For Agents
Plan dependency-aware work: create flows and tasks, link dependencies, start, complete, reopen and assign tasks, and read what is ready, in progress, blocked, or assigned to the caller.
Use for: Create a new flow, Add a task to a flow, Add a dependency between two tasks, Complete a task
Not supported: Does not handle time tracking, invoicing, or file storage. Use for planning flows, tasks, and their dependencies only.
The Flowral API runs a dependency-aware planner: flows, the tasks inside them, and the derived state that tells a team what is ready, what is blocked, and when a project actually lands. It creates flows and tasks, links tasks with dependencies, and moves work through start, complete, reopen, and assignment, while the work views surface what is available, in progress, blocked, or assigned to the caller. It also runs brainstorms that turn ideas into flows, shares flows with guests, and manages per-person notification preferences and a log of what was sent.
Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Flowral 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%2Fflowral.app%2Fflowral" | 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%2Fflowral.app%2Fflowral" | 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 Flowral API.
Create flows and add the tasks that make them up
Add and remove dependencies between tasks
Start, complete, reopen, and assign tasks
See what work is ready, in progress, blocked, or assigned to the caller
Run brainstorms and turn ideas into flows
Share a flow with a guest and publish it
Set per-person notification preferences and read the delivery log
Patterns agents use Flowral API for, with concrete tasks.
★ Agent project orchestration
An AI agent connected through Jentic sets up a project by creating a flow, adding its tasks, and linking the dependencies between them, then assigns and starts the first ready task, so planning happens through the API without the developer wiring the bearer or OAuth auth or the task lifecycle by hand.
Create a flow, add three tasks, link their dependencies, and start the first task that is ready
Dependency-aware scheduling
A scheduling assistant reads the work views to see what is ready and what is blocked and on what, then completes finished tasks so newly unblocked work surfaces, keeping the plan moving without someone manually tracking the critical path.
Read what is ready and what is blocked, complete a finished task, and re-read what became available
Status reporting
A reporting tool pulls the whole-workspace overview and a flow's delivery report to tell stakeholders where a project stands and when it is expected to land, turning live task state into a summary without a manual status roll-up.
Pull the workspace overview and a flow's delivery report and summarize where the project stands
74 endpoints — the flowral api runs a dependency-aware planner: flows, the tasks inside them, and the derived state that tells a team what is ready, what is blocked, and when a project actually lands.
METHOD
PATH
DESCRIPTION
/v1/flows
List flows
/v1/flows
Create a flow
/v1/flows/{flowId}/tasks
List a flow's tasks
/v1/flows/{flowId}/tasks
Add a task to a flow
/v1/tasks/{taskId}/dependencies
Add a dependency between tasks
/v1/tasks/{taskId}/complete
Complete a task
/v1/work/available
What is ready to start
/v1/work/blocked
What is stuck, and on what
/v1/flows
List flows
/v1/flows
Create a flow
/v1/flows/{flowId}/tasks
List a flow's tasks
/v1/flows/{flowId}/tasks
Add a task to a flow
/v1/tasks/{taskId}/dependencies
Add a dependency between tasks
/v1/tasks/{taskId}/complete
Complete a task
/v1/work/available
What is ready to start
/v1/work/blocked
What is stuck, and on what
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>What agents get from Jentic-routed access to this vendor.
Setup
Wiring Flowral by hand means handling its bearer key or OAuth2 client-credentials exchange, respecting the role tied to each credential, and sequencing flow, task, and dependency calls yourself. Through Jentic you install once, import Flowral from the API Directory, store the credential once, and your agent calls it.
Permission scoping
Flowral puts the flow id and task id in the URL path (/v1/flows/{flowId}, /v1/tasks/{taskId}), and its OAuth credentials carry scopes such as flows:read and work:write, so a rule can pin your agent to read-only flow and work views. You choose the operations it may call, so write operations like completing a task or archiving a flow are not included unless you add them.
Credential isolation
Your Flowral credential 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 project flow' or 'find what work is blocked', and Jentic returns the matching Flowral 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 Flowral API through Jentic.
What authentication does the Flowral API use?
The Flowral API authenticates with a bearer API key, or with an OAuth2 client-credentials token exchanged for a short-lived access token, per its OpenAPI spec. The OAuth token-exchange endpoints need no credential themselves. A credential belongs to one workspace and carries its own role. Through Jentic the credential 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 Flowral MCP server?
You don't need an MCP server to give your agent Flowral. Jentic connects it directly from the API Directory: import it, store your credential once, and your agent calls the flow, task, and work operations on demand, without a separate server's tool definitions loaded into its context.
Can I limit what my agent is allowed to do with the Flowral API?
Yes. Write a rule that allows only the read operations, such as listing flows and reading what work is ready or blocked, so the agent can report on a project but cannot create flows, complete tasks, or archive work, and every call it makes is logged.
Can I track task dependencies with the Flowral API?
Yes. You add a dependency between two tasks and remove it later, and the work views then report what is ready and what is blocked and on what, so an agent can reason about the critical path from live state.
What are the rate limits for the Flowral API?
The OpenAPI spec does not specify rate limits. Check the vendor documentation at https://flowral.app for current limits before running large planning jobs.
How do I create a flow and tasks through Jentic?
Search Jentic for 'create a project flow', which returns the Flowral create-flow operation with its input schema, then add tasks and link their dependencies. To run it on your own infrastructure, install Jentic One from its GitHub repo.
GET STARTED