LoopGantt API
62
AI ReadinessAI-Aware (B-)62/100
Official vendor OpenAPI document · agent-readyProductivityTask Managementbearer (API key, sk_live_ format) on project endpoints; keyless chart, schedule, and template endpoints8 EndpointsREST
For Agents
Schedule a task plan with dependencies, get back the critical path and end date, and hand the user a LoopGantt claim link or PNG of the chart. Start from an industry template or create stored projects with an API key.
Use for: I need to turn this task list into a Gantt chart with a critical path, Compute the project end date for these tasks and dependencies, Find a construction project template I can adapt, Get a PNG image of the Gantt chart I just created
Not supported: Does not handle time tracking, team assignments, resource leveling, or budgets. Use for scheduling task plans into Gantt charts with critical-path dates only.
The LoopGantt API turns a task list with durations and dependencies into a scheduled Gantt chart, computing the critical path, float, and project end date. A keyless endpoint creates a chart and returns a claim link the user can open to view, export, and save it, while a separate scheduling endpoint returns dates without storing anything. Dependencies support the FS, SS, FF, and SF link types with lag, tasks can be grouped under phases, and industry templates for software, construction, marketing, events, IT, HR, and finance provide ready-made task lists. Account holders can also create stored projects and list the projects they own with a bearer API key.
Install Jentic One Beta
Connect the LoopGantt API to your agent
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the LoopGantt 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.
1
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%2Floopgantt.com%2Floopgantt" | sh2
Step 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%2Floopgantt.com%2Floopgantt" | 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.
Capabilities
What an agent can do with LoopGantt API.
Compute a critical-path schedule with dates, float, and project end from a task list via POST /schedule without storing anything
Create a Gantt chart without an account through POST /gantt and return the claimUrl the user opens to view, export, and save it
Link tasks with FS, SS, FF, or SF dependencies and lag, and group them under phases using isPhase and parent
Start a plan from industry templates such as software, construction, or events via GET /templates and GET /templates/{slug}
Render the scheduled chart as a PNG with the critical path highlighted through GET /gantt/{token}/image.png
Create stored projects with tasks and list the projects you own through POST /projects and GET /projects with an API key
Use Cases
Patterns agents use LoopGantt API for, with concrete tasks.
★ Agent-built project plans through Jentic
A planning agent turns a conversation about a launch into tasks with durations and dependencies, then calls LoopGantt through Jentic to schedule them and return a chart the user can open. The agent searches Jentic for 'create a Gantt chart', receives the POST /gantt input schema with its tasks, dependencies, and workDays fields, and hands the user the claimUrl from the response.
Search Jentic for 'create a Gantt chart', then call POST /gantt with name 'Website relaunch', startDate '2026-12-01', and tasks Design (10 days), Build (15 days, FS on Design), and Launch (milestone, FS on Build), and return the claimUrl to the user
What-if schedule checks
Before committing to a plan, compute the schedule for alternative task orders or durations and compare the end dates. POST /schedule runs the critical-path engine and returns dates, the critical path, and float for each task without storing a chart, so a planner can test several variants and keep only the one that fits the deadline.
Call POST /schedule twice with the same five tasks, once with Testing at 5 days and once at 10 days, and report which variant finishes before 2027-02-01
Template-based kickoff
Start a new plan from LoopGantt's industry templates instead of a blank page. GET /templates lists templates for software, construction, marketing, events, IT, HR, and finance with task counts and typical durations, and GET /templates/{slug} returns the task list with durations and milestones, ready to adjust and pass to POST /gantt.
Call GET /templates, pick the events template, fetch it with GET /templates/{slug}, shift the start date to 2027-03-01, and create the chart with POST /gantt
Chart image for status updates
Drop a picture of the current plan into a status update or chat thread. GET /gantt/{token}/image.png returns a server-rendered PNG of the scheduled chart with the critical path highlighted and milestones drawn as diamonds, covering at most 40 rows, and fetching it does not extend the chart's expiry.
Take the token from the last segment of a claimUrl and call GET /gantt/{token}/image.png, then attach the PNG to the weekly status message
Key Endpoints
8 endpoints — the loopgantt api turns a task list with durations and dependencies into a scheduled gantt chart, computing the critical path, float, and project end date.
METHOD
PATH
DESCRIPTION
POST
/gantt
Create a Gantt chart without an account
POST
/schedule
Compute a critical-path schedule without storing it
GET
/gantt/{token}
Read the chart behind a claim link
GET
/gantt/{token}/image.png
Render the chart as a PNG
GET
/templates
List industry templates
GET
/templates/{slug}
Get one template with its task list
POST
/projects
Create a stored project with tasks
GET
/projects
List your projects
POST
/gantt
Create a Gantt chart without an account
POST
/schedule
Compute a critical-path schedule without storing it
GET
/gantt/{token}
Read the chart behind a claim link
GET
/gantt/{token}/image.png
Render the chart as a PNG
GET
/templates
List industry templates
GET
/templates/{slug}
Get one template with its task list
POST
/projects
Create a stored project with tasks
GET
/projects
List your projects
Jentic AI Readiness Score
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.
L
LoopGantt API
- AI-Aware (B-)62/100
59
Foundational Compliance64
Developer Experience & Jentic Compatibility47
AI-Readiness & Agent Experience94
Agent Usability60
Security77
AI DiscoverabilityPowered by JenticScoring Framework 1.0.0 | Scoring Engine 0.4.2
Show dimension breakdown
59
Foundational Compliance
Base layer of spec validity and structural soundness.
