LiveChat (Text) MCP Server
Chats, tags and canned replies in your LiveChat, worked by your agent.
Hosted MCP Server
npx add-mcp 'https://cotlet.dev/mcp/v1/livechat'Installs into Claude Code, Codex, Cursor and more
Documentation
Cotlet · Integrations · How it works · Security · For developers · For automation agencies · Blog · API docs · Help center · Changelog · Contact · Pricing · Sign up
LiveChat (Text) API and MCP server
LiveChat (Text) has a full REST API, the Agent Chat API and the Configuration API, but only a narrow official MCP server (checked 17 Oct 2026). The server at mcp.text.com documents 8 tools that all read: search, fetch, chat transcripts, archived chats, tickets and tags. It cannot reply, tag, transfer or change settings.
Chats, tags and canned replies in your LiveChat, worked by your agent. Use it in ChatGPT, Claude or any AI agent over MCP, or in n8n, Make and scripts over REST.
Cotlet is an independent service. It is not affiliated with, endorsed by or sponsored by LiveChat (Text). LiveChat (Text) is a trademark of its owner. If LiveChat (Text)'s own integrations cover what you need, use them first.
Live chat and support platform from Text: customers write from your website or messaging channels, and agents answer in the Chats section, tag conversations, transfer them and review them in Archives.
What is the LiveChat (Text) API?
Cotlet's LiveChat (Text) API exposes 12 endpoints for your own LiveChat (Text) account: list chats, get chat, list archived chats, list tags, list canned responses, list agents and groups, send message, send private note, tag chat, transfer chat, close and archive chat and save canned response. The list_chats endpoint returns chats in My chats, Queued chats, Unassigned chats or Supervised chats, with customer, channel and last message. Each endpoint takes simple JSON inputs like chat_id, group or cursor and works both as an operation of the livechat_read or livechat_write MCP tool for agents and as a REST call for scripts.
- Category: Customer support
- Endpoints: 12 (6 read, 6 write)
- Updated: 2026-11-15
LiveChat (Text) has a full REST API, the Agent Chat API and the Configuration API, but only a narrow official MCP server (checked 17 Oct 2026). Cotlet is a hosted MCP server and REST API for LiveChat (Text) with 12 endpoints (6 read, 6 write): you sign in once in your own cloud browser, your AI agent does the work.
Does LiveChat (Text) have an official API?
LiveChat (Text) has a full REST API, the Agent Chat API and the Configuration API, but only a narrow official MCP server (checked 17 Oct 2026). The server at mcp.text.com documents 8 tools that all read: search, fetch, chat transcripts, archived chats, tickets and tags. It cannot reply, tag, transfer or change settings.
| Task | LiveChat (Text) official | Cotlet |
|---|---|---|
| List active, queued and unassigned chats | Yes: Agent Chat API list_chats; no official MCP tool for live chats | Yes |
| Read a chat transcript | Yes: Agent Chat API get_chat; the official MCP has get-chat-transcript | Yes |
| Search archived chats by tag, agent, group or date | Yes: Agent Chat API list_archives; the official MCP has list-archived-chats | Yes |
| Send a reply or private note in a chat | Partly: Agent Chat API send_event with a token or OAuth app; the official MCP cannot send | Yes |
| Tag and untag a chat | Yes: Agent Chat API tag_thread and untag_thread; the official MCP can only list tags | Yes |
| Transfer a chat to an agent or group | Yes: Agent Chat API transfer_chat; not in the official MCP | Yes |
| Close and archive a chat | Yes: Agent Chat API deactivate_chat; not in the official MCP | Yes |
| Create and edit canned responses | Yes: Configuration API; not in the official MCP | Yes |
Sources: Text Platform: MCP server, Text Platform: Agent Chat API, Text Platform: Configuration API, Zapier: LiveChat triggers and actions
Quick reference
LiveChat (Text) has a full REST API, the Agent Chat API and the Configuration API, but only a narrow official MCP server (checked 17 Oct 2026). The server at mcp.text.com documents 8 tools that all read: search, fetch, chat transcripts, archived chats, tickets and tags. It cannot reply, tag, transfer or change settings.
Cotlet provides a hosted MCP server and REST API for LiveChat (Text): 12 tools (6 read, 6 write).
Access Sign up at https://cotlet.dev/app/signup?app=livechat and request the app in the Cotlet console. ChatGPT and Claude connect with OAuth at https://cotlet.dev/mcp/v1/connect, no API key; code editors and scripts use an API key from the console.
MCP server https://cotlet.dev/mcp/v1
MCP tools livechat_read, livechat_write, reads and writes apart; call one with {"operation": "<operation>", "arguments": {...}}
REST base https://cotlet.dev/api/v1/livechat, each operation at its own route, e.g. POST /api/v1/livechat/chats/{chat_id}/messages
Auth Authorization: Bearer <COTLET_API_KEY>. Listing endpoints and schemas needs no key; calling an endpoint needs one. Over MCP the input schemas come with sign-in.
