Install Jentic One Beta

Connect the Anjal API to your agent

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

Create an agent inbox with POST /v1/inboxes, idempotent on the requested username, with a strict flag that returns 409 instead of falling back to a numbered username

Send from an inbox with POST /v1/inboxes/{id}/send, passing an Idempotency-Key header so a retry never sends twice, plus labels and trackOpens

Reply, reply-all, or forward a received message by its messageId with POST /v1/inboxes/{id}/reply/{messageId} and its reply-all and forward siblings

Search mail across every inbox the key can see with GET /v1/messages/search by query, from, to, participant, direction, date range, or attachment filename

GET STARTED

Start building with Anjal API

Explore with Jentic One

View OpenAPI Document

Use Cases

Patterns agents use Anjal API for, with concrete tasks.

★ An inbox your agent owns, through Jentic

An agent that handles support or scheduling needs a real address it can send from and read. Through Jentic it finds the Anjal operations by intent, creates its inbox with POST /v1/inboxes and a username, sends with POST /v1/inboxes/{id}/send, and picks up replies with GET /v1/inboxes/{id}/threads or a message.received webhook. Sends to addresses that have never replied to the inbox are rejected unless verified is true.

Call POST /v1/inboxes with username 'scout' and displayName 'Scout', then POST /v1/inboxes/{id}/send with an Idempotency-Key header, to 'ops@example.com', subject 'Weekly report', and plainBody containing the report

Find the right message in one call

GET /v1/messages/search runs full-text search over subject, plain-text body, and participant addresses across every inbox the key can see, scoped automatically by key tier. Hits are lightweight: ids, participants, subject, receivedAt, hasAttachments, and a snippet of about 200 characters, never htmlBody, so an agent can scan results cheaply and then fetch the winning thread with GET /v1/inboxes/{id}/threads/{threadId}.

Call GET /v1/messages/search with query 'invoice', from 'billing@acme.com', and hasAttachment true, then call GET /v1/inboxes/{id}/threads/{threadId} for the newest hit

Sending from your own domain

Agents often need to send as your brand rather than as anjal.app. POST /v1/domains returns the DNS records to set at your registrar and starts the domain in pending; if the domain already receives mail at Google Workspace or Microsoft 365, pass sharedWith to keep that provider or replaceMailProvider to move mail over, otherwise the call returns 422 DOMAIN_HAS_MAIL_PROVIDER. GET /v1/domains/{domain}/verify confirms it and GET /v1/domains/{domain}/zone-file exports a BIND zone file.

Call POST /v1/domains with domain 'mail.example.com' and sharedWith 'google', report the returned DNS records, then call GET /v1/domains/mail.example.com/verify after they are set

Multi-step outreach cadences

Outbound sequences run on Anjal's side as cadences: an ordered list of steps such as a LinkedIn invite, a wait, a DM, and an email, with branching on events like an accepted invite or a reply. POST /cadences sets businessHoursOnly, exitOnReply, exitOnUnsubscribe, and a dailySendCap from 1 to 1000, and POST /cadences/{id}/enrollments enrolls each lead by leadExternalId.

Call POST /cadences with name 'Q4 founders', dailySendCap 40, and exitOnReply true, then POST /cadences/{id}/enrollments with leadExternalId 'crm-1042', leadName 'Dana Lee', and leadEmail 'dana@example.com'

Key Endpoints

112 endpoints — the anjal api gives ai agents their own email inboxes: it creates inboxes on anjal.

METHOD

PATH

DESCRIPTION

POST

/v1/inboxes

Create an inbox

POST

/v1/inboxes/{id}/send

Send a message

POST

/v1/inboxes/{id}/reply/{messageId}

Reply to a message

GET

/v1/inboxes/{id}/threads

List threads

GET

/v1/messages/search

Search messages across inboxes

POST

/v1/inboxes/{id}/drafts

Create a draft, optionally scheduled

POST

/v1/domains

POST

/v1/webhooks

Create a webhook

POST

/v1/inboxes

Create an inbox

POST

/v1/inboxes/{id}/send

Send a message

POST

/v1/inboxes/{id}/reply/{messageId}

Reply to a message

GET

/v1/inboxes/{id}/threads

List threads

GET

/v1/messages/search

Search messages across inboxes

POST

/v1/inboxes/{id}/drafts

Create a draft, optionally scheduled

POST

/v1/domains

POST

/v1/webhooks

Create a webhook

Why Jentic?

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

Setup

Wiring Anjal by hand means picking the right key tier among sa_, tk_, wk_, ak_, and mam_ for each endpoint, sending it in X-API-Key, and generating an Idempotency-Key for every send. Through Jentic you install once, import the Anjal API from the API Directory, store the key once, and your agent calls it.

Permission scoping

Anjal puts the inbox id in the URL path (/v1/inboxes/{id}/...), so a rule can pin your agent to one inbox and the operations you pick. You choose the operations it may call, so ones like deleting threads, registering domains, or LinkedIn outreach are not included unless you add them.

