Chatway Live Chat

Servidor MCP remoto para o chat ao vivo e suporte ao cliente do Chatway. Leia conversas, responda, resolva e atribua chats por meio de assistentes de IA. Autenticação OAuth, permissões limitadas e um plano gratuito.

Servidor MCP hospedado

npx add-mcp 'https://mcp.chatway.app/mcp'

Instala no Claude Code, Codex, Cursor e outros

Documentação

MCP overview

The Chatway MCP server lets an AI assistant — Claude, ChatGPT, Cursor, Codex, Grok, Muse, or anything else that speaks the Model Context Protocol — work inside your Chatway workspace using plain language.

MCP is a standard way for AI assistants to use tools provided by another service. Chatway supplies the inbox tools; your chosen assistant uses them to carry out your request. For example, it can find an unresolved conversation, read its messages, and prepare a reply. Reading needs read permissions; sending the reply needs send_replies. Connecting MCP alone does not create an automatic customer-reply workflow.

Connect Chatway to an AI assistant

Using ChatGPT or Codex? Install the official Chatway plugin and connect your Chatway account. No server URL is needed. For other assistants:

  1. Copy the MCP server URL:
https://mcp.chatway.app/mcp
  1. Add it as a remote MCP server in Claude, Cursor, Gemini, or another MCP client.
  2. Sign in to Chatway and choose the widgets, channels, and permissions the assistant can access.

That's it — no API key to paste. Client-specific steps are on Connect clients.

Test your connection by asking your assistant:

List my 5 most recent Chatway conversations.

MCP, webhooks, or the REST API?

Chatway offers three ways to connect an external system, and they solve different problems.

MCPWebhooksREST API
DirectionYour assistant → ChatwayChatway → your serverYour code → Chatway
What starts itYou ask your assistantA visitor does somethingYour code decides
What decides the outcomeThe modelYour codeYour code
Do you write code?NoYesYes
AuthOAuthSigned secretX-API-KEY
Set up inYour MCP clientSettings → Developer Tools → WebhooksSettings → Developer Tools → API Keys

Choose MCP when a person wants to work through an assistant on demand — triaging a queue, summarising a thread, drafting a reply. There is nothing to build, and the model decides which tools to call, which is exactly why it suits open-ended work and not fixed rules.

Choose webhooks when something in Chatway should trigger your system in real time, most often so an agent can answer visitors automatically the moment they write in.

Choose the REST API when your application needs to make specific requests to Chatway, such as syncing contacts or sending a reply. Your code controls when requests run and which inputs they use. You can also call the REST API from an AI-powered application. Use webhooks to notify that application about new activity, and MCP when a person wants to work through an assistant.

They combine well. A common setup uses webhooks to notify an agent, the REST API for that agent to reply deterministically, and MCP so the support team can still ask questions in natural language over the same inbox. See the API Reference in the sidebar for endpoints, and Quickstart for the receive-a-message-and-reply loop.

What MCP gives you

Once connected, your assistant can work in your inbox conversationally:

"How many conversations are still unresolved on the marketing widget?"

"Summarise the last conversation with john@example.com, then reply asking for their order number."

"Tag every conversation from today that mentions refunds."

It does this by calling tools you explicitly authorized. It never gets your password, and you never paste an API key into it.

The endpoint is a streamable HTTP MCP server and accepts POST requests. It is separate from the REST API: the REST API authenticates with an X-API-KEY header, MCP with OAuth.

Authentication

MCP clients use OAuth 2.1 with PKCE and request the mcp:use scope. Chatway supports dynamic client registration, so your client handles the whole exchange and you never create a client ID or secret.

  1. Your client discovers Chatway's authorization server from the MCP endpoint.
  2. A browser opens and you sign in to Chatway.
  3. You name the connection, so you can recognise it later.
  4. You choose which widgets and channels the assistant may access.
  5. You choose which permissions to grant, and which agent replies are sent as.
  6. Chatway issues an access token scoped to exactly those choices and returns you to your client.

Every connection belongs to your team workspace, not to an individual teammate. Owners and admins manage that connection under AI → External AI. Re-authorizing the same assistant client (for example Claude or Cursor) updates the team connection instead of creating a second one.

What assistants can do

Twenty-three tools are available. Each inbox tool requires a matching permission, so an assistant only sees the tools you actually granted. The two installation tools need no permission.

GroupTools
Read conversationslist-conversations, get-conversation, list-conversation-messages, search-conversations
Read peopleget-visitor, search-contacts
Read settingssearch-knowledge-base, list-tags, list-custom-fields, list-agents
Reply and triagesend-message, resolve-conversation, unresolve-conversation, assign-conversation
Annotateadd-note, add-tag, remove-tag
Custom dataadd-custom-data, update-custom-data, remove-custom-data
Escalatehandoff-to-human
Install on a websiteget-installation-code, get-installation-status

handoff-to-human uses the same handover behaviour as Chatway's built-in AI agent, so your team gets the notifications and inbox state they already expect. It works on conversations currently handled by a Chatway AI assistant.

