Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Hive Publish 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%2Fhivepublish.com%2Fhivepublish" | 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%2Fhivepublish.com%2Fhivepublish" | 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 Hive Publish Developer API.
Draft, schedule, and publish posts across the connected social networks
Send direct messages and reply to comments from the Community inbox
Read, assign, and resolve inbox conversations with tags and notes
Create contacts and set their tags and stored field values
Build comment and DM automations and set them live or on pause
GET STARTED
Read cross-network analytics summaries and saved reports
Register signed webhook subscriptions for workspace events
Patterns agents use Hive Publish Developer API for, with concrete tasks.
★ Scheduled Cross-Network Publishing
Queue content once and let Hive Publish deliver it to each connected network at the chosen time, instead of posting to Instagram, Telegram, and the rest separately. The API creates an editable draft with the composer options, then schedules it for a future slot in the workspace queue. Social teams use this to run a consistent posting calendar across a dozen networks from one place.
POST /api/v1/tools/create_draft with the post content and target accounts, then POST /api/v1/tools/schedule_post to queue it for a future time.
Unified Social Inbox Triage
Work every incoming DM and comment from one inbox and close them with a recorded resolution reason, rather than switching between native apps. The API lists redacted inbox threads, assigns them to teammates, and resolves them with a reason from the workspace's configured list. Support and community teams use this to keep response times low across channels.
POST /api/v1/tools/read_inbox_threads to list open conversations, then POST /api/v1/tools/resolve_thread with a resolution reason for each handled thread.
Contact Tagging and Segmentation
Keep the contact records Hive Publish builds from DM automation organized so segments and reporting stay accurate. The API finds a contact by email, phone, or a field value and lets you add tags or set stored field values by id or name. Marketing teams use this to label contacts for later broadcasts and sequences.
Call GET /api/v1/contacts to find a contact by email, then POST /api/v1/contacts/{id}/tags to add a tag by name.
Agent-Managed Social Workflow
An AI agent prepares and queues social content for a workspace without a bespoke integration against each network. Through Jentic the agent discovers the draft and schedule operations, loads their schemas, and chains them, then reports the resulting queue entry. This lets a marketing assistant turn a brief into scheduled posts directly.
Search Jentic for 'schedule a social post', draft with POST /api/v1/tools/create_draft, schedule with POST /api/v1/tools/schedule_post, and return the queued entry.
258 endpoints — the hive publish developer api automates organic social messaging and publishing: it drafts and schedules posts to twelve networks, answers direct messages on instagram, messenger, whatsapp, and telegram from one inbox, runs comment and dm automations, and reports on performance.
METHOD
PATH
DESCRIPTION
/api/v1/tools/create_draft
Create an editable post draft
/api/v1/tools/schedule_post
Queue a post for a future time
/api/v1/tools/send_direct_message
Send a direct message from a connected account
/api/v1/tools/read_inbox_threads
Read redacted inbox conversation threads
/api/v1/tools/read_analytics_summary
Read the latest organic metrics per account
/api/v1/contacts
Find contacts by email, phone, or field value
/api/v1/contacts/{id}/tags
Add a tag to a contact by id or name
/api/v1/webhooks
Create a signed webhook subscription
/api/v1/tools/create_draft
Create an editable post draft
/api/v1/tools/schedule_post
Queue a post for a future time
/api/v1/tools/send_direct_message
Send a direct message from a connected account
/api/v1/tools/read_inbox_threads
Read redacted inbox conversation threads
/api/v1/tools/read_analytics_summary
Read the latest organic metrics per account
/api/v1/contacts
Find contacts by email, phone, or field value
/api/v1/contacts/{id}/tags
Add a tag to a contact by id or name
What agents get from Jentic-routed access to this vendor.
Setup
Wiring Hive Publish by hand means handling its bearer auth and picking the right operations out of a very large surface for drafting, scheduling, inbox, and automations. Through Jentic you install once, import Hive Publish from the API Directory, store the token once, and your agent calls the operation it needs.
Permission scoping
Hive Publish carries post content, channels, and message targets inside the request body, so a rule bounds which operations your agent may call rather than which account or channel. You can allow only read and draft operations and withhold the ones that publish, send messages, or set automations live.
