Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Cheers Public API (legacy snapshot), 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%2Fcheers.tech%2Fcheers" | 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%2Fcheers.tech%2Fcheers" | 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 Cheers Public API (legacy snapshot) API.
List the organizations and organization connections in a workspace
List the cards (badges) tied to a workspace and update a card
Read the taps a card has recorded
Pull the reviews collected for a workspace
Read the links and the interactions logged against them
GET STARTED
Patterns agents use Cheers Public API (legacy snapshot) API for, with concrete tasks.
★ Agent-Built Engagement Reports
An AI agent reads a Cheers workspace's taps, reviews, links, and link interactions through Jentic and assembles an engagement report without a human exporting data by hand. Every call carries the workspace bearer token, so the agent only sees that workspace, and a rule can keep it on the read operations. The agent discovers each read by intent and calls it directly.
Read the taps, reviews, and link interactions for the workspace and summarize this week's engagement.
Review and Reputation Dashboard
A dashboard pulls the reviews a workspace has collected along with the cards (badges) and organizations they belong to, giving a reputation view per organization. Cheers returns reviews keyed to the bearer token's workspace, and the cards endpoint can update a badge's details. This drives a read-first reputation surface over the snapshot.
List the organizations, pull their reviews, and rank organizations by review count.
Tap and Link Interaction Analytics
An analytics flow reads taps from NFC cards and the interactions logged against shared links to measure how often each converts. Cheers exposes taps, links, and link interactions as separate reads keyed to the workspace. Teams use this to see which cards and links drive the most engagement.
Pull link interactions and taps, then compute the interaction rate per link for the workspace.
8 endpoints — the cheers api is a legacy public snapshot that reads a workspace's engagement data: organizations and their connections, the cards (badges) tied to them, the taps those cards record, the reviews collected, and the links and link interactions behind them.
METHOD
PATH
DESCRIPTION
/organizations
List organizations
/cards
List cards (badges)
/cards
Update a card (badge)
/taps
List taps
/reviews
List reviews
/links
List links
/link_interactions
List link interactions
/organizations
List organizations
/cards
List cards (badges)
/cards
Update a card (badge)
/taps
List taps
/reviews
List reviews
/links
List links
/link_interactions
List link interactions
What agents get from Jentic-routed access to this vendor.
Setup
Wiring the Cheers API by hand means sending a bearer token on every read and keeping to the one workspace that token belongs to, against a legacy snapshot whose current contract lives elsewhere. Through Jentic you install once, import Cheers from the API Directory, store the token once, and your agent calls it.
Permission scoping
Cheers is almost entirely read endpoints with a single card update, so a rule can bound your agent to the reads it needs, such as taps, reviews, and link interactions. You choose the operations it may call, so updating a card is not included unless you add it.
Credential isolation
Your Cheers token 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 'read the reviews for my workspace', and Jentic returns the matching Cheers 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 Cheers Public API (legacy snapshot) API through Jentic.
What authentication does the Cheers API use?
The Cheers API authenticates with a bearer token (an API key) in the Authorization header, per its OpenAPI spec, and every read is scoped to that token's workspace. This is a legacy public snapshot, so check the vendor's current documentation for any newer auth details. Through Jentic the token is stored encrypted by your own Jentic One instance and injected only at call time.
Can I read taps, reviews, and links with the Cheers API?
Yes. The API lists a workspace's organizations and connections, its cards (badges) and the taps they record, the reviews collected, and the links with their logged interactions. The cards endpoint can also update a badge's details.
What are the rate limits for the Cheers API?
The OpenAPI spec does not specify rate limits for the Cheers API, and because it is a legacy snapshot the current limits live with the vendor. Check the documentation at https://app.cheers.tech/docs for current limits.
Can I limit what my agent is allowed to do with the Cheers API?
Yes. Write a rule that allows only the read operations, such as listing taps, reviews, and links, so the agent reports on engagement but cannot update a card. Every call carries your workspace token, is logged, and the agent never sees the token itself.
Is there a Cheers MCP server?
You don't need an MCP server to give your agent the Cheers API. Jentic connects it directly from the API Directory: import it, store your workspace token once, and your agent calls the tap, review, and link reads. You skip loading another server's tool definitions into the agent's context.
How do I read Cheers engagement data through Jentic?
Add the Cheers API from the Jentic API Directory and store your workspace token once. Your agent then searches by intent such as 'read the reviews for my workspace' and Jentic returns the matching operation with its input schema, so it can pull the reviews, taps, and link interactions. To run it on your own infrastructure, install Jentic One from its GitHub repo.
For Agents
Read a workspace's organizations, cards (badges), taps, reviews, links, and link interactions, and update a card, using a bearer token. A legacy public snapshot for reporting on tap-card engagement and reviews.
Use for: List the organizations in my Cheers workspace, Read the taps recorded by a badge, Pull the reviews collected this month, Get the links and their interaction counts
Not supported: Does not send review requests, run ad campaigns, or program NFC cards. Use for reading Cheers workspace engagement, reviews, and link data only.
The Cheers API is a legacy public snapshot that reads a workspace's engagement data: organizations and their connections, the cards (badges) tied to them, the taps those cards record, the reviews collected, and the links and link interactions behind them. The cards endpoint also updates a badge. It returns the data a reporting or reputation dashboard needs, keyed to the bearer token's workspace, while the current contract lives behind the vendor's own documentation.
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>