Install Jentic One Beta

Connect the OpenShopGraph MCP Server to your agent

Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the OpenShopGraph MCP Server, 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%2Fopenshopgraph.com%2Fopenshopgraph" | 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%2Fopenshopgraph.com%2Fopenshopgraph" | 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 OpenShopGraph MCP Server API.

Identify an online shop from a name, domain, pasted URL, misspelling, or a question in English or German

Read a shop's stated return window in returns_days, free return label, tracking, payment methods, and buyer-protection seal, each with checked_at and source

Check a shop's stated shipping destinations, delivery time, and free-shipping threshold, with a ships_to verdict for a country

List currently usable discount codes for a shop with verification status and a count of codes withheld as expired or rejected

GET STARTED

Start building with OpenShopGraph MCP Server API

Explore with Jentic One

View OpenAPI Document

Use Cases

Patterns agents use OpenShopGraph MCP Server API for, with concrete tasks.

★ Shopping assistant answering policy questions

An AI shopping agent working through Jentic gets a question like 'can I return shoes at this shop', calls find_shop with the user's wording to identify the domain, then calls get_shop_policies for that shop_domain. Each policy fact comes back with collected, a value, checked_at, and a source of policy_page or llm_gap_resolution, so the agent can tell the user what the shop itself states and whether it was read from the shop or derived by a model.

Call POST /tool/find_shop with query 'rücksendung otto', then POST /tool/get_shop_policies with the returned shop_domain and report returns_days with its checked_at date and source

Shipping eligibility check before checkout

Before suggesting a shop, an agent checks whether it ships to the buyer. POST /tool/get_shipping_policy with a shop_domain and an ISO 3166-1 country returns the stated destinations, delivery time, free-shipping threshold, and a ships_to verdict, where unknown is a real answer meaning the shop's statement does not settle it. It carries no carrier or shipping price, because OpenShopGraph does not hold that data.

Call POST /tool/get_shipping_policy with shop_domain bergzeit.de and country AT, and return the ships_to verdict and stated delivery time

Verified discount codes

POST /tool/list_coupons returns discount codes that are currently usable, with verification status. Codes are withheld when expired, when a real checkout test proved they do not work, or when a display policy suppresses them, and the response reports total_count and how many were withheld so nothing is dropped silently.

Call POST /tool/list_coupons with shop_domain otto.de and limit 10, and return the usable codes with their verification status and the withheld count

Key Endpoints

12 endpoints — the openshopgraph api looks up online shops and returns what each shop states about its own returns, shipping, payment methods, and buyer protection, with every fact dated and attributed to where it was read.

METHOD

PATH

DESCRIPTION

POST

/tool/find_shop

Identify a shop from a name, URL, or question

POST

/tool/get_shop

Get a shop's public profile

POST

/tool/get_shop_policies

Read a shop's stated policies

POST

/tool/get_shipping_policy

Read a shop's stated shipping

POST

/tool/list_coupons

List usable discount codes

POST

/tool/list_categories

List category slugs with counts

GET

/suggest

Typeahead shop and category suggestions

POST

/tool/find_shop

Identify a shop from a name, URL, or question

POST

/tool/get_shop

Get a shop's public profile

POST

/tool/get_shop_policies

Read a shop's stated policies

POST

/tool/get_shipping_policy

Read a shop's stated shipping

POST

/tool/list_coupons

List usable discount codes

POST

/tool/list_categories

List category slugs with counts

GET

/suggest

Typeahead shop and category suggestions

Why Jentic?

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

Setup

Wiring OpenShopGraph by hand means mapping the request bodies of its tool endpoints, handling the optional x-api-token header, and interpreting collected:false gaps. Through Jentic you install once, import OpenShopGraph from the API Directory, add your token once if you have one, and your agent calls it.

Permission scoping

Rules bound OpenShopGraph by operation: the shop_domain travels in the request body, so a rule decides which tools your agent may call, not which shop it asks about. You choose the operations it may call, so resolve_checkout_url and the coupon tool are not included unless you add them.