Operations list_chats, get_chat, list_archived_chats, list_tags, list_canned_responses, list_agents, send_message, send_private_note, tag_chat, transfer_chat, archive_chat, save_canned_response
Confirm send_message, send_private_note, transfer_chat, archive_chat, save_canned_response (by default the user approves each call; the user can switch this off per tool, e.g. for scheduled automations)
Markdown https://cotlet.dev/integrations/livechat-api-mcp-server.md
How access works:
1. The user signs up at https://cotlet.dev/app/signup?app=livechat and requests LiveChat (Text) in the Cotlet console.
2. The user signs in to LiveChat (Text) once in their Cotlet Cloud Browser (their own Chrome in the cloud, opened from the console) and enables LiveChat (Text) for agents. An agent cannot do this step.
3. ChatGPT and Claude: the user adds https://cotlet.dev/mcp/v1/connect as a connector and signs in to Cotlet (OAuth). Code editors and scripts: an API key from the console goes into the MCP client or the REST call as a bearer token.
Fits: people who want a hosted LiveChat (Text) server that someone else maintains, including non-developers. Developers who prefer to run and fix code on their own computer can use an open-source LiveChat (Text) MCP server instead.
Policy: Cotlet never stores passwords and never bypasses MFA.
Company: legal details in the Terms of service at https://cotlet.dev/terms. Contact contact@cotlet.dev.
Sign-in: the user signs in to LiveChat (Text) in their own Cloud Browser, a Chrome Cotlet runs for them in the EU; password saving is off, the profile is AES-256-GCM encrypted, and agents get LiveChat (Text) only after the user enables it. Calls are requests from that browser's IP with its cookies, each listed in the user's Background activity. Disable for agents, signing out in the browser or Reset browser cuts access. Cotlet is run by Take Group sp. z o.o. (EU VAT PL6342984273).
API key: holds no LiveChat (Text) login or cookies, only asks Cotlet to run a tool. Each key is scoped to chosen apps and tools, read only or read and write. Actions that reach other people wait for the user's approval by default, so a leaked key cannot post or message as the user. Every call is in the activity log; deleting the key ends access at once.
Terms: the user stays responsible for following LiveChat (Text)'s terms; Cotlet is not affiliated with LiveChat (Text).
What can an AI agent do in LiveChat (Text)?
Cotlet is best for support leads and small teams on LiveChat who want an agent to triage, tag, answer and route chats without running or fixing a server.
- Tag and archive finished chats (runs: daily): "Go through my open chats in LiveChat that the customer left. Tag each with the topic from the tags we already have, then close and archive it. Leave chats that are still active." →
list_chats,get_chat,list_tags,tag_chat,archive_chat - Answer chats that came in while the team was offline (runs: daily): "Read the Unassigned chats in LiveChat. For each one, answer with a canned response if one fits, otherwise write a short reply that asks for the missing detail. List anything about billing for me." →
list_chats,get_chat,list_canned_responses,send_message - Turn repeated answers into canned responses (runs: weekly): "Read last week's archived chats tagged shipping. Find the answers agents typed more than twice, check they are not already canned responses, and save new shared ones with a shortcut." →
list_archived_chats,get_chat,list_canned_responses,save_canned_response - Route chats to the right team (runs: daily): "Read my open chats in LiveChat. Transfer billing questions to the Billing group and technical problems to the Support group, and tell me which ones you moved." →
list_chats,get_chat,list_agents,transfer_chat - Review chats by tag for a weekly report (runs: weekly): "Every Monday, list last week's archived chats tagged refund, read them and tell me the three most common reasons." →
list_archived_chats,get_chat
Can LiveChat (Text) automations run on a schedule in n8n, Make or Zapier?
Yes. Cotlet does not replace your automation platform: it gives it a LiveChat (Text) connection it does not have, with the same API key as your agent. Write actions ask for your OK by default; switch that off in your dashboard for the tools you choose, for example to tag and archive finished chats, and the schedule runs on its own. Cotlet runs in the cloud, so it keeps going while your computer is off.
| Where | How to connect | How to schedule |
|---|---|---|
| Your AI agent | Add https://cotlet.dev/mcp/v1 with your API key. | A scheduled agent run, for example a Claude Code routine. |
| n8n | MCP Client node with https://cotlet.dev/mcp/v1, or an HTTP Request node with the endpoint's method and URL, such as GET https://cotlet.dev/api/v1/livechat/chats. | Schedule Trigger node. |
| Make | HTTP module: the endpoint's method and URL with an Authorization: Bearer header, and a JSON body for POST, PUT and PATCH. | Scenario schedule. |
| Zapier | Webhooks by Zapier, Custom Request: the same method, URL, header and body. | Schedule by Zapier trigger. |
| Your own script | GET https://cotlet.dev/api/v1/livechat/chats with your API key. | cron or GitHub Actions. |
Tools
For AI agents: Every endpoint and its schema is public. The 12 endpoints on this page, with parameters and example responses, can be listed without an account. Calling one returns 401 without an API key and 403 while the key has no access to LiveChat (Text).
