Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Missive 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%2Fmissiveapp.com%2Fmissive" | shStep 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%2Fmissiveapp.com%2Fmissive" | 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.
What an agent can do with Missive API.
Create a new email draft in a shared inbox via POST /drafts with recipients, subject, and body
Create or update a contact record using POST /contacts so it appears in the team's address book
Retrieve a single conversation by id via GET /conversations/{id} including its messages and metadata
List conversations with GET /conversations to surface threads matching the team's filters
Patterns agents use Missive API for, with concrete tasks.
GET STARTED
★ AI-Drafted Replies for Human Review
An agent reads incoming customer messages from a shared inbox, drafts a reply, and posts it as a Missive draft via POST /drafts so a human teammate can review, edit, and send. Captures the speed of automation without sending unreviewed copy to customers.
POST /drafts to the shared inbox with the recipient, subject, and AI-drafted body, leaving the message unsent for human review
Contact Sync from External Systems
Push contact records from a CRM or signup form into Missive via POST /contacts so teammates see context the moment a thread arrives. The endpoint handles both creation and updates so nightly sync jobs stay simple.
POST /contacts with email, name, and phone for every new lead added in the CRM in the last 24 hours
Conversation Export for Analysis
Pull conversation threads with GET /conversations/{id} into a data warehouse or analytics tool to analyse response times, sentiment, or topic mix. Use GET /conversations to discover ids matching the desired filter, then fetch each thread's full message history.
GET /conversations to list ids, then GET /conversations/{id} for each to extract messages into a warehouse table
Agent-Driven Inbox Workflows
An AI agent uses Jentic to orchestrate Missive: read inbound threads, draft suggested replies, sync contacts. The bearer token sits in your Jentic One instance, scoped to the team's account, so the agent never holds the secret directly.
Search Jentic for 'create a draft email', load the Missive draft schema, and post drafts for every unanswered customer thread from today
4 endpoints — jentic publishes the only available openapi specification for missive api, keeping it validated and agent-ready.
METHOD
PATH
DESCRIPTION
/drafts
Create an email draft
/contacts
Create or sync a contact
/conversations
List conversations
/conversations/{id}
Get a conversation by id
/drafts
Create an email draft
/contacts
Create or sync a contact
/conversations
List conversations
/conversations/{id}
Get a conversation by id
What agents get from Jentic-routed access to this vendor.
Setup
Wiring Missive by hand means handling its bearer auth against public.missiveapp.com and coding the draft, contact, and conversation calls yourself. Through Jentic you install once, import Missive from the API Directory, store the token once, and your agent calls it.
Permission scoping
Missive puts the conversation id in the URL path (/conversations/{id}) for reads, while drafts and contacts carry their content in the request body, so scope the agent to the operations it needs, such as reading a conversation or creating a draft. You choose which operations are allowed, so creating a contact is only included if you add it.
Credential isolation
Your Missive bearer token 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 draft email' or 'read a conversation', and Jentic returns the matching Missive operation with its input schema so the agent calls the right endpoint without a separate Missive docs lookup.
Alternatives and complements available in the Jentic catalogue.
Specific to using Missive API through Jentic.
Why is there no official OpenAPI spec for Missive API?
Missive does not publish an OpenAPI specification. Jentic generates and maintains this spec so that AI agents and developers can call Missive API via structured tooling. It is validated against the live API and kept up to date. Get started with Jentic One, the self-hosted execution layer.
What authentication does the Missive API use?
Missive uses HTTP bearer token authentication. The token is sent in the Authorization header as `Bearer <token>` and can be issued from the Missive integrations settings. Jentic stores the token in its vault and injects it per call.
Can I create a draft email with the Missive API?
Yes. POST /drafts creates an unsent draft in a shared inbox. Provide the recipients, subject, and body; teammates will see the draft alongside other inbox items and can edit or send it.
How do I retrieve the full message history for a conversation?
Call GET /conversations/{id} with the conversation id. The response includes the conversation metadata and the ordered list of messages on the thread, including authors and timestamps.
How do I draft customer replies through Jentic?
Run `pip install jentic`, search Jentic for 'create a draft email', and Jentic returns the Missive POST /drafts operation. Provide the inbox, recipients, subject, and AI-generated body, then execute. The draft appears in Missive for human review.
Can I limit what my agent is allowed to do with the Missive API?
Yes. Because you run Jentic One yourself, your own rules decide which Missive operations the agent may call and which bearer token it uses. You can allow only reads, such as GET /conversations and GET /conversations/{id}, or add write operations like POST /drafts and POST /contacts one at a time, so creating a contact is available only if you include it. The token stays in your own instance and is injected at execution, so the agent never handles the secret directly.
Know of an official OpenAPI document? Contribute it →
For Agents
Create email drafts in a shared Missive inbox, sync contacts, and read conversation threads through the public Missive API.
Use for: Create a new draft reply in the support inbox, Sync a contact captured from the website into Missive, Retrieve conversation 12345 and its full message history, List the most recent conversations in the sales inbox
Not supported: Does not handle outbound SMS, calendar scheduling, or full ticketing workflows - use for shared inbox drafts, contacts, and conversation reads only.
Jentic publishes the only available OpenAPI specification for Missive API, keeping it validated and agent-ready. Missive is a team inbox and collaboration platform for email, SMS, and chat. The public API exposes endpoints to create draft emails, sync contacts, and read shared conversations across the team. Useful when an automation needs to draft outreach in Missive for human review or pull conversation threads into other tools.