Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Inistate 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%2Finistate.com%2Finistate" | 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%2Finistate.com%2Finistate" | 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 Inistate API.
List reachable workspaces and read a workspace's detail
Discover the modules available in a workspace
List and filter the entries held in a module
Create a new entry in a module
Update an existing entry by id
GET STARTED
Run an activity on an entry and read its activity history
Patterns agents use Inistate API for, with concrete tasks.
★ Agent-Driven Record Updates
An AI agent connected through Jentic lists the entries in a module, finds the one it needs with a filter, and updates it by id. Because entries, modules, and workspaces are addressed consistently, the agent reads and writes Inistate business records without a per-module integration.
List entries in a module, filter to the matching record, and update its fields by entry id
Workflow Activity Automation
Operations teams advance records through a process by running activities. Inistate exposes an activity-form operation that returns a form definition and initial payload and an activity operation that performs the action, so an agent fetches the form, fills it, and runs the step on the right entry.
Fetch the activity form for an entry, build the payload, and perform the activity to advance its workflow
Module Discovery and Reporting
Reporting tools map what a workspace contains before pulling data. Inistate's discovery operations list the modules in a workspace and their canvas payloads, so an agent learns the available modules and then lists each module's entries for a report.
Discover the modules in a workspace, then list the entries in a chosen module for a summary report
13 endpoints — the inistate api reads and writes the business records that live on the inistate low-code platform, organized as entries inside modules inside workspaces.
METHOD
PATH
DESCRIPTION
/api/workspace
List reachable workspaces
/api/workspace/{workspaceId}
Get a workspace's detail
/api/m/list
List entries with filters
/api/m
Create a new entry
/api/m/{entryId}
Update an existing entry
/api/m/activity
Perform an activity on an entry
/api/m/history
Get an entry's activity history
/api/workspace
List reachable workspaces
/api/workspace/{workspaceId}
Get a workspace's detail
/api/m/list
List entries with filters
/api/m
Create a new entry
/api/m/{entryId}
Update an existing entry
/api/m/activity
Perform an activity on an entry
/api/m/history
Get an entry's activity history
What agents get from Jentic-routed access to this vendor.
Setup
Wiring Inistate by hand means choosing between its `Authorization` API key and its OAuth 2.0 password flow, then learning the workspace, module, and entry shape before you can read a record. Through Jentic you install once, import Inistate from the API Directory, store the credential once, and your agent calls the entry and activity operations.
Permission scoping
Inistate carries read operations for workspaces, modules, and entries alongside write operations that create entries, update them, and run activities. You choose the operations your agent may call, so a rule can keep it to listing and reading entries and leave entry creation, updates, or activities out unless you add them.
Credential isolation
Your Inistate API key or OAuth token is held by your own Jentic One instance, encrypted, 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 entries in a module' or 'run an activity on an entry', and Jentic returns the matching Inistate 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 Inistate API through Jentic.
What authentication does the Inistate API use?
The spec declares two options: an API key sent in the `Authorization` header in the form `fsk {your api key}`, and an OAuth 2.0 password-flow token from the `/token` endpoint. Through Jentic the credential you choose is held by your own Jentic One instance and attached to each request at execution time, so it never appears in your agent's prompt or logs.
Can I create and update records with the Inistate API?
Yes. You create an entry in a module, update an existing entry by its id, and list entries with filters. Because entries live inside modules inside workspaces, your agent reads and writes business records across the platform through one consistent shape.
What are the rate limits for the Inistate API?
The OpenAPI spec does not specify rate limits. Check the Inistate community documentation at https://community.inistate.com for current limits before running bulk entry imports or updates.
Is there an Inistate MCP server?
You do not need an MCP server to give your agent the Inistate API. Jentic connects it directly from the API Directory: import it, store your key once, and your agent calls the workspace, entry, and activity operations on demand without loading an extra server's tool definitions into its context.
Can I limit what my agent is allowed to do with the Inistate API?
Yes. Write a rule that allows only the workspace and entry list operations, so the agent can read records across your modules and cannot create entries, update them, or run activities on them. You choose which operations it may call, and every call it makes is logged.
How do I update a record through Jentic?
Install the Jentic One command line with `curl -fsSL https://raw.githubusercontent.com/jentic/jentic-one/main/tools/install.sh | sh`, then add the Inistate API from the Jentic directory and search by intent such as 'update an entry in a module'. Jentic returns the matching operation with its input schema so your agent builds a valid request. To run it on your own infrastructure, install Jentic One from its GitHub repo.
Know of an official OpenAPI document? Contribute it →
For Agents
List Inistate workspaces and modules, list and filter entries, create and update entries, run activities on them, and read an entry's history through the Inistate low-code platform API.
Use for: List all workspaces I can access in Inistate, Discover the modules available in a workspace, Find entries in a module that match a filter, Create a new entry in a module
Not supported: Does not host websites, send email campaigns, or process payments. Use for reading and writing Inistate workspaces, modules, and entries only.
The Inistate API reads and writes the business records that live on the Inistate low-code platform, organized as entries inside modules inside workspaces. An agent lists the workspaces it can reach, discovers the modules available in a workspace, and then lists, creates, and updates the entries each module holds. Activities drive the workflow on an entry, and a history operation returns the actions that have been performed on it.
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>