list_chats
Chats in My chats, Queued chats, Unassigned chats or Supervised chats, with customer, channel and last message. Access: read. REST: GET /api/v1/livechat/chats. MCP: livechat_read → list_chats.
| Parameter | Type | Required | Description |
|---|---|---|---|
list | enum | no | my, queued, unassigned or supervised. Default: my. |
limit | integer | no | Number of chats per page. Default: 20. |
cursor | string | no | Next page cursor from the previous call. |
Lists the chats in one of the lists you see in the Chats section: my, queued, unassigned or supervised. Each item has the customer, the channel, the last message and whether the chat is active or inactive. Pass next_cursor back as cursor for the next page.
Example response:
{
"chats": [
{
"chat_id": "PJ0MRSHTDG",
"list": "unassigned",
"customer": {
"name": "Lena Ortiz",
"email": "lena@example.com"
},
"channel": "WhatsApp",
"active": true,
"last_message": {
"from": "customer",
"text": "Hi, I was charged twice in October.",
"sent_at": "2026-10-17T05:42:00Z"
}
}
],
"next_cursor": null
}
get_chat
Full transcript of one chat with every message, private note and tag. Access: read. REST: GET /api/v1/livechat/chats/{chat_id}. MCP: livechat_read → get_chat.
| Parameter | Type | Required | Description |
|---|---|---|---|
chat_id | string | yes | Chat ID from list_chats or list_archived_chats. |
Returns one chat, active or archived, with all messages in order, oldest first, the private notes your role can see, the tags and the agents who took part. Use it before replying or tagging so your agent reads the whole conversation.
Example response:
{
"chat_id": "PJ0MRSHTDG",
"customer": {
"name": "Lena Ortiz",
"email": "lena@example.com"
},
"tags": [],
"messages": [
{
"from": "customer",
"text": "Hi, I was charged twice in October.",
"sent_at": "2026-10-17T05:42:00Z"
},
{
"from": "customer",
"text": "Order 4821.",
"sent_at": "2026-10-17T05:43:00Z"
}
]
}
list_archived_chats
Archived chats, newest first, filtered by tag, agent, group, date or search text. Access: read. REST: GET /api/v1/livechat/archived-chats. MCP: livechat_read → list_archived_chats.
| Parameter | Type | Required | Description |
|---|---|---|---|
tags | string[] | no | Tag names to filter by. |
match_tags | enum | no | all or any. Default: any. |
agent | string | no | Only chats handled by this agent. |
group | string | no | Only chats in this group. |
from | date | no | Only chats ended on or after this date. |
to | date | no | Only chats ended on or before this date. |
query | string | no | Search text, like the Archives search bar. |
cursor | string | no | Next page cursor from the previous call. |
Searches Archives and returns chats newest first with customer, agent, tags and the first and last message. The filters are the ones Archives offers. With several tags, match_tags decides whether a chat needs all of them or any of them. Pass next_cursor back as cursor for the next page.
Example response:
{
"chats": [
{
"chat_id": "Q4D7XK2M91",
"customer": {
"name": "Sam Okafor"
},
"agent": "Maria Silva",
"group": "Support",
"tags": [
"shipping"
],
"ended_at": "2026-10-16T14:20:00Z",
"last_message": "Thanks, that helps."
}
],
"next_cursor": "eyJvZmZzZXQiOjIwfQ"
}
list_tags
Tags your role can see, with the group each one is limited to. Access: read. REST: GET /api/v1/livechat/tags. MCP: livechat_read → list_tags.
No parameters.
Returns the tags from Settings > Tags that you can see. A tag limited to a group shows that group; admins and the owner see all tags. Names are up to 70 characters. Use these names in tag_chat.
Example response:
{
"tags": [
{
"name": "refund",
"group": null
},
{
"name": "shipping",
"group": "Support"
}
]
}
list_canned_responses
Shared and private canned responses with text, shortcuts, group and tags. Access: read. REST: GET /api/v1/livechat/canned-responses. MCP: livechat_read → list_canned_responses.
| Parameter | Type | Required | Description |
|---|---|---|---|
visibility | enum | no | all, shared or private. Default: all. |
group | string | no | Only responses for this group. |
Lists the canned responses you can use: your private ones and the shared ones, with the text, the shortcuts you type after #, the group and the tags. Needs a plan with canned responses (Team, Business or Enterprise). Use the shortcut and text when replying.
