Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the FluoTest 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%2Ffluotest.com%2Ffluotest" | 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%2Ffluotest.com%2Ffluotest" | 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 FluoTest API.
Create a quiz and add its questions
List the quizzes in an account
Read a quiz's questions and its settings
Update an existing quiz
Publish a quiz so it can be taken
GET STARTED
Retrieve a published quiz's results
Delete a quiz that is no longer needed
Patterns agents use FluoTest API for, with concrete tasks.
★ Agent quiz creation
An AI agent connected through Jentic builds an assessment from a topic by creating a quiz and its questions and then publishing it, so a teacher or trainer gets a ready-to-take quiz without the developer wiring the JSON-RPC transport or the auth by hand.
Create a quiz with five questions on a topic and publish it so learners can take it
Assessment lifecycle management
A course tool lists existing quizzes, reads a quiz's questions and settings to review it, updates the wording, and republishes, keeping a bank of assessments current without editing each one in a dashboard.
List the quizzes, read one quiz's questions and settings, update a question, and republish it
Results retrieval
A reporting assistant retrieves a published quiz's results so it can summarise how learners did and flag questions that most people missed, reading the results directly rather than exporting a spreadsheet.
Retrieve a published quiz's results and summarise the score distribution for the teacher
4 endpoints — the fluotest api creates and manages quizzes over a json-rpc endpoint, so an agent can build an assessment and read how it performed.
METHOD
PATH
DESCRIPTION
/api/mcp
Send a quiz tool request over JSON-RPC
/api/mcp
Open the server-to-client event stream
/api/mcp
Terminate a session
/api/health
Service health check
/api/mcp
Send a quiz tool request over JSON-RPC
/api/mcp
Open the server-to-client event stream
/api/mcp
Terminate a session
/api/health
Service health check
What agents get from Jentic-routed access to this vendor.
Setup
Wiring FluoTest by hand means handling its bearer API key or OAuth2 sign-in and speaking its JSON-RPC transport to reach each quiz operation yourself. Through Jentic you install once, import FluoTest from the API Directory, store the credential once, and your agent calls it.
Permission scoping
FluoTest carries the quiz operation and its arguments in the JSON-RPC request body, so rules bound which operations your agent may call, not which quiz. Limit it to the quiz-create and quiz-read operations, so publishing and deleting quizzes stay out of reach unless you add those operations.
Credential isolation
Your FluoTest 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 'create a quiz' or 'read a quiz's results', and Jentic returns the matching FluoTest operation with its input schema so the agent calls the right operation without reading the reference docs.
Alternatives and complements available in the Jentic catalogue.
Specific to using FluoTest API through Jentic.
What authentication does the FluoTest API use?
The FluoTest API authenticates with either a personal API key sent as a bearer token or an OAuth2 sign-in, per its OpenAPI spec. The health check needs no credential. Through Jentic the key is stored encrypted by your own Jentic One instance and injected at call time, so it never lands in the agent's context.
Is there a FluoTest MCP server?
Yes. FluoTest's own surface speaks the Model Context Protocol over a JSON-RPC endpoint. You can also connect it directly through Jentic from the API Directory: your agent reaches the quiz operations through one gateway, your credential is injected at call time by your self-hosted instance instead of living in a config file, and your rules decide which operations the agent may call.
Can I limit what my agent is allowed to do with the FluoTest API?
Yes. The quiz tool and its arguments travel in the JSON-RPC request body, so a rule bounds which operations the agent may call. Allow only the quiz-create and quiz-read operations, so the agent can build and inspect quizzes but cannot publish or delete them, with every call logged.
Can I read a quiz's results with the FluoTest API?
Yes. Once a quiz is published, a results request returns how it performed, so an agent can summarise scores and flag the questions most learners missed without exporting a spreadsheet.
What are the rate limits for the FluoTest API?
The OpenAPI spec does not specify rate limits. Check the vendor documentation at https://fluotest.com/en/docs/api-reference for current limits before creating many quizzes.
How do I create a quiz through Jentic?
Search Jentic for 'create a quiz', which returns the FluoTest quiz-create operation with its input schema, then send the questions and publish the quiz. To run it on your own infrastructure, install Jentic One from its GitHub repo.
For Agents
Create and manage quizzes over a JSON-RPC endpoint: build a quiz and its questions, list quizzes, read questions and settings, update, publish, read results, and delete.
Use for: Create a quiz with questions, List all my quizzes, Get the questions for a quiz, Publish a quiz so it can be taken
Not supported: Does not handle proctoring, grading rubrics, or learner enrolment. Use for creating, publishing, and reading quizzes only.
The FluoTest API creates and manages quizzes over a JSON-RPC endpoint, so an agent can build an assessment and read how it performed. It creates a quiz and its questions, lists existing quizzes, reads a quiz's questions and settings, updates a quiz, and publishes it so it can be taken. Once a quiz is live it returns the results, and a quiz that is no longer needed can be deleted. A health endpoint confirms the service is up before a call.
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>