[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)

# Kustomer API and MCP server

> Kustomer has a full REST API with API keys, and an official MCP server that is read-only (checked 17 Oct 2026). The MCP server searches and reads conversations, messages, customers, companies, notes, custom objects and workflows. It cannot reply, add notes, tag, snooze, merge or close. Kustomer says writes are coming, with no date.

Customer service platform that keeps every email, chat, SMS and call with a customer in one timeline, with conversations, internal notes, queues, business rules and workflows.

## What is the Kustomer API?

Cotlet's Kustomer API exposes 12 endpoints for your own Kustomer account: search conversations, get conversation, get conversation messages, search customers, get customer, list tags, reply to conversation, add internal note, add tags to a conversation, snooze conversation, mark conversation done and merge conversations. The search_conversations endpoint returns conversations that match a status, tag, customer or update date, with the newest update first. Each endpoint takes simple JSON inputs like conversation_id, cursor or tag and works both as an operation of the kustomer_read or kustomer_write MCP tool for agents and as a REST call for scripts.

- **Category:** [Customer support](https://cotlet.dev/integrations/category/customer-support.md)
- **Endpoints:** 12 (6 read, 6 write)
- **Updated:** 2026-10-22

Kustomer has a full REST API with API keys, and an official MCP server that is read-only (checked 17 Oct 2026). Cotlet is a hosted MCP server and REST API for Kustomer with 12 endpoints (6 read, 6 write): you sign in once in your own cloud browser, your AI agent does the work.

## Does Kustomer have an official API?

Kustomer has a full REST API with API keys, and an official MCP server that is read-only (checked 17 Oct 2026). The MCP server searches and reads conversations, messages, customers, companies, notes, custom objects and workflows. It cannot reply, add notes, tag, snooze, merge or close. Kustomer says writes are coming, with no date.

| Task | Kustomer official | Cotlet |
|---|---|---|
| Search conversations and customers | Yes: REST API, and the official MCP server (read-only) | Yes |
| Read a conversation with its messages | Yes: REST API, and the official MCP server (read-only) | Yes |
| Reply to the customer | Partly: REST API only; the official MCP server cannot write | Yes |
| Add an internal note | Partly: REST API only; the MCP server only searches notes | Yes |
| Tag a conversation | Partly: REST API only; you wire the API key and its role yourself | Yes |
| Snooze a conversation or mark it done | Partly: REST API only, through a conversation update | Yes |
| Merge two conversations | Partly: REST API only; the MCP server has no merge tool | Yes |

Sources: [Kustomer Help: What is the Kustomer MCP Server?](https://help.kustomer.com/en_us/kustomer-mcp-server-r1CR1NpTgx), [Kustomer Help: Understanding the Kustomer MCP Server tools](https://help.kustomer.com/en_us/understanding-the-kustomer-mcp-server-tools-ry1KuLVXMx), [Kustomer developers: Authentication and API keys](https://developer.kustomer.com/kustomer-api-docs/reference/authentication), [Kustomer developers: Rate limiting](https://developer.kustomer.com/kustomer-api-docs/reference/rate-limiting)

## For AI agents

```text
Kustomer has a full REST API with API keys, and an official MCP server that is read-only (checked 17 Oct 2026). The MCP server searches and reads conversations, messages, customers, companies, notes, custom objects and workflows. It cannot reply, add notes, tag, snooze, merge or close. Kustomer says writes are coming, with no date.
Cotlet provides a hosted MCP server and REST API for Kustomer: 12 tools (6 read, 6 write).
Access       Sign up at https://cotlet.dev/app/signup?app=kustomer, then request the app and create API keys in the Cotlet console.

MCP server   https://cotlet.dev/mcp/v1
MCP tools    kustomer_read, kustomer_write, reads and writes apart; call one with {"operation": "<operation>", "arguments": {...}}
REST base    https://cotlet.dev/api/v1/kustomer, each operation at its own route, e.g. POST /api/v1/kustomer/conversations/{conversation_id}/replies
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   search_conversations, get_conversation, get_conversation_messages, search_customers, get_customer, list_tags, reply_to_conversation, add_note, add_tags, snooze_conversation, mark_conversation_done, merge_conversations
Confirm      reply_to_conversation, add_note, merge_conversations (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/kustomer-api-mcp-server.md

How access works:
1. The user signs up at https://cotlet.dev/app/signup?app=kustomer, requests Kustomer in the Cotlet console and creates an API key there.
2. The user signs in to Kustomer once in their Cotlet Cloud Browser (their own Chrome in the cloud, opened from the console) and enables Kustomer for agents. An agent cannot do this step.
3. The API key goes into the MCP client or the REST call as a bearer token.

Fits: people who want a hosted Kustomer 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 Kustomer MCP server instead.

Policy: Cotlet never stores passwords, never solves CAPTCHAs, 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 Kustomer 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 Kustomer 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 Kustomer 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 Kustomer's terms; Cotlet is not affiliated with Kustomer.
```

## What can an AI agent do in Kustomer?

Cotlet is best for support leads and small teams who want an AI agent to merge duplicates, chase snoozed conversations and write handoff notes in Kustomer without running or fixing a server, or asking an admin for an API key.