Example response:
{
"responses": [
{
"response_id": "cr_1041",
"visibility": "shared",
"group": "Support",
"shortcuts": [
"returns"
],
"text": "Hi %customer-name%, you can return an item within 14 days. Reply with your order number and I will start it.",
"tags": [
"refund"
]
}
]
}
list_agents
Agents and groups a chat can be transferred to, with their current availability. Access: read. REST: GET /api/v1/livechat/agents. MCP: livechat_read → list_agents.
No parameters.
Returns the agents and groups shown in the Transfer to... dialog, with each agent's group and availability. Use the agent_id or group from here in transfer_chat. Transferring to a group lands on the first free agent in it, so no agent is chosen for a group.
Example response:
{
"agents": [
{
"agent_id": "maria@example.com",
"name": "Maria Silva",
"groups": [
"Support"
],
"available": true
}
],
"groups": [
{
"group": "Billing"
},
{
"group": "Support"
}
]
}
send_message
Reply to the customer in a chat, as you. Access: write, asks the user first. REST: POST /api/v1/livechat/chats/{chat_id}/messages. MCP: livechat_write → send_message.
| Parameter | Type | Required | Description |
|---|---|---|---|
chat_id | string | yes | Chat ID from list_chats or list_archived_chats. |
body | string | yes | Message text. |
canned_response | string | no | Response ID from list_canned_responses. Replaces body. |
Sends a message to the customer in one chat, under your agent name. Pass canned_response to send the text of a canned response with its variables filled in. By default you confirm each call; you can switch that off for this tool.
Example response:
{
"chat_id": "PJ0MRSHTDG",
"event_id": "ev_5530",
"status": "sent",
"sent_at": "2026-10-17T07:02:00+02:00"
}
send_private_note
Add a message to a chat that only agents see. Access: write, asks the user first. REST: POST /api/v1/livechat/chats/{chat_id}/private-notes. MCP: livechat_write → send_private_note.
| Parameter | Type | Required | Description |
|---|---|---|---|
chat_id | string | yes | Chat ID from list_chats or list_archived_chats. |
body | string | yes | Note text. |
Adds a private message to a chat. Other agents on the chat see it and the customer does not. Private notes belong to the Business and Enterprise plans. A sent note stays in the chat. By default you confirm each call; you can switch that off for this tool.
Example response:
{
"chat_id": "PJ0MRSHTDG",
"event_id": "ev_5531",
"status": "sent",
"visibility": "agents"
}
tag_chat
Add tags to a chat, or remove them. Access: write. REST: POST /api/v1/livechat/chats/{chat_id}/tag. MCP: livechat_write → tag_chat.
| Parameter | Type | Required | Description |
|---|---|---|---|
chat_id | string | yes | Chat ID from list_chats or list_archived_chats. |
add | string[] | no | Tag names to add. |
remove | string[] | no | Tag names to remove. |
Adds the tags in add to a chat and removes the tags in remove. Tags must already exist in Settings > Tags, which only admins and the owner can change, and must be visible to your role. Works on active and archived chats. Tagging reaches no customer and is undone with one call, so tag_chat runs without asking first.
Example response:
{
"chat_id": "PJ0MRSHTDG",
"added": [
"refund"
],
"removed": [],
"tags": [
"refund"
]
}
transfer_chat
Move a chat to another agent or to a group. Access: write, asks the user first. REST: POST /api/v1/livechat/chats/{chat_id}/transfer. MCP: livechat_write → transfer_chat.
| Parameter | Type | Required | Description |
|---|---|---|---|
chat_id | string | yes | Chat ID from list_chats or list_archived_chats. |
agent_id | string | no | Agent from list_agents. Use this or group. |
group | string | no | Group from list_agents. Use this or agent_id. |
note | string | no | Private note for the next agent. Business and Enterprise. |
Transfers an active chat to one agent, or to a group where it goes to the first free agent by your routing rules. You cannot pick an agent inside another group. An optional private note goes along on Business and Enterprise. By default you confirm each call; you can switch that off for this tool.
Example response:
{
"chat_id": "PJ0MRSHTDG",
"status": "transferred",
"to": {
"group": "Billing"
}
}
archive_chat
Stop an active chat and move it to Archives. Access: write, asks the user first. REST: POST /api/v1/livechat/chats/{chat_id}/archive. MCP: livechat_write → archive_chat.
| Parameter | Type | Required | Description |
|---|---|---|---|
chat_id | string | yes | Chat ID from list_chats or list_archived_chats. |
Closes one chat the way Close and archive does in My chats, and the chat moves to Archives with its tags. Tag the chat first, because Archives and tag reports use the tags. By default you confirm each call; you can switch that off for this tool.
