Integration

Chatlayer integration

Chatlayer by Sinch is a conversational AI platform for building chatbots. With this integration an agent can list the team's bots and their channels, read conversations, message history and session data of a bot, send a user message to a bot through a Webhook channel, execute actions in a live conversation (send bot messages, set session data, trigger a dialog, hand-off options), extract intents, entities and sentiment from an expression with the bot's NLP model, register or delete a Webhook channel, and delete a session or all data of a user. Authentication is a team access token generated in the Chatlayer platform, sent as a Bearer token. api_host is the API host of the account's region: api.chatlayer.ai (Europe), api.prod.us-east4.gcp.chatlayer.ai (United States) or api.prod.asia-south1.gcp.chatlayer.ai (APAC).

Connect Chatlayer How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Chatlayer.Built from the 13 Chatlayer tools below, on the connection you add once.

What you can do with Chatlayer

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

Bot, 2 operations

get_botGet botGETGet one bot by id: name, default and supported languages, typing delay, and whether its LIVE and DRAFT versions are enabled.
list_botsList botsGETList all the bots of the team the access token belongs to, with their id, name, languages and status. Use the id as botId in the other tools.

Channel, 2 operations

delete_bot_channelDelete bot channelDELETEDelete a channel of a bot by id. Get the channel ids from list_bot_channels. Messages can no longer be sent through a deleted Webhook channel.
list_bot_channelsList bot channelsGETList the channels configured for one version of a bot. Each item carries the channel id used by send_webhook_message and delete_bot_channel.

Message, 2 operations

list_messagesList messagesGETList the messages of one user of a bot, most recent first, paginated (up to 100 per page). The messages can span several conversations. actor says who sent each: user, bot or agent.
send_webhook_messageSend webhook messagePOSTSend a user message to a bot through its Webhook channel. Answers EVENT_RECEIVED; the bot's replies are POSTed to the url of the channel, not returned here. Use list_messages to read them.

Session data, 2 operations

delete_sessionDelete sessionDELETEDelete all session data of a user's session. A new session is created when the user resumes the conversation.
get_session_dataGet session dataGETGet the session data of a user's session: the variables saved during the bot flow, plus session details (expiry, channel, current dialog, last intent). Filter by namespace.

Action, 1 operation

execute_conversation_actionExecute conversation actionPOSTAct in a user's active conversation: send bot messages to the user, set session data, trigger a bot dialog, delete contexts, or pause the bot for a human handover. Send at least one action.

Conversation, 1 operation

list_conversationsList conversationsGETList the conversations of a bot version, paginated: page 1 to 20, up to 100 per page. Filter by user_id, or by date with before and after.

Extract, 1 operation

extract_nlp_resultExtract nlp resultPOSTRun one expression through the bot's NLP model: returns the best intent and its score, the ranked intents, entities and, with options.includeSentiment, the sentiment. Nothing is sent to a user.

User, 1 operation

delete_user_dataDelete user dataDELETEDelete all sessions and conversations of a user of a bot. A new session and conversation are created if the user talks to the bot again. Cannot be undone.

Webhook, 1 operation

create_webhook_channelCreate webhook channelPOSTAdd a Webhook channel to a bot version. The bot then POSTs every reply to url, with your verifyToken in each payload. Returns the channel id that send_webhook_message needs.

Use Chatlayer from Claude Code, Cursor or Codex

Connect Chatlayer in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its Chatlayer operations become tools the client can call, next to every other integration you connected.

Claude Code

claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"

Codex (~/.codex/config.toml)

[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"

Cursor, Claude Desktop and other JSON configs

{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect Chatlayer

Create your workspace
Sign up free. Nothing to install.
Connect Chatlayer once
Add your Chatlayer connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.
Describe the job in chat
The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.