Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Embeddables 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%2Fembeddables.com%2Fembeddables" | 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%2Fembeddables.com%2Fembeddables" | 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 Embeddables API.
List the embeddable forms, quizzes, and widgets in your account
List the entries submitted through your embeddables
Read conversion counts for your embeddables
Patterns agents use Embeddables API for, with concrete tasks.
★ Agent-built conversion report
An agent assembles a conversion report by listing your embeddables and reading their conversion counts, then summarising which widgets are converting best. It discovers the embeddables and conversions operations through Jentic by intent and calls them with your API key injected, so no documentation or token handling is needed.
GET STARTED
List the account's embeddables, read their conversion counts, and report the top converting widgets
Submission review
Pull the entries submitted through an embeddable so an agent can review or export recent responses. Because the entries operation returns structured JSON, an assistant can scan new submissions and route them into a downstream workflow.
List recent entries for an embeddable and summarise the new submissions since the last check
Embeddable inventory audit
List every embeddable in the account so an agent can audit which forms, quizzes, and widgets are live before a reporting or cleanup task. The listing gives the inventory an assistant needs to decide which embeddables to pull entries and conversions for next.
List all embeddables in the account and group them by whether they have collected any entries
3 endpoints — the embeddables api reads the embeddable forms, quizzes, and widgets in your account along with the entries they collect and their conversion counts.
METHOD
PATH
DESCRIPTION
/api/v1/embeddables
List embeddables
/api/v1/entries
List entries
/api/v1/conversions
Conversion counts
/api/v1/embeddables
List embeddables
/api/v1/entries
List entries
/api/v1/conversions
Conversion counts
What agents get from Jentic-routed access to this vendor.
Setup
Wiring the Embeddables API by hand means sending your key in the x-api-key header, targeting the api.embeddables.com host, and paging through entries and conversions yourself. Through Jentic you install once, import the Embeddables API from the API Directory, store the key once, and your agent calls it.
Permission scoping
The Embeddables API is read-only, and its three operations list embeddables, read entries, and read conversions, so a rule bounds which of them your agent may call. You choose the operations it may call, so any you leave out stay off.
Credential isolation
Your Embeddables key 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 'list embeddable entries' or 'read conversion counts', and Jentic returns the matching Embeddables operation with its input schema so the agent calls the right endpoint without browsing the reference docs.
Alternatives and complements available in the Jentic catalogue.
Specific to using Embeddables API through Jentic.
What authentication does the Embeddables API use?
The Embeddables API authenticates with an API key sent in the x-api-key header, per its OpenAPI spec. Through Jentic the key is stored encrypted by your own Jentic One instance and injected at execution time, so it never enters the agent's context.
Can I read form entries with the Embeddables API?
Yes. The entries operation lists the submissions collected through your embeddables, and the conversions operation returns conversion counts, so an agent can review responses and report on how each widget is performing.
What are the rate limits for the Embeddables API?
The OpenAPI spec does not state request rate limits. Check the Embeddables documentation at https://api.embeddables.com for current limits and any per-key quotas.
Is there an Embeddables MCP server?
You don't need an MCP server to give your agent the Embeddables API. Jentic connects it directly from the API Directory: import it, store your key once, and your agent calls the embeddables, entries, and conversions operations it needs.
Can I limit what my agent is allowed to do with the Embeddables API?
Yes. The Embeddables API is read-only, so you scope by operation: write a rule that allows just the operations the task needs, such as listing entries and reading conversions, and the agent can call those and nothing else. Every call the agent makes is logged.
How do I read conversions through Jentic?
Search Jentic for 'read embeddable conversion counts', and it returns the Embeddables conversions operation with its input schema; your agent calls it with your key injected. To run it on your own infrastructure, install Jentic One from its GitHub repo.
For Agents
Read your Embeddables widgets, the entries they collect, and their conversion counts over a read-only API keyed by an x-api-key header.
Use for: List all embeddables in my account, Retrieve the entries submitted to an embeddable, Get conversion counts for my embeddables, Check how many entries an embeddable collected
Not supported: Does not build or edit embeddables, send notifications, or process payments. Use for reading embeddable entries and conversion counts only.
The Embeddables API reads the embeddable forms, quizzes, and widgets in your account along with the entries they collect and their conversion counts. An agent lists your embeddables, pulls the entries submitted through them, and reads conversion totals, authenticating with an API key in the x-api-key header. It is a read-only reporting surface over data captured by embeddables placed on your site.
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>