Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Management 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%2Factivecalculator.com%2Factivecalculator" | 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%2Factivecalculator.com%2Factivecalculator" | 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 Management API.
List all interactive calculators in your account
Register a webhook to receive calculator events
Read an existing webhook by its id
Remove a webhook you no longer need
Read your account identity
GET STARTED
Patterns agents use Management API for, with concrete tasks.
★ Agent-Managed Webhook Setup
A team wants calculator submissions to flow into their CRM automatically. An AI agent registers a webhook on the ActiveCalculator account that points at the destination, confirms it by reading the webhook back, and removes stale webhooks, so submission events reach downstream systems without manual configuration in the dashboard.
Register a webhook for calculator events pointing at a CRM endpoint, then read it back to confirm it was created
Calculator Inventory Sync
An operations team keeps a record of every calculator published across the account. The ActiveCalculator Management API lists all calculators and reads the account identity, so an agent can pull the current inventory and keep an internal catalog of calculators and their owner in sync.
List all calculators in the account and record each one alongside the account identity
Webhook Cleanup Routine
Over time an account accumulates webhooks pointing at endpoints that no longer exist. The API lists webhooks, reads each one by id, and removes the ones that are stale, letting an agent run a periodic cleanup so only live destinations keep receiving calculator events.
List the account's webhooks, identify ones pointing at dead endpoints, and remove them
6 endpoints — the activecalculator management api lists the interactive calculators in your account and manages the webhooks that fire when those calculators are used.
METHOD
PATH
DESCRIPTION
/calculators
List all calculators in the account
/webhooks
List all registered webhooks
/webhooks
Register a webhook for calculator events
/webhooks/{webhookId}
Read a webhook by its id
/webhooks/{webhookId}
Remove a webhook
/me
Read the caller's account identity
/calculators
List all calculators in the account
/webhooks
List all registered webhooks
/webhooks
Register a webhook for calculator events
/webhooks/{webhookId}
Read a webhook by its id
/webhooks/{webhookId}
Remove a webhook
/me
Read the caller's account identity
What agents get from Jentic-routed access to this vendor.
Setup
Wiring the ActiveCalculator Management API by hand means handling its header API key and tracking which webhook ids you have registered. Through Jentic you install once, import it from the API Directory, store the key once, and your agent calls it.
Permission scoping
You choose which ActiveCalculator operations your agent may call, so it can list calculators and read webhooks while the webhook register and remove operations stay out of the set unless you add them.
Credential isolation
Your ActiveCalculator 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 'register a calculator webhook' or 'list my calculators', and Jentic returns the matching 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 Management API through Jentic.
What authentication does the ActiveCalculator Management API use?
The ActiveCalculator Management API authenticates with an API key sent in a request header, per its OpenAPI spec. You generate the key in your ActiveCalculator account and send it with each request. Through Jentic the key is stored encrypted by your own Jentic One instance and injected at call time, so it never reaches the agent's context.
Can I register a webhook for calculator events through an agent?
Yes. The API registers a webhook that fires when a calculator is used, and it lets you read the webhook back by its id or remove it later. An agent can set up, verify, and clean up webhooks so calculator submissions reach your downstream systems.
What are the rate limits for the ActiveCalculator Management API?
The OpenAPI spec does not define rate limits. Check the ActiveCalculator documentation at https://activecalculator.com for the current limits that apply to the Management API.
How do I set up calculator webhooks through Jentic?
Import the ActiveCalculator Management API from the Jentic directory and give your agent an intent such as 'register a calculator webhook'. Jentic returns the webhook-registration operation with its input schema, your agent supplies the destination and calls it, and your stored key is injected at execution time. To run it on your own infrastructure, install Jentic One from its GitHub repo.
Can I limit what my agent is allowed to do with the ActiveCalculator Management API?
Yes. Write a rule that allows only the read operations, such as listing calculators and reading webhooks and the account, so your agent cannot register or remove webhooks, and every call it makes is logged.
Is there an ActiveCalculator MCP server?
You don't need an MCP server to give your agent the ActiveCalculator Management API. Jentic connects it directly from the API Directory: import it, store your credential once, and your agent calls it, so no extra server's tool definitions sit in the agent's context.
For Agents
List the calculators in an ActiveCalculator account and register, read, or remove the webhooks that deliver calculator events.
Use for: List all calculators in my ActiveCalculator account, Register a webhook for calculator submissions, Get an existing webhook by its id, Remove a webhook I no longer need
Not supported: Does not build, embed, or render calculators, and does not collect responses directly. Use for listing calculators and managing their webhooks only.
The ActiveCalculator Management API lists the interactive calculators in your account and manages the webhooks that fire when those calculators are used. You can register a webhook to receive calculator events, read or remove an existing webhook by id, list all your calculators, and read your account identity. It is the programmatic control surface for an ActiveCalculator workspace rather than the embed or builder itself.
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>