Install Jentic One Beta

Connect the Tempi API to your agent

Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Tempi 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%2Fmeettempi.com%2Fmeettempi" | sh

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%2Fmeettempi.com%2Fmeettempi" | sh
jentic register       # connects your agent to your Jentic One instance

Jentic 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 Tempi API.

List a person's or team's event types by handle, then find open slots for one event type in the invitee's timezone by date or a from and to range

Recheck that a start time is still open, then book it with start, name, email, and timezone, handling pending_approval and pending_payment statuses

Check a repeating series that recurs every 1, 2, or 4 weeks and book the whole series with repeat

Reschedule or cancel a booking as the invitee with the booking token, or as the host with an API key

GET STARTED

Start building with Tempi API

Explore with Jentic One

View OpenAPI Document

Use Cases

Patterns agents use Tempi API for, with concrete tasks.

★ Assistant booking through Jentic

An AI assistant can book a meeting on a Tempi page through Jentic without the invitee holding an account. It reads the host's event types by handle, finds open slots for the chosen type in the invitee's timezone, rechecks the chosen time, and books it with name, email, and timezone. If the event requires approval the booking comes back as pending_approval, and a paid event returns a paymentUrl, so the assistant can tell the person it is not confirmed yet.

Read the event types for handle sam, find open slots for slug intro-call next week in Europe/Dublin, check the first afternoon slot is still open, then book it for Jordan Lee at jordan@example.com

Host availability management

Hosts can let an agent keep their schedule in shape with an API key: replace weekly hours, set date overrides for holidays or travel, cap meetings per day or week, and preview the next days as bookers see them. When something looks wrong, the explain route lists every time on a date with the reason each one is blocked, such as a buffer, a calendar event, or a limit.

Set a date override for 2026-12-24 with no windows, cap meetings at 5 per day, then preview the next 14 days of availability

Team scheduling and booking requests

Teams can create collective event types, check when all hosts are in working hours with the shared-hours route, and handle requests that need approval. Host-side routes list bookings by window, approve or decline requests, reschedule or cancel, and attach a meeting link, while team webhooks report booking events to other systems.

List upcoming bookings, find the one from Alex with status pending_approval and approve it, decline a duplicate request with a reason, and add a webhook for the team that posts to the operations endpoint

Key Endpoints

80 endpoints — the tempi api finds open meeting times on a person's or team's booking page and books, reschedules, or cancels meetings, with public routes that need no account so an assistant can book on someone's behalf.

METHOD

PATH

DESCRIPTION

GET

/api/v1/public/{handle}

List a person's or team's event types

GET

/api/v1/public/{handle}/{slug}/slots

Find open times

POST

/api/v1/public/{handle}/{slug}/bookings

Book a meeting

POST

/api/v1/public/bookings/{id}/reschedule

Reschedule a booking as the invitee

POST

/api/v1/availability

Replace weekly hours

GET

/api/v1/bookings

List bookings

GET

/api/v1/event-types/{id}/availability

Explain why times can or can't be booked

GET

/api/v1/public/{handle}

List a person's or team's event types

GET

/api/v1/public/{handle}/{slug}/slots

Find open times

POST

/api/v1/public/{handle}/{slug}/bookings

Book a meeting

POST

/api/v1/public/bookings/{id}/reschedule

Reschedule a booking as the invitee

POST

/api/v1/availability

Replace weekly hours

GET

/api/v1/bookings

List bookings

GET

/api/v1/event-types/{id}/availability

Explain why times can or can't be booked

Why Jentic?

What agents get from Jentic-routed access to this vendor.

Setup

Wiring Tempi by hand means splitting calls between public routes, token-based invitee routes, and bearer-key account routes, and handling timezones, approval holds, and payment statuses yourself. Through Jentic you install once, import Tempi from the API Directory, store the key once, and your agent calls it.

Permission scoping

Tempi puts the host handle and event type slug in the URL path (/api/v1/public/{handle}/{slug}/bookings), so a rule can pin your agent to one booking page and the operations you pick. You choose the operations it may call, so destructive ones like deleting a team, revoking API keys, or disconnecting a calendar are not included unless you add them.

Credential isolation

Your Tempi 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 'find open meeting times' or 'book a meeting', and Jentic returns the matching Tempi operation with its input schema so the agent calls the right endpoint without browsing the reference docs.

FAQs

Specific to using Tempi API through Jentic.

What authentication does the Tempi API use?

Per its OpenAPI spec, the public booking routes, such as listing event types, finding open times, and booking, need no credential, and invitee changes use the booking's token instead. Account routes accept a bearer API key starting bk_ from Settings in the web app, or the tempi_session cookie used by the web app itself. Through Jentic the API key is stored encrypted on your own instance and injected at call time.

Is there a Tempi MCP server?

You don't need an MCP server to give your agent Tempi. Jentic connects it directly from the API Directory: import it, store your credential once, and your agent calls it. Operations are discovered on demand, so your agent's context carries no extra server's tool definitions.