Grade: C+Signals: 4
94%
Lint Results
Aggregated quality score from linter diagnostics, weighted by severity.
100%
Resolution Completeness
Percentage of `$ref` references that resolve successfully.
0%
Specification Validity
Checks whether the API description parses successfully and conforms to its declared specification (e.g., OpenAPI).
42%
Structural Integrity
Structural correctness score based on schema issues using logarithmic dampening.
64
Developer Experience & Jentic Compatibility
Clarity, completeness, and ingestion readiness for developers and tooling.
Grade: BSignals: 4
0%
Example Density
How richly the API is illustrated with examples.
100%
Example Validity
Percentage of examples that conform to their schemas.
56%
Response Coverage
Percentage of operations with complete response definitions (success, client error, server error).
100%
Tooling Readiness
Health of API ingestion, bundling, and resolution within Jentic pipelines.
47
AI-Readiness & Agent Experience
Semantic breadth, depth, and agent comprehension for AI systems.
Grade: DSignals: 4
38%
Description Coverage
Coverage of descriptions across API elements.
0%
Error Standardization
Coverage of RFC 9457 Problem Details for error responses.
100%
OperationId Quality
Coverage, uniqueness, and casing consistency of operationIds for AI inference.
50%
Summary Coverage
Coverage of summaries across operations/tags/info.
94
Agent Usability
Functional utility, complexity comfort, and AI orchestration readiness.
Grade: A+Signals: 1
94%
Complexity Comfort
Agent comfort level based on API operational and structural complexity.
60
Security
Trust, risk posture, and security compliance.
Grade: B-Signals: 1
60%
Authentication Strength
Average quality of security schemes based on authentication method strength (weakest link for OAuth2).
77
AI Discoverability
Findability, semantic richness, and reasoning readiness.
Grade: A-Signals: 1
77%
Descriptive Richness
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>Why Jentic?
What agents get from Jentic-routed access to this vendor.
Setup
Wiring LoopGantt by hand means modelling task dependencies with FS, SS, FF, and SF links, tracking which endpoints are keyless and which need the sk_live_ bearer key, and handling 429 responses with Retry-After. Through Jentic you install once, import LoopGantt from the API Directory, store the API key once, and your agent calls it.
Permission scoping
Rules filter by method and path, so you can bound the agent to LoopGantt's keyless planning operations, such as scheduling and template reads, and leave the authenticated project operations out. Chart reads carry the claim token in the path (/gantt/{token}), so a rule can also pin the agent to one chart's read and image operations.
Credential isolation
Your LoopGantt API 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 Gantt chart' or 'compute a critical path', and Jentic returns the matching LoopGantt operation with its input schema, including the tasks and dependencies structure, so the agent calls the right endpoint without browsing the reference docs.
Related APIs
Alternatives and complements available in the Jentic catalogue.
FAQs
Specific to using LoopGantt API through Jentic.
What authentication does the LoopGantt API use?
Per its OpenAPI spec, the LoopGantt API uses a bearer token, an API key in the sk_live_ format, on the project endpoints POST /projects and GET /projects. The chart, schedule, and template endpoints such as POST /gantt and POST /schedule are keyless and need no credential. Through Jentic, the API key is stored encrypted by your own Jentic One instance and attached at execution time.
Can I get the critical path without creating a chart?
Yes. POST /schedule takes the same task list as POST /gantt, with durations, dependencies of type FS, SS, FF, or SF, optional lag, workDays, and holidays, and returns dates, the critical path, float, and project end. Nothing is stored, so it suits trying several plan variants before creating the chart the user will keep.
What are the rate limits for the LoopGantt API?
The OpenAPI spec states that POST /gantt is limited to 10/hour and 30/day, and that POST /schedule is rate limited to 60 per hour per network. Exceeded limits return HTTP 429 with a Retry-After header. Check https://loopgantt.com for current limits on the authenticated project endpoints.
How do I create a Gantt chart with LoopGantt through Jentic?
Install Jentic One, add the LoopGantt API from the Jentic directory, and have your agent search for 'create a Gantt chart'. Jentic returns the POST /gantt operation with its input schema; the agent sends name, startDate, and tasks, then gives the user the claimUrl from the response. To run it on your own infrastructure, install Jentic One from its GitHub repo.
How long does a keyless LoopGantt chart last?
A chart created with POST /gantt expires after 7 days, extended to 30 days once its claim link is opened. Reading it with GET /gantt/{token} extends the expiry, while fetching the PNG with GET /gantt/{token}/image.png does not. The user saves the chart to an account from the claim link to keep it.
Is there a LoopGantt MCP server?
You don't need an MCP server to give your agent LoopGantt. Jentic connects it directly from the API Directory: import it, store your API key once for the project endpoints, and your agent calls it. Operations are found on demand by intent, so no extra tool definitions sit in the agent's context.
Can I limit what my agent is allowed to do with the LoopGantt API?
Yes. A rule that allows POST /schedule and GET /templates lets the agent plan and test schedules without creating anything, and adding POST /gantt lets it hand out new charts while your saved projects stay out of reach. The agent's calls are logged for review.
GET STARTED