Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Glade Amazon 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%2Fgladeapi.com%2Fgladeapi" | shStep 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%2Fgladeapi.com%2Fgladeapi" | sh
jentic register # connects your agent to your Jentic One instanceJentic 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.
What an agent can do with Glade Amazon API.
Look up full product details for an ASIN, including its variants and offers
Search the Amazon catalog and get autocomplete query suggestions
Pull a product's reviews and its current offers from listed sellers
Retrieve stock and sales estimates for a product
Browse the category taxonomy, best sellers, and current deals
GET STARTED
Convert between ASIN and GTIN and look up seller and author profiles
Patterns agents use Glade Amazon API for, with concrete tasks.
★ Agent-Driven Product Research
An AI agent gathers a full picture of an Amazon product before a human reads a line of it. It resolves the product by ASIN, pulls the variants and current offers, and reads the reviews so it can summarize sentiment and price spread. Jentic exposes each Glade operation with its input schema so the agent passes the ASIN and options correctly on the first call.
Resolve a product by ASIN, pull its variants and offers, and retrieve its reviews to summarize price and sentiment
Competitive Pricing and Offers
A seller tool tracks how a product is priced across the offers on its listing. The Glade Amazon API returns the product's offers, stock estimate, and sales estimate, and converts a known GTIN to an ASIN so the tool can match its own catalog. The data arrives normalized, so the tool does not parse raw Amazon pages.
Convert a GTIN to an ASIN, then pull that product's offers and stock estimate
Catalog and Deal Discovery
A deals site surfaces trending products and discounts without scraping. The Glade Amazon API serves the category taxonomy, best sellers, best-seller categories, and current deals, and autocomplete helps turn a shopper's partial query into a precise search. The site refreshes its feeds straight from the normalized data.
List the current deals in a category and cross-reference them with that category's best sellers
17 endpoints — the glade amazon api returns normalized amazon product, search, seller, category, offer, review, deal, and estimate data from a single rest surface.
METHOD
PATH
DESCRIPTION
/api/amazon/product
Get full product details for an ASIN
/api/amazon/search
Search the Amazon catalog
/api/amazon/product/reviews
Get a product's reviews
/api/amazon/product/offers
Get a product's offers
/api/amazon/deals
List current deals
/api/amazon/bestsellers
List best sellers
/api/amazon/seller
Look up a seller profile
/api/amazon/product
Get full product details for an ASIN
/api/amazon/search
Search the Amazon catalog
/api/amazon/product/reviews
Get a product's reviews
/api/amazon/product/offers
Get a product's offers
/api/amazon/deals
List current deals
/api/amazon/bestsellers
List best sellers
/api/amazon/seller
Look up a seller profile
What agents get from Jentic-routed access to this vendor.
Setup
Wiring the Glade Amazon API by hand means choosing between its API-KEY header and bearer token, and learning the query parameters that drive product, search, offers, and estimate lookups. Through Jentic you install once, import Glade from the API Directory, store the credential once, and your agent calls it.
Permission scoping
Glade's lookups take the ASIN, GTIN, or search term in the query string, so a rule bounds which operations your agent may call, such as product lookup and search, not which product. Every operation is a read, so you choose exactly which lookups the agent may run and nothing it calls changes your own data.
Credential isolation
Your Glade credential 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 'look up an Amazon product' or 'search Amazon', and Jentic returns the matching Glade operation with its input schema so the agent calls the right endpoint without reading the reference docs.
Alternatives and complements available in the Jentic catalogue.
Specific to using Glade Amazon API through Jentic.
What authentication does the Glade Amazon API use?
The Glade Amazon API accepts either an API key in the API-KEY header or a bearer token in the Authorization header per its OpenAPI spec. Through Jentic the credential you choose is stored encrypted by your own Jentic One instance and injected at call time, so it never sits in your agent's prompt or logs.
Can I search Amazon products with the Glade Amazon API?
Yes. The search operation queries the catalog and autocomplete turns a partial query into suggestions, while the product operation resolves a specific ASIN with its variants and offers. All of this data comes back normalized, so your agent does not parse raw Amazon pages.
What are the rate limits for the Glade Amazon API?
The Glade Amazon OpenAPI spec does not publish fixed rate limits. Plan for per-key limits and have your agent back off and retry on errors rather than assume an unlimited quota.
Is there a Glade Amazon API MCP server?
You do not need an MCP server to give your agent the Glade Amazon API. Jentic connects it directly from the API Directory: import it, store your credential once, and your agent calls its operations. Operations are discovered on demand, so your agent's context stays lean instead of loading a full tool list up front.
Can I limit what my agent is allowed to do with the Glade Amazon API?
Yes. Write a rule that allows only the product and search read operations, so the agent can look up products and search the catalog but cannot pull seller or deals data, and every call it makes is logged. Every Glade operation is a read, so nothing it can do changes your own data.
How do I look up an Amazon product with the Glade Amazon API through Jentic?
Search Jentic for 'look up an Amazon product by ASIN', and it returns the Glade product operation with its input schema. Your agent passes the ASIN and reads back the normalized details, variants, and offers. To run it on your own infrastructure, install Jentic One from its GitHub repo.
For Agents
Look up normalized Amazon product, search, seller, review, offer, and deal data, including stock and sales estimates and ASIN-GTIN conversion.
Use for: Get the full details for an Amazon product by ASIN, Search Amazon for wireless headphones, Find all current deals in a category, Retrieve the reviews for a product
Not supported: Does not place orders, manage listings, or process payments. Use for reading normalized Amazon product, search, seller, and pricing data only.
The Glade Amazon API returns normalized Amazon product, search, seller, category, offer, review, deal, and estimate data from a single REST surface. It resolves a product by ASIN with its variants and offers, converts between ASIN and GTIN, and serves search and autocomplete over the catalog. Stock and sales estimates, best sellers, category taxonomy, and current deals round out the read-only data it exposes.
This API is usable in Jentic One now. Its AI-readiness score against Jentic's framework shows where it stands today and where improvements would make it even easier for agents to use.
Base layer of spec validity and structural soundness.
Aggregated quality score from linter diagnostics, weighted by severity.
Percentage of `$ref` references that resolve successfully.
Checks whether the API description parses successfully and conforms to its declared specification (e.g., OpenAPI).
Structural correctness score based on schema issues using logarithmic dampening.
Clarity, completeness, and ingestion readiness for developers and tooling.
How richly the API is illustrated with examples.
Percentage of examples that conform to their schemas.
Percentage of operations with complete response definitions (success, client error, server error).
Health of API ingestion, bundling, and resolution within Jentic pipelines.
Semantic breadth, depth, and agent comprehension for AI systems.
Coverage of descriptions across API elements.
Coverage of RFC 9457 Problem Details for error responses.
Coverage, uniqueness, and casing consistency of operationIds for AI inference.
Coverage of summaries across operations/tags/info.
Functional utility, complexity comfort, and AI orchestration readiness.
Agent comfort level based on API operational and structural complexity.
Trust, risk posture, and security compliance.
Average quality of security schemes based on authentication method strength (weakest link for OAuth2).
Findability, semantic richness, and reasoning readiness.
Clarity and depth of descriptions across API elements.
Score it yourself
Every API in the directory is allowlisted, so you can re-score it with no key required.
npx @jentic/api-scorecard-cli score <openapi-url>