Example response:
{
"chat_id": "PJ0MRSHTDG",
"status": "archived",
"tags": [
"refund"
]
}
save_canned_response
Create a canned response, or change one by its ID. Access: write, asks the user first. REST: POST /api/v1/livechat/canned-response/save. MCP: livechat_write → save_canned_response.
| Parameter | Type | Required | Description |
|---|---|---|---|
text | string | yes | Message text. Variables: %customer-name%, %customer-email%, %agent-name%, %agent-email%. |
shortcuts | string[] | yes | Words you type after #. |
visibility | enum | no | shared or private. Default: shared. |
group | string | no | Limit the response to one group. |
tags | string[] | no | Up to 5 tags from the same group. |
response_id | string | no | Set to change an existing response. |
Creates a shared or private canned response with its text, shortcuts, group and up to 5 tags, or updates an existing one when response_id is set. A shared response is usable by the whole team, or by one group. Variables such as %customer-name% are filled in when an agent sends it. By default you confirm each call; you can switch that off for this tool.
Example response:
{
"response_id": "cr_1042",
"visibility": "shared",
"shortcuts": [
"delivery-times"
],
"status": "saved"
}
How do I connect LiveChat (Text) to ChatGPT, Claude, Cursor or Codex?
Connecting LiveChat (Text) takes three steps: sign up, sign in to LiveChat (Text) once in your Cloud Browser and enable it for agents, then add Cotlet to ChatGPT or Claude as a connector, with no API key, or add one MCP server or call the REST API with an API key.
Connect LiveChat (Text) to your agent.
-
Create an account Sign up and add LiveChat (Text) in the console. ChatGPT and Claude need no API key: you sign in to Cotlet when you add the connector. Code editors and scripts take an API key from the console.
-
Sign in to LiveChat (Text) in your Cloud Browser Open your Cloud Browser in the console: your own Chrome in the cloud. Sign in to LiveChat (Text) there yourself, the way you always do, then press Enable for agents, read only or read and write. We never save your password, and your agent keeps working even when your computer is off.
-
Add Cotlet to ChatGPT, Claude or your agent Paste the snippet for your client. The same server and key serve every app you connect, so you do this once.
ChatGPT:
Settings > Apps & Connectors > Create
MCP server URL: https://cotlet.dev/mcp/v1/connect
Authentication: OAuth
Claude:
Settings > Connectors > Add custom connector
URL: https://cotlet.dev/mcp/v1/connect
Claude Code:
claude mcp add --transport http cotlet \
https://cotlet.dev/mcp/v1 \
--header "Authorization: Bearer $COTLET_API_KEY"
Cursor:
{
"mcpServers": {
"cotlet": {
"url": "https://cotlet.dev/mcp/v1",
"headers": {
"Authorization": "Bearer ${COTLET_API_KEY}"
}
}
}
}
Codex:
# ~/.codex/config.toml
[mcp_servers.cotlet]
url = "https://cotlet.dev/mcp/v1"
bearer_token_env_var = "COTLET_API_KEY"
- Ask your agent Ask in plain words. Your agent finds the LiveChat (Text) tools on the server and calls them for you; anything that reaches other people waits for your OK unless you switch that off for a tool.
Go through my open chats in LiveChat that the customer left. Tag each with the topic from the tags we already have, then close and archive it. Leave chats that are still active.
Call LiveChat (Text) from your scripts.
- Export your API key Your scripts use the same API key as your agent. Keep it in an environment variable, never in your code.
export COTLET_API_KEY="cotlet_..."
- Call a tool Every tool is an endpoint under /api/v1/livechat with its own method and path, listed with the endpoints above. Path parameters go in the URL; the other parameters go in the query for GET and DELETE and in a JSON body otherwise.
curl -X POST https://cotlet.dev/api/v1/livechat/chats/PJ0MRSHTDG/messages \
-H "Authorization: Bearer $COTLET_API_KEY" \
-H "Content-Type: application/json" \
-d '{"body":"Hi Lena, thanks for writing. Could you send me your order number so I can check the delivery?"}'
- Read the result You get plain JSON back, ready for your script. A failed call costs nothing.
{
"chat_id": "PJ0MRSHTDG",
"event_id": "ev_5530",
"status": "sent",
"sent_at": "2026-10-17T07:02:00+02:00"
}
How to use the LiveChat (Text) REST API
Create your Cotlet API key
Create a Cotlet API key with access to LiveChat (Text) and its read operations. Store it as COTLET_API_KEY in your environment or automation platform's credential store.
Connect LiveChat (Text) in Cotlet and enable it for agents. Account access: Your own LiveChat agent login (agent, admin or owner). What your agent can do follows your role. You sign in in your own browser and keep your SSO or 2-step verification.
Make your first LiveChat (Text) API request
REST:
curl "https://cotlet.dev/api/v1/livechat/chats?list=unassigned&limit=5" \
-H "Authorization: Bearer $COTLET_API_KEY"
Read chats and apply the operation limits
A successful REST call puts the tool output in result. This illustrative response excerpt omits call IDs, messages and credit details.
