[Cotlet](https://cotlet.dev/index.md) · [Integrations](https://cotlet.dev/integrations.md) · [How it works](https://cotlet.dev/how-it-works.md) · [Use cases](https://cotlet.dev/use-cases.md) · [Security](https://cotlet.dev/security.md) · [For developers](https://cotlet.dev/for-developers.md) · [For automation agencies](https://cotlet.dev/for-agencies.md) · [Blog](https://cotlet.dev/blog.md) · [API docs](https://cotlet.dev/docs.md) · [Help center](https://cotlet.dev/help.md) · [Changelog](https://cotlet.dev/changelog.md) · [Contact](https://cotlet.dev/contact.md) · [Pricing](https://cotlet.dev/pricing.md) · [Sign up](https://cotlet.dev/signup)

# Tag and archive finished LiveChat chats

> Tag every finished LiveChat chat with a topic from your own tag list, then close and archive it, so Archives and tag reports stay usable. Runs daily.

Source: https://cotlet.dev/integrations/livechat-api-mcp-server/tag-and-archive-chats

At the end of the shift the My chats list still holds a dozen finished conversations, and each one needs a topic tag and a Close and archive click before Archives and the tag reports show anything useful.

Cotlet does it in your own LiveChat (Text) account with list\_chats, get\_chat, list\_tags, tag\_chat and archive\_chat, called by your AI agent, an n8n workflow or a script.

[Sign up free](https://cotlet.dev/app/signup?app=livechat) [All LiveChat (Text) tools](https://cotlet.dev/integrations/livechat-api-mcp-server.md)

Hosted · nothing to install or maintain

## Can LiveChat (Text) do this on its own?

LiveChat offers tag suggestions on the Team, Business and Enterprise plans once you have tagged at least 100 chats (checked 17 Oct 2026). A suggestion still needs an agent click per chat. The official MCP can list a chat's tags but not set them, and the Agent Chat API has tag\_thread, which you call with your own token and code.

## How you do it in LiveChat (Text) today

1. In the Chats section, an agent opens a finished chat in My chats and clicks the Add tag link at the bottom of the page, then picks one or more tags from the list.
2. Tags come from Settings > Tags, where only admins and the owner can add them, up to 70 characters each, optionally limited to one group.
3. The agent then hovers over the customer name and clicks x > Close and archive, or opens the three dots menu and chooses Stop this chat > Stop chat.
4. When an agent archives an untagged chat, LiveChat can show a short reminder to tag it first, so the tag is a manual step on every conversation.
5. Later, Archives filters by Tags with Match all or Match any, which only helps if the tagging was done and done the same way each time.

## How to tag and archive finished LiveChat chats

Prompt

```
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.
```

1. 01  
### Find chats that are over  
list\_chats reads My chats and your agent keeps the chats where the last message is from the customer long ago or the customer said goodbye. Active conversations are never touched.
2. 02  
### Learn the tag list first  
list\_tags returns the tags your role can see, so the agent only uses names that exist. It never invents a tag, because creating tags is an admin task in Settings > Tags.
3. 03  
### Read before tagging  
get\_chat returns the transcript, and the agent picks the tags that match what was asked, for example refund or shipping. A chat that fits no tag is listed for you.
4. 04  
### Tag, then archive  
tag\_chat adds the tags and archive\_chat closes the chat. Tags go first, so a stopped run leaves a tagged chat and never an archived chat without a tag. Closing ends the chat for the customer, so it waits for your OK by default.
5. 05  
### Report what was left  
Chats with no fitting tag, and chats that had new messages in the meantime, stay open and come back in the summary.

### What you get back

Example data

```
Open chats checked: 14
Tagged and archived 11, e.g. PJ0MRSHTDG tagged refund
Left open because the customer is still writing: 2
Left for you, no fitting tag: 1 ("question about a reseller contract")
```

### Other ways to ask

- Every evening, tag chats from the last 24 hours that mention a refund with the refund tag, but do not archive them.
- List the archived chats from last week that have no tag at all and tag them from the transcript.
- Show me how many chats got each tag this week, using Archives, and name the busiest topic.

## What LiveChat (Text) allows, and what to know first

- LiveChat tags are created in Settings > Tags by admins and the owner, with a name of up to 70 characters, so a non-admin account can use tags but not add new ones.
- A tag can be limited to one group; only agents in that group see it, while admins and the owner see all tags.
- Archives has a Tags filter with Match all and Match any, so a tag set once can be searched later by one topic or by a combination.
- Tag suggestions start after you have tagged at least 100 chats and are offered on Team, Business and Enterprise.
- Inactive chats, greyed out at the bottom of My chats, do not count toward the concurrent chats limit.

archive\_chat asks for your OK by default. To run it daily without you, switch confirmation off for that tool in your dashboard.