Credential isolation

Your Anjal 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 'send an email from my agent inbox' or 'search my email for an invoice', and Jentic returns the matching Anjal operation with its input schema so the agent calls the right endpoint without browsing the reference docs.

FAQs

Specific to using Anjal API through Jentic.

Is there an Anjal MCP server?

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

What authentication does the Anjal API use?

Per its OpenAPI spec, the Anjal API takes an API key in the X-API-Key header. Keys come in tiers with the prefixes sa_, tk_, wk_, ak_, and mam_, and scope is enforced per endpoint; for example, creating an inbox needs a tenant master or workspace master key. Two operations use a one-time t query token instead of a key: GET /downloads/{downloadId} and PUT /uploads/{uploadId}. Through Jentic, the key is stored encrypted by your own Jentic One instance and injected at call time.

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

Yes. For example, write a rule that allows only GET /v1/inboxes/{id}/threads, GET /v1/inboxes/{id}/threads/{threadId}, and POST /v1/inboxes/{id}/reply/{messageId} for one inbox id. Your agent can then read that inbox and answer mail in it, but it cannot send fresh outbound mail, delete threads, touch domains, or run LinkedIn actions, and every call it makes is logged.

What are the rate limits for the Anjal API?

The OpenAPI spec does not state a general request rate limit. It does describe per-session quotas for the LinkedIn operations, reported by GET /linkedin/sessions/utilization, and a dailySendCap of 1 to 1000 per cadence. Check https://anjal.app for current account limits.

How do I send an email from my agent's inbox through Jentic?

Search Jentic for 'send an email from my agent inbox', load the sendMessage operation, and call POST /v1/inboxes/{id}/send with to and subject, a plainBody or htmlBody, and an Idempotency-Key header. To run it on your own infrastructure, install Jentic One from its GitHub repo.

Why was my Anjal send rejected?

As a deliverability safeguard, sends to an address that has never replied to the inbox are rejected unless you pass verified: true. Check recipients first with POST /v1/verify-email, which MX-probes the domain, then send with verified set to true.

Can I schedule an email with the Anjal API?

Yes. Create a draft with POST /v1/inboxes/{id}/drafts and set sendAt, and Anjal sends it at that time with no cron on your side. A draft.send_failed webhook event reports a scheduled send that did not go out.

Myagentmail Anjal API

AI ReadinessFoundational (C)56/100

See full scorecard

Official vendor OpenAPI document · agent-readyCommunicationsEmail DeliveryapiKey112 EndpointsREST

For Agents

Give your agent its own email inbox: send, reply, forward, and schedule mail, search and label threads, handle attachments, register custom domains, subscribe to mail events, and run LinkedIn and email outreach cadences.

Use for: I need my agent to have its own email address, Send a follow-up email from the sales inbox without sending it twice on retry, Search all inboxes for messages from acme.com with an invoice attached, Reply to the last message in this thread

Not supported: Does not read or send from a person's existing Gmail or Outlook mailbox, run newsletter campaigns with templates, or send SMS. Use for agent-owned email inboxes, their mail and domains, and Anjal's outreach cadences only.

The Anjal API gives AI agents their own email inboxes: it creates inboxes on anjal.app or a custom domain, sends, replies, forwards, and schedules mail from them, and reads, labels, and searches what comes back. Mail is organized into threads and messages with attachments, raw .eml download, drafts that send at a set sendAt time, and contact lists per inbox, and a cross-inbox full-text search returns compact hits with a short snippet instead of whole bodies. Custom domains come with the DNS records to set, a verify call, and a BIND zone file export, and webhooks cover events such as message.received, message.bounced, and message.opened. The same API also runs LinkedIn sessions, intent signals, and multi-step outreach cadences that mix LinkedIn and email steps, all organized by tenant and workspace with tiered API keys.

Jentic One on Github View OpenAPI Document

Show dimension breakdown

Foundational Compliance

Base layer of spec validity and structural soundness.

Grade: DSignals: 4

51%

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).

30%

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: C+Signals: 4

Example Density

How richly the API is illustrated with examples.

100%

Example Validity

Percentage of examples that conform to their schemas.

36%

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: D+Signals: 4

32%

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.

59%

Summary Coverage

Coverage of summaries across operations/tags/info.

Agent Usability

Functional utility, complexity comfort, and AI orchestration readiness.

Grade: ASignals: 1

81%

Complexity Comfort

Agent comfort level based on API operational and structural complexity.

Security

Trust, risk posture, and security compliance.

Grade: C-Signals: 1

50%

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

79%

Descriptive Richness

Clarity and depth of descriptions across API elements.

Connect the Anjal API to your agent

Capabilities

Start building with Anjal API

Use Cases

Key Endpoints

Why Jentic?

Related APIs

FAQs

Myagentmail Anjal API

Jentic AI Readiness Score

Anjal 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