Illustrative response excerpt:
{
"status": "success",
"app": "livechat",
"tool": "list_chats",
"result": {
"chats": [
{
"chat_id": "PJ0MRSHTDG",
"list": "unassigned",
"customer": {
"name": "Lena Ortiz",
"email": "lena@example.com"
},
"channel": "WhatsApp",
"active": true,
"last_message": {
"from": "customer",
"text": "Hi, I was charged twice in October.",
"sent_at": "2026-10-17T05:42:00Z"
}
}
],
"next_cursor": null
}
}
Lists the chats in one of the lists you see in the Chats section: my, queued, unassigned or supervised. Each item has the customer, the channel, the last message and whether the chat is active or inactive.
Pass next_cursor back as cursor for the next page.
limit: Number of chats per page. Default: 20.
cursor: Next page cursor from the previous call.
Keep the same selection when continuing a list. Compare changed record values as well as identifiers when refreshing your destination.
LiveChat (Text) workflows for agents and automations
| Tool | Connect through | Example workflow |
|---|---|---|
| n8n | HTTP Request | Full transcript of one chat with every message, private note and tag. Use get_chat in your configured support report. |
| Make | HTTP > Make a request | Archived chats, newest first, filtered by tag, agent, group, date or search text. Use list_archived_chats in your configured support report. |
| Python or Node.js | REST API | Shared and private canned responses with text, shortcuts, group and tags. Use list_canned_responses in your configured support report. |
Send Authorization: Bearer <your Cotlet API key> in request headers. You configure the schedule, destination and record comparisons.
Cotlet reads LiveChat (Text); your workflow steps write to your chosen destination. These HTTP workflows do not require a native Cotlet connector or a prebuilt template.
Python and Node.js can use the same HTTP requests without an AI agent. Keep access keys in credentials, outside shared workflow exports.
The API and MCP reference lists operations and inputs. The REST API guide explains authentication, errors and approvals.
Why use Cotlet for LiveChat (Text)?
Built for agents
- One MCP server for every app you connect.
- The same tools as a REST API for scripts and cron jobs.
- Works with ChatGPT, Claude, Claude Code, Codex and Cursor.
Your login stays yours
- You sign in to LiveChat (Text) yourself, in your own Cloud Browser. We never save your password; the profile is encrypted with AES-256-GCM, the cipher 1Password uses.
- A+ on Qualys SSL Labs, securityheaders.com and Mozilla Observatory.
- The model never sees a login.
- No stored passwords, no MFA bypass.
You stay in control
- Scope each API key: its apps, its tools, read only or read and write.
- Anything that reaches other people waits for your OK, so a leaked key cannot post or message as you.
- Every background request listed in your Background activity. Disable for agents in one click.
Kept working for you
- We test every integration every 6 hours.
- When LiveChat (Text) changes, the tool pauses until we fix it.
- Failed calls cost nothing.
Is it safe to connect LiveChat (Text) to Cotlet?
Yes. You sign in to LiveChat (Text) yourself, in your own Cloud Browser, and we never save your password. Your agents only get LiveChat (Text) once you enable it, and every background request is listed. The browser profile is stored encrypted with AES-256-GCM, the same cipher 1Password uses for its vaults and Apple for iCloud Keychain. Independent public scanners grade cotlet.dev A+ and find it clean; click a result to rerun it yourself.
- A+ on Qualys SSL Labs: Encryption in transit: TLS setup and certificates, on all four server addresses. Live result
- A+ on securityheaders.com: Browser protections sent with every page, all six headers present. Live result
- A+ on Mozilla Observatory: Mozilla's web security baseline: score 120 of 100, 12 of 12 tests passed. Live result
- Clean on Sucuri SiteCheck: No malware, spam or defacement, and not on any of 9 blocklists, Google Safe Browsing included. Live result
How Cotlet protects your access
Common concerns
Who runs Cotlet?
Cotlet is run by Take Group, a Polish software company working since 2019. Take Group runs about 3,200 websites on its own systems and has its own DevOps team for infrastructure security. We built and used integrations like this inside the company for years before opening them as Cotlet.
Is this an official LiveChat (Text) integration?
No, Cotlet is independent of LiveChat (Text). LiveChat (Text)'s own API is too limited for this work. Cotlet works through your own LiveChat (Text) account, the way you use LiveChat (Text) in the browser.
What about client data and GDPR?
Cotlet is run from the EU and follows the GDPR. Cloud Browsers run in Finland, a Tier 1 country in the ITU Global Cybersecurity Index 2024. Data passes through a call and is not kept after it.
Can I start with read only?
Yes. Enable the app for agents as read only, or make the API key read only, and anything that reaches other people waits for your OK unless you switch that off per tool.
Is it reliable?
Every Cotlet service is checked every 3 minutes from Europe, North America, Asia and Australia. The live results and any outage are public at status.cotlet.dev.
How do I stop?
