canonical: https://jentic.com/apis/frontapp.com/front

# Frontapp Front Core API

The Front Core API drives the Front shared inbox, where teams handle customer conversations across email and other channels from one place. It lists, searches, and updates conversations, assigns them, sends message replies and drafts, and adds internal comments and mentions. It also manages contacts, contact groups and lists, inboxes, channels, tags, knowledge base articles and categories, and analytics reports. Requests authenticate with a bearer token.

## For AI agents

Triage and reply to customer conversations in the Front shared inbox, assign and tag them, manage contacts and inboxes, and author knowledge base content. Authenticated with a bearer token.

## Scope

Does not handle billing, telephony dialing, or marketing campaign sending. Use for the Front shared inbox: conversations, contacts, inboxes, and knowledge base only.

## Capabilities

- List, search, and update conversations and set their assignee
- Send message replies and create drafts within a conversation
- Add internal comments and mentions to a conversation
- Tag conversations and list the inboxes and channels they belong to
- Manage contacts along with contact groups and contact lists
- Author and localise knowledge base articles and categories
- Create analytics reports and exports over conversation activity

## Use cases

### Agent-Driven Conversation Triage

An AI agent connected through Jentic can triage the Front shared inbox without a developer wiring the bearer token and conversation paths. The agent lists an inbox's conversations, tags and assigns each one to the right teammate, and drafts a reply for review. Jentic injects the token at call time so the credential never reaches the agent.

Example prompt: List the conversations in an inbox, tag each by topic, assign it to a teammate, and draft a reply

### Automated Reply Drafting

Support teams can have an agent draft responses that a human approves before sending. The agent reads a conversation's messages, creates a draft reply in the conversation, and leaves an internal comment explaining its reasoning. This keeps a human in the loop while removing the blank-page step.

Example prompt: Read a conversation's messages, create a draft reply, and add an internal comment summarising the suggested answer

### Knowledge Base Maintenance

Teams keeping self-service content current can update articles across locales programmatically. The agent fetches an article's content, updates it in the default locale, and syncs the change into other locales. This keeps the knowledge base aligned with the latest answers.

Example prompt: Fetch a knowledge base article's content, update it in the default locale, then update the same article in another locale

## Key endpoints

| Method | Path | Description |
| --- | --- | --- |
| GET | `/conversations` | List conversations |
| GET | `/conversations/{conversation_id}` | Get a conversation |
| POST | `/conversations/{conversation_id}/messages` | Send a message reply |
| POST | `/conversations/{conversation_id}/comments` | Add an internal comment |
| POST | `/conversations/{conversation_id}/tags` | Add a tag to a conversation |
| PUT | `/conversations/{conversation_id}/assignee` | Set a conversation's assignee |
| GET | `/contacts` | List contacts |

## Key resources

- **Conversations** — List, search, update, assign, tag, comment on, and reply within conversations
- **Messages & Drafts** — Create message replies and manage drafts in channels and conversations
- **Contacts** — Create and manage contacts, handles, notes, groups, and lists
- **Inboxes & Channels** — List inboxes and channels, manage access, and import messages
- **Knowledge Base** — Read and update knowledge base articles and categories across locales
- **Analytics** — Create analytics reports and exports over activity

## AI readiness

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.

- **Score:** 54 / 100
- **Maturity:** Foundational
- **Dimensions:**
  - Foundational Compliance: 45 / 100
  - Developer Experience & Jentic Compatibility: 61 / 100
  - AI-Readiness & Agent Experience: 56 / 100
  - Agent Usability: 43 / 100
  - Security: 75 / 100
  - AI Discoverability: 66 / 100
- **View full report:** https://jentic.com/apis/frontapp.com/front/scorecard
- **How the score is calculated:** https://docs.jentic.com/reference/api-readiness-framework/overview/
- **More about the dimensions:** https://docs.jentic.com/reference/api-readiness-framework/specification/#dimensional-model-overview

### Score it yourself

Every API in the directory is allowlisted, so you can re-score it with no key required.

- **Score your own API:** https://jentic.com/scorecard.md
- **Scoring CLI agent skill:** https://github.com/jentic/jentic-api-scorecard/blob/main/skills/jentic-api-scorecard/SKILL.md

```sh
npx @jentic/api-scorecard-cli score <openapi-url>
```

## Why Jentic

- **Setup:** Wiring Front by hand means managing a bearer token, threading conversation, inbox, and contact ids through nested paths, and handling pagination across a large surface yourself. Through Jentic you install once, import Front from the API Directory, store the token once, and your agent calls it.
- **Permission scoping:** Front puts the inbox and conversation ids in the URL path, for example `/inboxes/{inbox_id}` and `/conversations/{conversation_id}`, so a rule can pin your agent to one inbox or conversation. You choose which operations it may call, so destructive ones like deleting a conversation or an account are not included unless you add them.
- **Credential handling:** Your Front 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.
- **Discovery method:** Agents search Jentic by intent such as 'reply to a conversation' or 'assign a conversation', and Jentic returns the matching Front operation with its input schema so the agent calls the right endpoint without browsing the reference docs.

## Related APIs

- **Missive** — Team inbox for shared email, chat, and conversations
- **Help Scout** — Shared inbox and help desk with knowledge base
- **Zendesk** — Ticketing-first customer support platform
- **Salesforce** — CRM for the accounts and contacts behind conversations

## FAQ

### What authentication does the Front Core API use?

Per its OpenAPI spec, the Front Core API uses a bearer token sent on each request. Through Jentic the token is stored encrypted by your own instance and injected at call time, so it never reaches the agent.

### Is there a Front MCP server?

You don't need an MCP server to give your agent Front. Jentic connects it directly from the API Directory: import it, store your credential once, and your agent calls operations like replying to a conversation or assigning it on demand, without loading another server's tool definitions into its context.

### Can I limit what my agent is allowed to do with Front?

Yes. Front puts the inbox and conversation ids in the URL path, so a rule can pin your agent to one inbox and allow only reply, tag, and assign operations, so it cannot delete a conversation or an account unless you add those operations, and every call it makes is logged. This matches a triage bot that routes and drafts without destructive power.

### Can I draft and send replies with the Front Core API?

Yes. Read a conversation's messages, then create a draft reply for a human to approve or send a message reply directly in the conversation. You can also add an internal comment that stays private to the team.

### What are the rate limits for the Front Core API?

The OpenAPI spec does not specify rate limits. Check the Front developer documentation at https://dev.frontapp.com for current rate limits and tier-based ceilings before running bulk conversation jobs.

### How do I triage conversations with the Front Core API through Jentic?

Search Jentic for 'triage a shared inbox', which returns the conversation list, tag, and assignee operations with their input schemas. The agent lists an inbox's conversations, tags and assigns each, and drafts a reply, with your stored token injected at call time. To run it on your own infrastructure, install Jentic One from its GitHub repo.