Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the CheapShark 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%2Fcheapshark.com%2Fcheapshark" | 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%2Fcheapshark.com%2Fcheapshark" | 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 CheapShark API.
List current PC game deals filtered by store, price, and rating
Compare a game's price across the tracked digital storefronts
Look up a game and its price history by title or id
List the stores CheapShark tracks
Manage price alerts for a game
Patterns agents use CheapShark API for, with concrete tasks.
★ Game deal comparison
A shopping tool needs to show where a PC game is cheapest right now. The CheapShark API lists current deals across storefronts so the tool can rank them by price and highlight the best offer.
Call GET /deals filtered by title and return the lowest-priced offer across stores
Price history lookup
A wishlist feature needs a game's price history to judge whether a deal is good. The games operation returns a game with its historical low so a backend can flag genuine discounts.
Call GET /games for a title and compare the current deal against the historical low
AI agent deal finder
An AI agent helping a shopper can find and compare game deals with no key to configure. Through Jentic the agent discovers the deals operation by intent and calls it directly.
Search Jentic for 'find current PC game deals', load the schema, and return the cheapest offer for a title
4 endpoints — the cheapshark api aggregates pc game deals and prices across digital storefronts.
METHOD
PATH
DESCRIPTION
/deals
List current game deals
/stores
List tracked digital storefronts
/games
Look up games and price history
/alerts
Manage price alerts for a game
/deals
List current game deals
/stores
List tracked digital storefronts
What agents get from Jentic-routed access to this vendor.
Setup
Wiring the CheapShark API by hand means shaping the deals, stores, and games query parameters and paging through results yourself. Through Jentic you install once, import the API from the API Directory, and your agent calls it.
Permission scoping
The CheapShark API takes its inputs as query parameters rather than a resource id in the URL path, so you limit the agent to the operations it needs, such as listing deals or looking up a game. You credit the agent only with the operations you allow, so anything you have not granted stays out unless you add it.
Credential isolation
The CheapShark API needs no key, so there is no secret to manage. Jentic runs the calls from your own self-hosted instance, and no credential enters the agent's prompt, logs, or context.
Intent-based discovery
Agents search Jentic by intent such as 'find current PC game deals', and Jentic returns the matching operation with its input schema so the agent calls the right endpoint without browsing docs.
Alternatives and complements available in the Jentic catalogue.
Specific to using CheapShark API through Jentic.
Does the CheapShark API require an API key?
No. The CheapShark public endpoints need no key, so there is no secret to manage. Through Jentic the calls run from your own self-hosted instance and no credential enters the agent's prompt, logs, or context.
Is there a CheapShark MCP server?
You don't need an MCP server to give your agent the CheapShark API. Jentic connects it directly from the API Directory: import it and your agent calls it, with no key required. That keeps another server's tool definitions out of your agent's context while still giving it the operation set from the spec.
Can the CheapShark API show a game's price history?
Yes. The GET /games operation returns a game with its historical low price, so a tool can judge whether a current deal is genuinely a discount.
Can I limit what my agent is allowed to do with the CheapShark API?
Yes. Because you run Jentic One yourself, your own rules decide which CheapShark operations the agent may use. You grant only the operations it needs, such as listing deals, so anything you have not granted stays off limits unless you add it. The choice of what the agent may call is yours.
How do I connect my agent to the CheapShark API through Jentic?
Search Jentic by intent such as 'find current PC game deals' to discover the operation, load its input schema, and your agent calls it with your stored credential injected at run time. To run it on your own infrastructure, install Jentic One from its GitHub repo.
GET STARTED
/games
Look up games and price history
/alerts
Manage price alerts for a game
For Agents
Find PC game deals, compare prices across stores, look up games with price history, and manage price alerts.
Use for: I need the current deals for a PC game, Compare a game's price across stores, Find the cheapest place to buy a game, Look up a game's price history
Not supported: Does not handle purchasing, payment, or game downloads - use for finding and comparing PC game deals and prices only.
The CheapShark API aggregates PC game deals and prices across digital storefronts. It lists current deals, the stores it tracks, game lookups with price history, and price alerts, so a shopping tool can compare where a game is cheapest. The public endpoints require no key.
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>