Official vendor OpenAPI document · agent-readyProductivityTask ManagementapiKey, bearer159 EndpointsREST
For Agents
Track time across projects and tasks with timers, expenses, and notes. Manage projects, tasks, tags, rates, teams, and organizations, and generate exports and invoice series from tracked time.
Use for: Start a timer for a task, Create a new project and task, Log an expense against a project, List time tracked this week
Not supported: Does not handle payroll runs, payment processing, or HR records. Use for time tracking, expenses, and billing exports only.
The Timesheet API tracks time across projects, tasks, and teams, recording timers, expenses, and notes against each. It manages projects, tasks, tags, rates, and organizations, generates exports and invoice series from tracked time, and drives automations and webhooks, so an agent can run time tracking and billing workflows without manual entry.
Install Jentic One Beta
Connect the Timesheet API to your agent
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Timesheet 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%2Fapi.timesheet.io%2Ftimesheet" | 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%2Fapi.timesheet.io%2Ftimesheet" | 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 Timesheet API.
Start, pause, and read the running timer for time tracking
Manage projects, tasks, and tags that time is tracked against
Record expenses and notes tied to work
Manage teams, organizations, and their members
Generate exports and invoice series from tracked time
Configure automations, webhooks, and API keys
Use Cases
Patterns agents use Timesheet API for, with concrete tasks.
★ Time Tracking Agent
An AI agent records work by starting and stopping the timer against the right task, and logs expenses or notes as they come up. Through Jentic the agent discovers the timer and task operations by intent and calls them directly, so time is captured as work happens without a person opening a tracker.
Start the timer for a task and log an expense against the same project
Project and Task Setup
Set up the structure that time is tracked against by creating projects, tasks, and tags, and assigning rates. This lets an agent onboard a new client or engagement so that subsequent time entries and invoices map to the right work.
Create a project with a task and apply the billing rate for the engagement
Billing and Export
Turn tracked time into billing by generating exports and invoice series from the recorded entries. The agent can produce a data export for reporting or an invoice series for a client, closing the loop from tracked time to billing.
Generate an invoice series from the time tracked against a project this month
Key Endpoints
159 endpoints — the timesheet api tracks time across projects, tasks, and teams, recording timers, expenses, and notes against each.
METHOD
PATH
DESCRIPTION
GET
/v1/tasks
List tasks
POST
/v1/tasks
Create a task
GET
/v1/timer
Get the running timer
GET
/v1/expenses
List expenses
POST
/v1/invoice-series
Create an invoice series
GET
/v1/tasks
List tasks
POST
/v1/tasks
Create a task
GET
/v1/timer
Get the running timer
GET
/v1/expenses
List expenses
POST
/v1/invoice-series
Create an invoice series
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.
T
Timesheet API
- Foundational (C+)57/100
81
Foundational Compliance65
Developer Experience & Jentic Compatibility36
AI-Readiness & Agent Experience63
Agent Usability63
Security100
AI DiscoverabilityPowered by JenticScoring Framework 1.0.0 | Scoring Engine 0.4.0
Show dimension breakdown
81
Foundational Compliance
Base layer of spec validity and structural soundness.
Grade: ASignals: 4
94%
Lint Results
Aggregated quality score from linter diagnostics, weighted by severity.
100%
Resolution Completeness
Percentage of `$ref` references that resolve successfully.
100%
Specification Validity
Checks whether the API description parses successfully and conforms to its declared specification (e.g., OpenAPI).
30%
Structural Integrity
Structural correctness score based on schema issues using logarithmic dampening.
65
Developer Experience & Jentic Compatibility
Clarity, completeness, and ingestion readiness for developers and tooling.
Grade: BSignals: 4
5%
Example Density
How richly the API is illustrated with examples.
100%
Example Validity
Percentage of examples that conform to their schemas.
55%
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.
36
AI-Readiness & Agent Experience
Semantic breadth, depth, and agent comprehension for AI systems.
Grade: FSignals: 4
34%
Description Coverage
Coverage of descriptions across API elements.
0%
Error Standardization
Coverage of RFC 9457 Problem Details for error responses.
50%
OperationId Quality
Coverage, uniqueness, and casing consistency of operationIds for AI inference.
61%
Summary Coverage
Coverage of summaries across operations/tags/info.
63
Agent Usability
Functional utility, complexity comfort, and AI orchestration readiness.
Grade: B-Signals: 1
63%
Complexity Comfort
Agent comfort level based on API operational and structural complexity.
63
Security
Trust, risk posture, and security compliance.
Grade: B-Signals: 1
62%
Authentication Strength
Average quality of security schemes based on authentication method strength (weakest link for OAuth2).
100
AI Discoverability
Findability, semantic richness, and reasoning readiness.
Grade: A+Signals: 1
100%
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 the Timesheet API by hand means handling two auth options and the timer, task, and export sequence yourself. Through Jentic you install once, import Timesheet from the API Directory, store the credential once, and your agent calls it.
Permission scoping
Timesheet identifies projects, tasks, and time entries by an id in the request path, so a rule bounds which operations your agent may call. You choose those operations, so destructive ones like deleting a project or an account are not included unless you add them.
Credential isolation
Timesheet accepts a JWT bearer token or an API key in the Authorization header. Whichever you provide is stored once, encrypted, by your own Jentic One instance and injected at execution time, so it never enters the agent's prompt or logs.
Intent-based discovery
Agents search Jentic by intent such as 'start a timer' or 'generate an invoice from tracked time', and Jentic returns the matching Timesheet operation with its input schema 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 Timesheet API through Jentic.
What authentication does the Timesheet API use?
The Timesheet API accepts two credentials: a JWT bearer token, or an API key sent in the Authorization header using the ApiKey scheme. Through Jentic whichever you provide is stored encrypted by your own Jentic One instance and injected at call time, so it never enters the agent's prompt or logs.
Can I start a timer with the Timesheet API?
Yes. Use the timer operations to start, pause, and read the running timer, and GET /v1/tasks to pick the task it applies to. Time recorded this way flows into exports and invoice series.
What are the rate limits for the Timesheet API?
The OpenAPI spec does not specify rate limits. Check the Timesheet documentation at https://api.timesheet.io before running high-volume sync or export jobs.
Is there a Timesheet MCP server?
You don't need an MCP server to give your agent the Timesheet API. Jentic connects it directly from the API Directory: import it, store your credential once, and your agent calls the timer and task operations it needs.
Can I limit what my agent is allowed to do with the Timesheet API?
Yes. Write a rule that allows only the timer, task, and expense operations, so the agent can track work but cannot delete a project or an account, and every call it makes is logged.
How do I track time with the Timesheet API through Jentic?
Search Jentic for 'start a timer for a task', and it returns the timer and GET /v1/tasks operations with their input schemas so your agent records time directly. To run it on your own infrastructure, install Jentic One from its GitHub repo.
GET STARTED