Install Jentic One Beta

Connect the Myla Developer API to your agent

Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Myla Developer 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%2Fmyla.cx%2Fmyla" | 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%2Fmyla.cx%2Fmyla" | 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 Myla Developer API.

Upsert a contact by phone or email so an existing match is updated instead of duplicated

Update a contact's name, lifecycleStageId, and customFields values

Add tags to a contact by passing tagIds

Look up contacts by email or phone and page through the full contact list

Read a conversation with its channel, status, priority, awaitingReply flag, and messages

GET STARTED

Start building with Myla Developer API

Explore with Jentic One

View OpenAPI Document

Use Cases

Patterns agents use Myla Developer API for, with concrete tasks.

★ Agent-maintained contact records through Jentic

A developer's agent connected through Jentic keeps Myla contacts in sync with another system. It upserts each contact by email or phone, so a match is updated rather than duplicated, sets the lifecycleStageId as the customer moves on, and fills customFields with fieldId and value pairs. The workspace stays current without manual imports.

Call POST /api/v1/contacts with email='jo@example.com', name='Jo Park', and lifecycleStageId='stage_123', then POST /api/v1/contacts/{id}/tags with tagIds set to the VIP tag id using the returned id

Conversation summaries for follow-up

A support lead wants a daily digest of open threads. An agent lists conversations, fetches each one with its messages, and checks status and awaitingReply to pick out threads still waiting on the team. It returns a short summary per thread with the customer name and channel.

Call GET /api/v1/conversations with limit=25, then GET /api/v1/conversations/{id} for each one and report the threads where awaitingReply is true

Real-time event triggers

When a downstream workflow needs to react to customer messages, a webhook subscription posts to a public HTTPS target URL each time message.received, conversation.opened, or conversation.closed fires. Deliveries are HMAC-signed, so the receiver can check they came from Myla. The same mechanism backs Myla's Zapier REST Hook triggers.

Call POST /api/v1/webhooks with event='conversation.closed' and targetUrl='https://hooks.example.com/myla', and store the returned id so DELETE /api/v1/webhooks/{id} can remove it later

Key Endpoints

10 endpoints — the myla developer api reads and updates the contacts and conversations in a myla brand workspace and registers webhooks for conversation events.

METHOD

PATH

DESCRIPTION

POST

/api/v1/contacts

Create or update a contact

GET

/api/v1/contacts

List contacts, filterable by email or phone

PATCH

/api/v1/contacts/{id}

Update a contact

POST

/api/v1/contacts/{id}/tags

Add tags to a contact

GET

/api/v1/conversations/{id}

Get a conversation with messages

POST

/api/v1/webhooks

Subscribe to an event

GET

/api/v1/me

Verify credentials

POST

/api/v1/contacts

Create or update a contact

GET

/api/v1/contacts

List contacts, filterable by email or phone

PATCH

/api/v1/contacts/{id}

Update a contact

POST

/api/v1/contacts/{id}/tags

Add tags to a contact

GET

/api/v1/conversations/{id}

Get a conversation with messages

POST

/api/v1/webhooks

Subscribe to an event

GET

/api/v1/me

Verify credentials

Why Jentic?

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

Setup

Wiring Myla by hand means creating a brand-scoped key in the dashboard, sending it as a bearer token, unwrapping the data envelope on every response, and backing off on 429s. Through Jentic you install once, import Myla from the API Directory, store the key once, and your agent calls it.

Permission scoping

Myla puts contact and conversation ids in the URL path, as in /api/v1/contacts/{id} and /api/v1/conversations/{id}, so a rule can hold your agent to the operations it needs and to specific records. You choose the operations it may call, so webhook registration or deletion is not included unless you add it.

Credential isolation

Your Myla 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 'upsert a contact' or 'read a conversation', and Jentic returns the matching Myla operation with its input schema so the agent calls the right endpoint without browsing the reference docs.

FAQs

Specific to using Myla Developer API through Jentic.