Sources: [LiveChat Help: Using tags for chats and tickets](https://www.livechat.com/help/tagging-chats-and-tickets/) · [LiveChat Help: Chats section](https://www.livechat.com/help/how-to-chat-section/) · [LiveChat Help: Archives section explained](https://www.livechat.com/help/archives-overview/) · [Text Platform: MCP server](https://platform.text.com/docs/guides/mcp)

## Call tag\_chat from a script

curl

```
curl -X POST https://cotlet.dev/api/v1/livechat/chats/PJ0MRSHTDG/tag \
  -H "Authorization: Bearer $COTLET_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"add":["refund"]}'
```

Example response

```
{
"chat_id": "PJ0MRSHTDG",
"added": [
"refund"
],
"removed": [],
"tags": [
"refund"
]
}
```

MCP: add https://cotlet.dev/mcp/v1 with the same key; the call is livechat\_write → tag\_chat. Example data.

[Schedule it in n8n, Make, Zapier or cron](https://cotlet.dev/integrations/livechat-api-mcp-server.md#automations)

## LiveChat (Text) tools this automation uses

__Cotlet LiveChat (Text) tools used to tag and archive finished LiveChat chats__
| Tool | Parameters |
| ------------- | --------------------- |
| list\_chats | list, limit, cursor |
| get\_chat | chat\_id |
| list\_tags | none |
| tag\_chat | chat\_id, add, remove |
| archive\_chat | chat\_id |

[All 12 LiveChat (Text) tools with descriptions](https://cotlet.dev/integrations/livechat-api-mcp-server.md#tools)

## Frequently asked questions

### 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.

## More LiveChat (Text) automations

- [Answer unassigned LiveChat chats from the offline hours](https://cotlet.dev/integrations/livechat-api-mcp-server/answer-unassigned-chats.md)
- [Build LiveChat canned responses from past chats](https://cotlet.dev/integrations/livechat-api-mcp-server/build-canned-responses.md)
- [LiveChat (Text) API and MCP server: every tool](https://cotlet.dev/integrations/livechat-api-mcp-server.md)
- [All use cases](https://cotlet.dev/use-cases.md)

## Give your agent access to LiveChat (Text).

Free 7-day trial with 2,000 credits, no card needed. Cotlet is independent and not affiliated with LiveChat (Text).

[Sign up free](https://cotlet.dev/app/signup?app=livechat)

---

Give your AI agents your signed-in browser.

**Product:** [Integrations](https://cotlet.dev/integrations.md) · [Use cases](https://cotlet.dev/use-cases.md) · [How it works](https://cotlet.dev/how-it-works.md) · [Pricing](https://cotlet.dev/pricing.md) · [Security](https://cotlet.dev/security.md)

**Resources:** [Blog](https://cotlet.dev/blog.md) · [API docs](https://cotlet.dev/docs.md) · [Help center](https://cotlet.dev/help.md) · [Changelog](https://cotlet.dev/changelog.md) · [GitHub](https://github.com/cotletdev/cotlet)

**Solutions:** [For developers](https://cotlet.dev/for-developers.md) · [For automation agencies](https://cotlet.dev/for-agencies.md)

**Company:** [About](https://cotlet.dev/about.md) · [AI info: company facts](https://cotlet.dev/ai-info.md) · [Contact](https://cotlet.dev/contact.md)

**Legal:** [Terms of service](https://cotlet.dev/terms) · [Privacy policy](https://cotlet.dev/privacy) · [Refund policy](https://cotlet.dev/refunds) · [Acceptable use](https://cotlet.dev/acceptable-use) · [Cookie policy](https://cotlet.dev/cookies) · [DPA](https://cotlet.dev/dpa) · [Subprocessors](https://cotlet.dev/subprocessors)

**Elsewhere:** [Status page](https://status.cotlet.dev) · [Cotlet on GitHub](https://github.com/cotletdev) · [Cotlet on X](https://x.com/cotletdev) · [Cotlet on LinkedIn](https://www.linkedin.com/company/cotletdev) · [Cotlet on Product Hunt](https://www.producthunt.com/products/cotlet) · [Cotlet on Crunchbase](https://www.crunchbase.com/organization/cotlet) · [Cotlet on SaaSHub](https://www.saashub.com/cotlet)

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.

## For AI agents: sign your user up

Is your user asking you to sign them up for Cotlet? You can do it for them, no account or key needed.

1. Read the fields and their allowed values: GET https://cotlet.dev/api/v1/access-requests
2. Ask the user for each value: email, apps, what you will do with them. If they leave the password to you, generate a strong one and show it to them.
3. Show the user what you will send, then POST it as JSON to https://cotlet.dev/api/v1/access-requests.

One call creates the account and sends the access request; we email the user when access is granted.