Chatwoot

Name: Chatwoot API
Brand: Chatwoot
Availability: InStock

★ Only Publicly Available OpenAPI DocumentCRMCustomer SupportapiKey144 EndpointsREST

For Agents

Manage Chatwoot conversations, contacts, agents, inboxes, and automation rules through a single API so an agent can triage support tickets, send replies, label conversations, and pull reports.

Quickstart

Get started with Chatwoot in minutes using your preferred integration method.

# Add to your MCP client config (Claude Desktop, Cursor, Windsurf)
{
  "jentic": {
    "url": "https://api.jentic.com/mcp",
    "auth": "oauth"
  }
}

# Then ask your agent:
"send a message in a chatwoot conversation"

# → Jentic returns the GET /events tool with parameter schema, agent executes.

Capabilities

What an agent can do with Chatwoot API.

Create, list, and update contacts and merge duplicates across inboxes

Read and reply to conversations across email, web, and messaging channels

Send outbound messages and attach private notes for agent collaboration

Provision inboxes, agents, teams, and labels for new accounts

Configure automation rules that route conversations and apply labels

GET STARTED

Start building with Chatwoot API

Explore with Jentic

View OpenAPI Document

Jentic publishes the only available OpenAPI document for Chatwoot, keeping it validated and agent-ready.

Jentic publishes the only available OpenAPI specification for Chatwoot, keeping it validated and agent-ready. Chatwoot is an open-source customer engagement platform that unifies conversations from email, web chat, social channels, and messaging apps into a shared inbox. Its API exposes deep control over accounts, agents, contacts, conversations, messages, inboxes, teams, labels, automation rules, and reporting — 144 endpoints across more than 30 resource groups. It supports three distinct API token types (user, agent bot, and platform app) so you can build everything from in-app integrations to multi-tenant provisioning.

Use Cases

Patterns agents use Chatwoot API for, with concrete tasks.

★ Automated Conversation Triage

Route incoming customer conversations to the right team based on content, channel, or contact attributes. Use the conversations and labels endpoints to inspect new threads, apply tags, and assign them to agents or teams. Pair with automation rules so the platform handles routine cases without human intervention.

Fetch all unassigned conversations in account 12, label any matching 'billing' as 'finance-team', and assign them to team_id 4.

Unified Contact Management

Keep customer profiles in sync between Chatwoot and your CRM. Create, search, and update contacts via the Contacts API; attach custom attributes for product tier or lifecycle stage; and merge duplicates that arrive through different channels. Useful for support teams running on multiple sources of truth.

Create a contact for 'jane@example.com' with custom attribute plan='enterprise' in account 12 and confirm the contact id is returned.

Support Reporting and Analytics

Pull operational metrics — conversation volume, response times, agent workload, CSAT — into a BI tool or weekly stand-up summary. The Reports endpoints aggregate by team, agent, label, or inbox, so you can compare performance across channels and time windows without exporting data manually.

Pull the agents report for account 12 between 2026-06-01 and 2026-06-07 and summarise the top three agents by conversations resolved.

AI Agent for Customer Support

An autonomous agent watches Chatwoot for new conversations, drafts contextual replies based on the contact's history and product, posts them as private notes for human approval, and labels the thread. Through Jentic, the agent calls the Conversations and Messages APIs without ever holding the api_access_token in its prompt.

Through Jentic, search 'reply to a conversation', load the schema, and post a private note suggesting a refund for conversation_id 9876.

Key Endpoints

144 endpoints — jentic publishes the only available openapi specification for chatwoot, keeping it validated and agent-ready.

METHOD

PATH

DESCRIPTION

GET

/api/v1/accounts/{account_id}/conversations

List conversations in an account

POST

/api/v1/accounts/{account_id}/conversations/{conversation_id}/messages

Send a message in a conversation

POST

/api/v1/accounts/{account_id}/contacts

Create a contact

GET

/api/v1/accounts/{account_id}/reports

Retrieve reports for an account

POST

/api/v1/accounts/{account_id}/automation_rules

Create an automation rule

POST

/api/v1/accounts/{account_id}/agent_bots

Create an agent bot

GET

/api/v1/accounts/{account_id}/conversations

List conversations in an account

POST

/api/v1/accounts/{account_id}/conversations/{conversation_id}/messages

Send a message in a conversation

POST

/api/v1/accounts/{account_id}/contacts

Create a contact

GET

/api/v1/accounts/{account_id}/reports

Retrieve reports for an account

POST

/api/v1/accounts/{account_id}/automation_rules

Create an automation rule

Why though Jentic?

Three things that make agents converge on Jentic-routed access.

Credential isolation

Chatwoot api_access_token values (user, agent bot, or platform app) are stored encrypted in the Jentic MAXsystem vault. Agents receive scoped access at execution time — the raw token never enters the agent's prompt.

Intent-based discovery

Agents search by intent (e.g. 'reply to a conversation' or 'create a contact') and Jentic returns the matching Chatwoot operation with its input schema, so the agent picks the right endpoint among 144 without browsing docs.

Time to first call

Direct Chatwoot integration: 2-4 days to learn the three token types, conversation lifecycle, and webhook handling. Through Jentic: under 1 hour — search, load schema, execute.

Related APIs

Alternatives and complements available in the Jentic catalogue.

Complementary

Chatsistant API

AI chatbot platform that can pre-handle conversations before they hit a Chatwoot agent

Choose Chatsistant when you want an AI chatbot to deflect simple queries before escalating to a Chatwoot human agent

Alternative

Chatwork API

Team chat platform with a different focus — internal collaboration rather than customer support

Choose Chatwork when the need is internal team messaging, not external customer conversations

Complementary

Checkly API

Synthetic monitoring you can use to verify Chatwoot endpoints stay available

Choose Checkly to set up uptime monitoring for a self-hosted Chatwoot deployment

FAQs

Specific to using Chatwoot API through Jentic.

Why is there no official OpenAPI spec for Chatwoot?

Chatwoot does not publish an OpenAPI specification on its own site. Jentic generates and maintains this spec so that AI agents and developers can call Chatwoot via structured tooling. It is validated against the live API and kept up to date. Get started at https://app.jentic.com/sign-up.

What authentication does the Chatwoot API use?

Chatwoot uses an API key passed in the api_access_token header. Three token types are defined: user (full user permissions), agent bot (limited bot integrations), and platform app (provisioning accounts and users). Through Jentic, the right token is stored encrypted in the MAXsystem vault and injected at execution time without entering the agent's context.

Can I send replies to conversations with the Chatwoot API?

Yes. POST /api/v1/accounts/{account_id}/conversations/{conversation_id}/messages sends a reply or private note in a specific conversation. The endpoint accepts the message content, message type (incoming, outgoing, or private), and optional attachments.

How do I create a contact via the Chatwoot API?

Use POST /api/v1/accounts/{account_id}/contacts with name, email, phone, and any custom attributes. The endpoint returns the created contact id, which you can then attach to inboxes or conversations.

What are the rate limits for the Chatwoot API?

The OpenAPI specification does not declare formal rate limits. Self-hosted Chatwoot instances are bound by the host's configuration, and the cloud version applies plan-based throttling — check your dashboard or the Chatwoot docs for current limits and plan for retry-with-backoff on 429 responses.

How do I post a reply to a Chatwoot conversation through Jentic?

Install the SDK with `pip install jentic`, then run Jentic.search('send a message in a conversation'), load the schema for /api/v1/accounts/{account_id}/conversations/{conversation_id}/messages, and execute with the conversation_id and message content. Jentic injects the api_access_token automatically.