For each tool's parameters, return shape, and limits, see the Tool reference.

Scope of access

A connection can only reach the widgets and channels you selected. It sees nothing from your other widgets, and it can never reach data belonging to another team. Both are enforced on every request, independently of which permissions you granted.

Permissions also respect your Chatway role. Only owners and admins can run the MCP OAuth flow to connect or reconnect an assistant and open AI → External AI in Settings. Members do not have access to that menu. Write permissions on a connection can only be granted by an owner or admin.

Safety on bulk and destructive actions

Bulk actions ask for confirmation before Chatway will run them. When the assistant resolves, unresolves or assigns more than one conversation at once, it has to put the question to you first, along with how much it is about to affect:

This action will resolve 30 conversations. Are you sure?

Confirm and it proceeds. Your approval lasts 5 minutes and is tied to that exact action, so an assistant cannot reuse it for anything else.

Every other action, including resolving, unresolving or assigning a single conversation, runs straight away within the permissions you granted, so an agent can work unattended. Your AI client may still ask you to approve a tool call on its own. See Permissions & access for the full policy.

Rate limits

Two limits apply, and both must allow a call:

LimitCountsScope
120 requests per minuteEvery MCP requestPer connection
30 conversations per minute for each of resolve, unresolve and assignEach conversation in the callPer account, shared with the REST API

The request limit is per connection, so a busy assistant cannot slow down your other connections. Over it, the server returns 429 and the assistant should retry after a short pause.

The conversation limit is per account. Every connection and API key draws from the same budget, so opening another connection does not increase it. A call with 10 conversations uses 10. Resolve, unresolve and assign each have their own budget. A single call can include up to 30 conversations.

When a call would go over the conversation limit, the whole call is rejected and nothing is queued. The tool returns an error that says how many seconds to wait. The budget resets one minute after the first counted conversation.

Replying in real time with webhooks

MCP is on-demand: the assistant acts when you ask it to. If you want your AI agent to answer visitors automatically as soon as they send a message, use Chatway webhooks together with the REST API.

Visitor → Chatway → webhook → your AI agent → Chatway API → visitor

Chatway POSTs a signed event to your endpoint, your agent decides what to say, and it replies through the REST API. Alongside the reply your agent can record optional confidence and model details, which is useful for tracking how well it is performing before you let it handle everything.

You can also connect the same agent through MCP for on-demand access to your Chatway workspace — triaging the queue, summarizing threads, or taking actions in natural language. MCP is optional for the real-time loop above; webhooks and the REST API are enough on their own.

Fourteen events are documented, including the ones most agents need:

EventFires when
conversation.createdA new chat has started
message.receivedA visitor sent a new message
conversation.resolvedA conversation was resolved
agent.assignedAn agent was assigned to a conversation
contact.form.submittedA visitor submitted a contact or offline form

Webhook-driven agents can reply and route conversations to humans using an API key, without an interactive MCP session. Your application can reply with Create Message, resolve a conversation with Resolve Conversation, hand it to your team with Request Human Handoff, assign an agent or team with Assign Conversation or Unassign Conversation, and tag it with Add Conversation Tag or Remove Conversation Tag. Check the REST reference for each operation you need; the MCP tool list is a separate interface.

Set this up under Settings → Developer Tools → Webhooks, and see Webhook docs → Overview in the sidebar for the full event list, payload shapes, signature verification, and retries. Quickstart walks through the receive-a-message-and-reply loop end to end.

Next steps

{"<?php $__contextArgs = [];\nif (context()->has($__contextArgs[0])) :\nif (isset($value)) { $__contextPrevious[] = $value; }\n$value = context()->get($__contextArgs[0]); ?>":"https://schema.org","@type":"TechArticle","headline":"Overview","description":"The Chatway MCP server lets an AI assistant — Claude, ChatGPT, Cursor, Codex, Grok, Muse, or anything else that speaks the [Model Context Protocol](https://mode…","url":"https://developers.chatway.app/mcp/guides.mcp_overview","image":"https://chatway.app/wp-content/themes/chatway-theme/assets/images/preview/chatway-v2-preview.webp","author":{"@type":"Organization","name":"Chatway"},"publisher":{"@type":"Organization","name":"Chatway","logo":{"@type":"ImageObject","url":"https://chatway.app/wp-content/themes/chatway-theme/assets/images/preview/chatway-v2-preview.webp"}}}