Press Disable for agents next to LiveChat (Text) in your console: your agents lose access at once and you stay signed in. Signing out of LiveChat (Text) in the browser works too, and Reset browser deletes the whole profile.
Is there a LiveChat (Text) MCP server on GitHub?
Yes. Community LiveChat MCP servers exist on GitHub, usually maintained by one person. You install one yourself, give it a personal access token, and fix it when LiveChat changes. Cotlet hosts the same kind of server for you, signs in as your agent, and our team keeps it working.
| GitHub MCP server | Cotlet | |
|---|---|---|
| Setup | Clone the repo, create a token or an app in the Developer Console, pick scopes, add the server to each MCP client | Sign up, sign in to LiveChat once, add one MCP server or API key |
| When LiveChat changes | It breaks until you or the maintainer fix it | Our team tests it daily and fixes it for you; failed calls are free |
| Your LiveChat access | A token in a file on your computer, readable by any program you run | Signed in inside your own Cloud Browser in the EU, profile encrypted, only for the apps you enable, disabled for agents in one click |
| When access expires | Tools fail until you renew the token or sign in again by hand | Your Cloud Browser keeps you signed in; if LiveChat logs you out, your agent gets a link to sign in again |
| Upkeep | You update, monitor and debug it yourself | Nothing to host or update |
| Where it runs | Your computer, while it is on | Hosted: Claude Code, Codex, Cursor, n8n and scripts, also on a schedule |
| Price | Free, paid for with your time | Free 7-day trial, then pay-as-you-go credit packs, no subscription |
Which one fits you
Pick Cotlet if
- you are not a developer, or you do not want to maintain a server
- you need it to keep working when LiveChat (Text) changes, without checking it yourself
- your agent or a script should run it on a schedule, also while your computer is off
Pick an open-source server if
- you are comfortable installing, updating and fixing it yourself
- you want your sign-in to stay on your own computer
- you only need it now and then, from one MCP client
How much does the LiveChat (Text) API cost?
Free 7-day trial with 2,000 credits, no card needed. After that, the LiveChat (Text) API is pay as you go with no limit on apps: Credit packs from $29 for 5,000 credits, one-time, no subscription. A successful call uses 10 to 100 credits (10 for most tools, about $0.04 to $0.06), your Cloud Browser uses 50 credits a day while it has an app enabled for agents, however many apps that is, and an agent driving the browser itself uses 5 credits a minute. Credit packs stay valid for 12 months and stack, so unused credits carry over.
| Credits | Price, one time | Calls at 10 credits | Per 1,000 credits |
|---|---|---|---|
| 5,000 | $29 | 500 | $5.80 |
| 15,000 | $79 | 1,500 | $5.27 |
| 32,000 | $149 | 3,200 | $4.66 |
| 60,000 | $249 | 6,000 | $4.15 |
Only successful calls use credits; failed calls and timeouts cost nothing. At a balance of 0 calls pause, never a surprise charge. Authenticate with the Authorization: Bearer header. See full pricing
How Cotlet holds your access
Cotlet hosts MCP servers and REST APIs for apps with no usable API. Your agent works in your own LiveChat (Text) account.
- Company details: Cotlet is run by Take Group sp. z o.o., a company registered in Poland. Its full address and registration numbers are in the Terms of service. Terms of service
- Your sign-in: You sign in to LiveChat (Text) yourself, in your own Cloud Browser: a Chrome we run for you in the EU, one per app. We never save your password (password saving is off), the profile is stored encrypted with AES-256-GCM, and your agents get LiveChat (Text) only after you enable it. When LiveChat (Text) signs you out, your agent gives you a link to sign in again. Security
- Revoking access: Press Disable for agents next to LiveChat (Text), sign out of LiveChat (Text) in your Cloud Browser, or reset the browser. Every background request is listed in your Background activity. Actions that reach other people wait for your OK unless you switch that off per tool.
- What we never do: Store passwords or bypass MFA.
- LiveChat (Text)'s terms: You use your own LiveChat (Text) account and stay responsible for following LiveChat (Text)'s terms. Cotlet is independent and not affiliated with LiveChat (Text). Terms
- Contact: Questions about the company, security or an app: contact@cotlet.dev
LiveChat (Text) API and MCP: questions
How do I get access?
Sign up free, open LiveChat (Text) in the console and press Activate. Then you create your API key and connect LiveChat (Text) there.
Do I need to be technical?
No. You sign in to LiveChat (Text) once in your Cloud Browser, a normal Chrome you open from the console, and paste one command into your agent, or one URL into n8n. Your agent can walk you through it. There is no server to install, update or fix.
Is it safe to connect LiveChat (Text) to Cotlet?