Credential isolation
Your Hive Publish 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 'schedule a social post' or 'read the social inbox', and Jentic returns the matching Hive Publish operation with its input schema so the agent calls the right endpoint without browsing hundreds of tools.
Alternatives and complements available in the Jentic catalogue.
Specific to using Hive Publish Developer API through Jentic.
Is there a Hive Publish MCP server?
Yes. Hive Publish offers an MCP server that exposes its organic-social tools. You can also connect Hive Publish directly through Jentic: your agent gets the full 258-endpoint surface without loading another server's tool definitions into its context, your bearer token is injected at call time by your self-hosted instance instead of living in a config file, and your own rules decide which operations the agent may call.
What authentication does the Hive Publish Developer API use?
The Hive Publish Developer API authenticates with a bearer token in the Authorization header, per its OpenAPI spec. Through Jentic the token is stored encrypted by your own Jentic One instance and injected at call time, so it never enters the agent's prompt, logs, or context.
Can I manage the social inbox with the Hive Publish Developer API?
Yes. POST /api/v1/tools/read_inbox_threads returns redacted conversation threads, POST /api/v1/tools/assign_thread hands one to a teammate, and POST /api/v1/tools/resolve_thread closes it with a resolution reason. Direct messages are sent with POST /api/v1/tools/send_direct_message on a connected account.
What are the rate limits for the Hive Publish Developer API?
The OpenAPI spec does not specify request rate limits; Hive Publish meters usage per connected account on its pricing tiers. Check the Hive Publish documentation at https://hivepublish.com for the current limits that apply to your plan.
How do I schedule a social post through Jentic?
Search Jentic with the query 'schedule a social post', load the schema for POST /api/v1/tools/create_draft, create the draft, then execute POST /api/v1/tools/schedule_post to queue it. 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 Hive Publish Developer API?
Yes. Write a rule that allows only the read and draft operations, such as reading the inbox and creating a draft, so the agent can prepare content and report back without publishing or messaging anyone, and every call it makes is logged. Granting the schedule, send, or automation operations is an explicit choice you add.
For Agents
Draft and schedule social posts, answer DMs and comments from one inbox, run automations, manage contacts, and read cross-network analytics for a workspace.
Use for: Schedule a post to go out across my connected networks, Send a direct message to a contact on their channel, Show me the open conversations in the inbox, Create a new content draft in the workspace
Not supported: Does not run paid ad campaigns, process payments, or host your website. Use for organic social publishing, inbox management, automations, and reporting only.
The Hive Publish Developer API automates organic social messaging and publishing: it drafts and schedules posts to twelve networks, answers direct messages on Instagram, Messenger, WhatsApp, and Telegram from one inbox, runs comment and DM automations, and reports on performance. Hundreds of operations span content, inbox, contacts, automations, listening, and reporting for a single workspace. Use it to run an organic social presence from an agent or app instead of logging into each network by hand.
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.
/api/v1/webhooks
Create a signed webhook subscription
Base layer of spec validity and structural soundness.
Aggregated quality score from linter diagnostics, weighted by severity.
Percentage of `$ref` references that resolve successfully.
Checks whether the API description parses successfully and conforms to its declared specification (e.g., OpenAPI).
Structural correctness score based on schema issues using logarithmic dampening.
Clarity, completeness, and ingestion readiness for developers and tooling.
How richly the API is illustrated with examples.
Percentage of examples that conform to their schemas.
Percentage of operations with complete response definitions (success, client error, server error).
Health of API ingestion, bundling, and resolution within Jentic pipelines.
Semantic breadth, depth, and agent comprehension for AI systems.
Coverage of descriptions across API elements.
Coverage of RFC 9457 Problem Details for error responses.
Coverage, uniqueness, and casing consistency of operationIds for AI inference.
Coverage of summaries across operations/tags/info.
Functional utility, complexity comfort, and AI orchestration readiness.
Agent comfort level based on API operational and structural complexity.
Trust, risk posture, and security compliance.
Average quality of security schemes based on authentication method strength (weakest link for OAuth2).
Findability, semantic richness, and reasoning readiness.
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>