What authentication does the Myla Developer API use?

Per its OpenAPI spec, the Myla Developer API uses a bearer token: a brand-scoped API key sent as Authorization: Bearer. You create the key in the Myla dashboard under Settings, Integrations, Developer API, and each key works for a single brand workspace. GET /api/v1/me confirms a key is valid. Through Jentic, the key is stored once by your own Jentic One instance and injected at call time.

Does creating a contact in Myla create duplicates?

No. POST /api/v1/contacts upserts by phone or email, and at least one of the two is required. If an existing contact matches, it is updated; otherwise a new one is created. Use PATCH /api/v1/contacts/{id} when you already have the contact id.

Which webhook events does the Myla Developer API support?

POST /api/v1/webhooks takes an event and a targetUrl. The event enum is message.received, conversation.opened, and conversation.closed, and the target must be a public HTTPS URL. Deliveries are HMAC-signed. Remove a subscription with DELETE /api/v1/webhooks/{id}.

What are the rate limits for the Myla Developer API?

The spec says requests are rate limited per API key and that exceeding the limit returns HTTP 429, after which you retry after a short delay. It does not state the numeric limit; see https://api.myla.cx/openapi.json and the Myla dashboard documentation for current figures.

How do I tag a Myla contact through Jentic?

Install Jentic One with `curl -fsSL https://raw.githubusercontent.com/jentic/jentic-one/main/tools/install.sh | sh`, import the Myla Developer API from the API Directory, and store your brand API key once. Your agent searches for 'tag a contact in Myla', finds the contact with GET /api/v1/contacts filtered by email, then calls POST /api/v1/contacts/{id}/tags with tagIds. To run it on your own infrastructure, install Jentic One from its GitHub repo.

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

Yes. For a read-only digest agent, write a rule that allows GET /api/v1/conversations and GET /api/v1/conversations/{id}, so it can read threads and messages but cannot edit contacts or register webhooks. A rule can also name a single conversation id in the path if the agent should only read one thread.

Myla Cx Myla Developer API

AI ReadinessFoundational (D-)40/100

See full scorecard

Official vendor OpenAPI document · agent-readyCRMContact Managementbearer10 EndpointsREST

For Agents

Upsert, update, and tag Myla contacts, read conversations with their messages, and subscribe to message and conversation events in one brand workspace.

Use for: Find the Myla contact with this email address, Add a new lead to Myla from a form submission, Tag a contact as a VIP customer, Move a contact to a new lifecycle stage

Not supported: Does not send outbound messages, reply to conversations, or manage tags and lifecycle stage definitions. Use for Myla contact records, conversation reads, and event webhooks only.

The Myla Developer API reads and updates the contacts and conversations in a Myla brand workspace and registers webhooks for conversation events. Contacts can be listed and filtered by email or phone, upserted by phone or email, patched with a lifecycle stage and custom fields, and tagged. Conversations come back with their channel, status, priority, and full message history. Webhook subscriptions fire HMAC-signed deliveries when a message is received or a conversation opens or closes.

Jentic One on Github View OpenAPI Document

Show dimension breakdown

Foundational Compliance

Base layer of spec validity and structural soundness.

Grade: B+Signals: 4

78%

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).

100%

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: FSignals: 4

16%

Description Coverage

Coverage of descriptions across API elements.

Error Standardization

Coverage of RFC 9457 Problem Details for error responses.

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: A+Signals: 1

94%

Complexity Comfort

Agent comfort level based on API operational and structural complexity.

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).

AI Discoverability

Findability, semantic richness, and reasoning readiness.

Grade: A-Signals: 1

71%

Descriptive Richness

Clarity and depth of descriptions across API elements.

Connect the Myla Developer API to your agent

Capabilities

Start building with Myla Developer API

Use Cases

Key Endpoints

Why Jentic?

Related APIs

FAQs

Myla Cx Myla Developer API

Jentic AI Readiness Score

Myla Developer 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