Yes. You sign in to LiveChat (Text) yourself, in your own Cloud Browser in the EU, and we never save your password. Your agents only get LiveChat (Text) once you enable it, every background request is listed, and the browser profile is stored encrypted with AES-256-GCM, the cipher 1Password uses for its vaults. The AI model never sees a login, posts and messages wait for your OK, and Disable for agents cuts access in one click. Independent scanners grade cotlet.dev A+ on Qualys SSL Labs, securityheaders.com and Mozilla Observatory; live results are on https://cotlet.dev/security.
Is a hosted server safer than a local one? My LiveChat (Text) sign-in would leave my computer.
On Cotlet you sign in inside your own Cloud Browser, which only you open, and its profile is stored encrypted with AES-256-GCM in the EU. Agents get only the apps you enable, and every background request is listed. A local server keeps your LiveChat (Text) cookie in a plain file on your computer, readable by any program you run, and stops when your computer is off.
Why does Cotlet send requests instead of clicking in my browser?
To be fast, Cotlet doesn't click through LiveChat (Text)'s pages. It sends the same requests your browser would, from your browser's IP with its cookies, without opening a window. LiveChat (Text) sees the same browser and IP you signed in with, and every request is listed in your Background activity.
What if someone gets my Cotlet API key?
The key holds no LiveChat (Text) login or cookies, it only asks Cotlet to run a tool. It can call only the apps and tools you gave it, and a read-only key changes nothing. Anything that reaches other people, like posts, comments or messages, waits for your OK in the dashboard by default, so a leaked key cannot post or message as you. When you switch approval off for a scheduled job, give that job its own key limited to that one tool. Every call is in your activity log, and deleting the key ends access at once.
Why a signed-in browser and not OAuth, like other integration platforms?
LiveChat (Text) offers no OAuth token you can simply grant for these tools: its official API leaves them out or needs a developer app, a plan or an approval first (see the official API section above). That is why Cotlet sets the limits itself: per key, per tool, with your approval before anything reaches other people. Cotlet is run by Take Group sp. z o.o., an EU company (VAT PL6342984273).
How do I connect LiveChat (Text) to ChatGPT or Claude?
Sign up at cotlet.dev, log in to LiveChat (Text) once in its Cloud Browser and add Cotlet to ChatGPT or Claude, following the steps in your console. No API key is needed. ChatGPT and Claude then work in your LiveChat (Text) account through Cotlet, in their phone apps too.
What can ChatGPT do in LiveChat (Text)?
With Cotlet, ChatGPT, Claude and other AI agents handle jobs like these in LiveChat (Text): tag and archive finished chats; answer chats that came in while the team was offline; turn repeated answers into canned responses. You ask in plain words, and anything that reaches other people waits for your OK first.
Can my agent work LiveChat tickets?
These tools cover chats, tags and canned responses. LiveChat's own ticketing is a legacy system that was retired from January 2025, depending on the plan, and accounts created after 1 June 2023 use HelpDesk for tickets. The official MCP lists ticket tools, but only to read.
Which LiveChat plan do I need?
Chats, tags and transfers work on every plan. Canned responses need Team, Business or Enterprise, and private notes on a transfer need Business or Enterprise. Tag creation is an admin task in Settings > Tags, so a normal agent account can use tags but not add them.
Can my agent post or send messages in LiveChat (Text) without asking me?
No. Every call to send_message, send_private_note, transfer_chat, archive_chat or save_canned_response waits for your OK by default. For scheduled automations you can switch confirmation off per tool in your dashboard, for example only for approvals. tag_chat runs without asking, because it sends nothing to anyone and one call undoes it.
Can I use the LiveChat (Text) API in n8n?
Yes. Add https://cotlet.dev/mcp/v1 with your API key in n8n's MCP Client node, or call its endpoints under https://cotlet.dev/api/v1/livechat from the HTTP Request node.
Can I use the LiveChat (Text) API without an AI agent?
Yes. Call Cotlet's REST API from a script or an HTTP step in n8n, Make or Zapier with your Cotlet key. MCP is the alternative for AI agents; you do not need to connect an agent to use REST.
Give your AI agents your signed-in browser.
Product: Integrations · How it works · Pricing · Security
Resources: Blog · API docs · Help center · Changelog · GitHub
Solutions: For developers · For automation agencies
Company: About · AI info: company facts · Contact
Legal: Terms of service · Privacy policy · Refund policy · Acceptable use · Cookie policy · DPA · Subprocessors
Elsewhere: Status page · Cotlet on GitHub · Cotlet on X · Cotlet on LinkedIn · Cotlet on Product Hunt · Cotlet on Crunchbase · Cotlet on SaaSHub
Cotlet.dev is built by Bart Krawczyk and Jake Slugocki, the founders of Take Group sp. z o.o., ul. Wincentego Janasa 4, 40-855 Katowice, Poland. KRS 0000871398, NIP 6342984273, VAT EU: PL6342984273. About us
Cotlet is an independent service. It is not affiliated with, endorsed by or sponsored by any of the products listed on this site. Product names are trademarks of their respective owners.