodes

Label and Diet Filtering

Screen products against dietary needs. Product records carry labels and category data, so a workflow can look up a barcode and check whether an item fits a vegan, gluten-free, or allergen-aware requirement.

Look up a product by barcode and report which dietary labels it carries

Key Endpoints

4 endpoints — the open food facts api is the public interface to open food facts, a collaborative database of food products from around the world.

METHOD

PATH

DESCRIPTION

GET

/api/v2/product/{barcode}

Look up a product by barcode (v2)

GET

/api/v2/search

Search products (v2)

GET

/api/v3/product/{barcode}

Look up a product by barcode (v3)

GET

/api/v3/search

Search products (v3)

GET

/api/v2/product/{barcode}

Look up a product by barcode (v2)

GET

/api/v2/search

Search products (v2)

GET

/api/v3/product/{barcode}

Look up a product by barcode (v3)

GET

/api/v3/search

Search products (v3)

Why Jentic?

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

Setup

Wiring Open Food Facts by hand still means reading its docs, choosing between the version 2 and version 3 endpoints, and paging search results yourself. Through Jentic you install once, import the API from the API Directory, and your agent calls the lookup or search operation it needs.

Permission scoping

You decide which Open Food Facts operations your agent may call. A rule can allow product lookups and searches, and because the API is read-only, the agent can only read public product data. A rule bounds which operations run, and every call is logged.

Credential isolation

Open Food Facts is a public API and needs no key, so there is nothing to store. Jentic still routes every call through your own Jentic One instance, keeping the request path under your control.

Intent-based discovery

Agents search Jentic by intent such as 'look up a product by barcode' or 'search products by brand', and Jentic returns the matching Open Food Facts operation with its input schema so the agent calls the right endpoint without reading the reference docs.

FAQs

Specific to using Open Food Facts API (public) API through Jentic.

What authentication does the Open Food Facts API use?

The public Open Food Facts API requires no authentication in its OpenAPI spec: the product and search endpoints are open. Because there is no key, there is nothing for Jentic to inject, and calls still route through your own Jentic One instance so the request path stays under your control.

Can I search Open Food Facts without a barcode?

Yes. The search endpoints match products by name, brand, category, and other criteria, so an agent can discover items and read their barcodes before pulling full product details.

What are the rate limits for the Open Food Facts API?

The OpenAPI spec does not publish specific rate limits. Check the Open Food Facts documentation for current guidance, and have your agent cache results and back off when it receives a throttling response.

How do I look up a product with the Open Food Facts API through Jentic?

Search Jentic for an intent like 'look up a product by barcode', and it returns the matching Open Food Facts operation with its input schema. Import the connector once and your agent reads product data without hand-written HTTP code. To run it on your own infrastructure, install Jentic One from its GitHub repo.

Is there an Open Food Facts MCP server?

You don't need an MCP server to give your agent Open Food Facts. Jentic connects it directly from the Jentic API Directory: import the API and your agent calls the product and search operations. Operations are discovered on demand, so no extra tool definitions are loaded into the agent's context.

Can I limit what my agent is allowed to do with the Open Food Facts API?

Yes. You choose the operations the agent may call, so a rule can allow product lookups and searches. Since the API is read-only and public, the agent can only read product data, and every call is logged.

Open Food Facts API (public)

AI ReadinessNon-Ready (F)38/100

See full scorecard

Community OpenAPI document · agent-readyData EnrichmentCompany Datanone4 EndpointsREST

Know of an official OpenAPI document? Contribute it →

For Agents

Look up food products by barcode and search the Open Food Facts database by name, brand, and category through its public API.

Use for: I want to look up a product by its barcode, Search for a food product by name, Find products from a specific brand, Read the nutrition facts for a product

Not supported: Does not sell products or track inventory. Use it to look up food products by barcode and search the Open Food Facts database only.

The Open Food Facts API is the public interface to Open Food Facts, a collaborative database of food products from around the world. Given a product barcode it returns the product's attributes, and its search endpoints find products by name, brand, category, and other criteria. Both a version 2 and a version 3 of the product and search endpoints are available.

Jentic One on Github View OpenAPI Document

Show dimension breakdown

100

Foundational Compliance

Base layer of spec validity and structural soundness.

Grade: A+Signals: 4

98%

Lint Results

Aggregated quality score from linter diagnostics, weighted by severity.

100%

Resolution Completeness

Percentage of `$ref` references that resolve successfully.

100%

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.

Developer Experience & Jentic Compatibility

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

Grade: CSignals: 4

Example Density

How richly the API is illustrated with examples.

100%

Example Validity

Percentage of examples that conform to their schemas.

25%

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.

AI-Readiness & Agent Experience

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

Grade: FSignals: 4

14%

Description Coverage

Coverage of descriptions across API elements.

Error Standardization

Coverage of RFC 9457 Problem Details for error responses.

OperationId Quality

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

44%

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

50%

Descriptive Richness

Clarity and depth of descriptions across API elements.

Connect the Open Food Facts API (public) to your agent

Capabilities

Use Cases

Start building with Open Food Facts API (public) API

Key Endpoints

Why Jentic?

Related APIs

FAQs

Open Food Facts API (public)

Jentic AI Readiness Score

Open Food Facts API (public)

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