Credential isolation

If you use an OpenShopGraph token, it 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 'check a shop's return policy' or 'find discount codes for a shop', and Jentic returns the matching OpenShopGraph operation with its input schema, including shop_domain and country, so the agent calls it directly.

FAQs

Specific to using OpenShopGraph MCP Server API through Jentic.

What authentication does the OpenShopGraph API use?

Per its OpenAPI spec, the tool endpoints accept an optional API key in the x-api-token header: each tool operation, such as POST /tool/find_shop, lists both no authentication and the token as valid, and read tools are keyless within fair use. GET /suggest, the health, readiness, and version probes, and the protocol endpoint need no key at all. If you have a token, Jentic stores it in your own instance and attaches it at call time.

Can the OpenShopGraph API tell me a shop's shipping price?

No. get_shipping_policy and get_shop_policies return what the shop states: destinations, delivery time, free-shipping threshold, return window, and payment methods. They carry no carrier and no shipping price, because OpenShopGraph does not hold that data. When nothing has been collected for a shop, the reply says so with collected set to false.

What are the rate limits for the OpenShopGraph API?

The OpenAPI spec does not state numeric limits; it says read tools are keyless within fair use. See https://openshopgraph.com/en/terms/ for the current terms.

Is there an OpenShopGraph MCP server?

Yes - OpenShopGraph serves the same tools over the MCP protocol at POST /mcp. You can also connect it directly through Jentic: your agent gets the full 12-endpoint REST surface without loading another server's tool definitions into its context, any token is injected at call time by your self-hosted instance, and your rules decide which operations the agent may call.

How do I look up a shop's return policy through Jentic?

Search Jentic for 'look up a shop's return policy', load POST /tool/find_shop to identify the shop from the user's wording, then POST /tool/get_shop_policies with the returned shop_domain. Read returns_days and its source from the response. To run it on your own infrastructure, install Jentic One from its GitHub repo.

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

Yes. For a policy assistant, write a rule that allows POST /tool/find_shop and POST /tool/get_shop_policies only, and the agent can identify shops and read their stated policies but cannot resolve checkout URLs or list coupons. Every call it makes is logged.

OpenShopGraph MCP Server

AI ReadinessFoundational (C)55/100

See full scorecard

Official vendor OpenAPI document · agent-readyData EnrichmentCompany DataapiKey12 EndpointsREST

For Agents

Identify online shops from a name, URL, or question, and read their stated return, shipping, payment, and buyer-protection policies plus verified discount codes, each fact dated and sourced.

Use for: Is zalando a legitimate shop?, How many days do I have to return something at otto.de?, Check whether bergzeit.de ships to Austria, Find all working discount codes for this shop

Not supported: Does not quote shipping prices, place orders, or compare product prices. Use for identifying online shops and reading their stated policies and discount codes only.

The OpenShopGraph API looks up online shops and returns what each shop states about its own returns, shipping, payment methods, and buyer protection, with every fact dated and attributed to where it was read. A search tool identifies a shop from a name, domain, pasted URL, misspelling, or a question such as 'does bergzeit ship to austria', in English or German, and the profile lookup returns its canonical domain, country, and categories. Policy lookups report fields such as returns_days and free-shipping thresholds, and a coupon tool lists currently usable discount codes with their verification status and an explicit count of what was withheld and why. Read tools are keyless within fair use, and the data is licensed CC-BY-4.0.

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: B-Signals: 4

Example Density

How richly the API is illustrated with examples.

100%

Example Validity

Percentage of examples that conform to their schemas.

42%

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

12%

Description Coverage

Coverage of descriptions across API elements.

Error Standardization

Coverage of RFC 9457 Problem Details for error responses.

67%

OperationId Quality

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

48%

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.

Security

Trust, risk posture, and security compliance.

Grade: C-Signals: 1

50%

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: B-Signals: 1

62%

Descriptive Richness

Clarity and depth of descriptions across API elements.

Connect the OpenShopGraph MCP Server to your agent

Capabilities

Start building with OpenShopGraph MCP Server API

Use Cases

Key Endpoints

Why Jentic?

Related APIs

FAQs

OpenShopGraph MCP Server

Jentic AI Readiness Score

OpenShopGraph MCP Server

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