Can I limit what my agent is allowed to do with the Tempi API?

Yes. For a booking assistant, write a rule that allows only GET /api/v1/public/sam/intro-call/slots and POST /api/v1/public/sam/intro-call/bookings, so it can find times and book on that one page but cannot change your hours, cancel bookings, or create API keys. Every call it makes is logged.

What are the rate limits for the Tempi API?

The OpenAPI spec does not specify rate limits; check https://meettempi.com for current limits.

Is a booking confirmed as soon as I create it?

Free events are confirmed at once. If the event type requires approval, the booking comes back with status pending_approval and holds the time until a host approves or declines, lapsing if nobody answers by its start. Paid events return status pending_payment with a paymentUrl that the person must pay first.

How do I book a meeting with Tempi through Jentic?

Search Jentic for an intent like 'book a meeting on a Tempi page' and import the Tempi API. Your agent calls GET /api/v1/public/{handle}/{slug}/slots for open times, then POST /api/v1/public/{handle}/{slug}/bookings with start, name, email, and timezone. Host-side changes use your API key, stored once. To run it on your own infrastructure, install Jentic One from its GitHub repo.

Meettempi Tempi API

AI ReadinessAI-Aware (B-)61/100

See full scorecard

Official vendor OpenAPI document · agent-readyProductivityCalendar Schedulingbearer, apiKey80 EndpointsREST

For Agents

Look up open times on a Tempi booking page and book, reschedule, or cancel meetings without an account, or, with an API key, manage working hours, event types, bookings, approvals, teams, calendars, and webhooks.

Use for: Find open times on Sam's 30-minute intro call next week, Book a meeting with the sales team for Thursday at 2pm my time, Check whether 10am tomorrow is still open before I book it, Reschedule my booking to next Monday

Not supported: Does not handle video calling, payment processing, or general calendar event editing. Use for Tempi booking pages, availability, and meeting bookings only.

The Tempi API finds open meeting times on a person's or team's booking page and books, reschedules, or cancels meetings, with public routes that need no account so an assistant can book on someone's behalf. Open slots already account for hosts' calendars, buffers, and limits, a time can be rechecked just before booking, and repeating series every 1, 2, or 4 weeks are checked and booked whole. Account routes let hosts set weekly hours and date overrides, cap meetings per day or week, create event types, approve or decline booking requests, connect calendars, manage teams and webhooks, and ask why a given time cannot be booked.

Jentic One on Github View OpenAPI Document

Show dimension breakdown

Foundational Compliance

Base layer of spec validity and structural soundness.

Grade: D+Signals: 4

94%

Lint Results

Aggregated quality score from linter diagnostics, weighted by severity.

100%

Resolution Completeness

Percentage of `$ref` references that resolve successfully.

Specification Validity

Checks whether the API description parses successfully and conforms to its declared specification (e.g., OpenAPI).

Structural Integrity

Structural correctness score based on schema issues using logarithmic dampening.

Developer Experience & Jentic Compatibility

Clarity, completeness, and ingestion readiness for developers and tooling.

Grade: B-Signals: 4

Example Density

How richly the API is illustrated with examples.

100%

Example Validity

Percentage of examples that conform to their schemas.

50%

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.

AI-Readiness & Agent Experience

Semantic breadth, depth, and agent comprehension for AI systems.

Grade: CSignals: 4

61%

Description Coverage

Coverage of descriptions across API elements.

Error Standardization

Coverage of RFC 9457 Problem Details for error responses.

100%

OperationId Quality

Coverage, uniqueness, and casing consistency of operationIds for AI inference.

53%

Summary Coverage

Coverage of summaries across operations/tags/info.

Agent Usability

Functional utility, complexity comfort, and AI orchestration readiness.

Grade: ASignals: 1

89%

Complexity Comfort

Agent comfort level based on API operational and structural complexity.

Security

Trust, risk posture, and security compliance.

Grade: CSignals: 1

55%

Authentication Strength

Average quality of security schemes based on authentication method strength (weakest link for OAuth2).

AI Discoverability

Findability, semantic richness, and reasoning readiness.

Grade: A-Signals: 1

72%

Descriptive Richness

Clarity and depth of descriptions across API elements.

Connect the Tempi API to your agent

Capabilities

Start building with Tempi API

Use Cases

Key Endpoints

Why Jentic?

Related APIs

FAQs

Meettempi Tempi API

Jentic AI Readiness Score

Tempi API

Foundational Compliance

Lint Results

Resolution Completeness

Specification Validity

Structural Integrity

Developer Experience & Jentic Compatibility

Example Density

Example Validity

Response Coverage

Tooling Readiness

AI-Readiness & Agent Experience

Description Coverage

Error Standardization

OperationId Quality

Summary Coverage

Agent Usability

Complexity Comfort

Security

Authentication Strength

AI Discoverability

Descriptive Richness