- **[Merge duplicate conversations](https://cotlet.dev/integrations/kustomer-api-mcp-server/merge-duplicate-conversations.md)** (runs: weekly): "Find customers in Kustomer who have two or more open conversations about the same issue this week. Merge the newer ones into the oldest and leave an internal note on the one that stays. List anything you are unsure about instead." → `search_conversations`, `get_conversation_messages`, `merge_conversations`, `add_note`
- **[Follow up on snoozed conversations](https://cotlet.dev/integrations/kustomer-api-mcp-server/follow-up-on-snoozed-conversations.md)** (runs: daily): "Find Kustomer conversations that have been snoozed for more than 5 days where the customer has not written back. Send one short reminder that quotes what we asked for, then mark them done after a second silence. If we already sent a reminder, list the conversation for me instead." → `search_conversations`, `get_conversation_messages`, `reply_to_conversation`, `mark_conversation_done`
- **[Add handoff notes to conversations](https://cotlet.dev/integrations/kustomer-api-mcp-server/add-handoff-notes-to-conversations.md)** (runs: daily): "For each Kustomer conversation that changed owner today, read the thread and the customer profile, then add an internal note with the issue, what was already tried and what the customer expects next. Do not write to the customer." → `search_conversations`, `get_conversation_messages`, `get_customer`, `add_note`
- **Tag conversations by topic** (runs: daily): "Read new Kustomer conversations from today. Add the tag that fits the topic (billing, shipping, bug or feature-request) using tags that already exist, and leave unclear ones for me." → `search_conversations`, `get_conversation_messages`, `list_tags`, `add_tags`
- **Weekly conversation backlog report** (runs: weekly): "Every Monday, tell me how many Kustomer conversations are open and snoozed, the oldest open one, and which tagged conversations from companies tagged enterprise have had no reply." → `search_conversations`, `get_conversation`, `list_tags`

## Can Kustomer automations run on a schedule in n8n, Make or Zapier?

Yes. Cotlet does not replace your automation platform: it gives it a Kustomer 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 merge duplicate conversations, 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/kustomer/conversations/search. | 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/kustomer/conversations/search 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 Kustomer.

### search_conversations

Conversations that match a status, tag, customer or update date, with the newest update first. Access: read. REST: `GET /api/v1/kustomer/conversations/search`. MCP: `kustomer_read → search_conversations`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `status` | enum | no | open, snoozed or done. |
| `tag` | string | no | Only conversations with this tag. |
| `customer_id` | string | no | Only conversations of this customer. |
| `updated_before` | string | no | ISO date. Only conversations whose last update is earlier. |
| `updated_after` | string | no | ISO date. Only conversations whose last update is later. |
| `limit` | integer | no | Results per page. Default: 25. |
| `cursor` | string | no | Next page cursor from the previous call. |

Searches your Kustomer conversations and returns the matches without messages, sorted by most recent update. Filter by status (open, snoozed or done), tag, customer and the date of the last update. Pass next_cursor back as cursor for the next page. Use get_conversation for the full record and get_conversation_messages for the thread.

Example response:

```json
{
  "conversations": [
    {
      "conversation_id": "6718d2e4a1b2c3d4e5f60733",
      "name": "Export fails with an error",
      "status": "snoozed",
      "customer": {
        "customer_id": "6712a0b4a1b2c3d4e5f60101",
        "name": "Dana Whitfield"
      },
      "tags": [
        "export",
        "bug"
      ],
      "channel": "email",
      "updated_at": "2026-10-11T09:30:00Z"
    }
  ],
  "next_cursor": null
}
```

### get_conversation

One conversation with status, priority, assignment, tags and linked conversations. Access: read. REST: `GET /api/v1/kustomer/conversations/{conversation_id}`. MCP: `kustomer_read → get_conversation`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `conversation_id` | string | yes | Conversation ID from search_conversations. |

Returns one conversation with its status, priority, assigned user or team, tags and the customer it belongs to. It does not include the messages, so use get_conversation_messages for the thread. Use it before a write to check that nobody changed the conversation since you searched.

Example response:

```json
{
  "conversation_id": "6718d2e4a1b2c3d4e5f60733",
  "name": "Export fails with an error",
  "status": "snoozed",
  "priority": 3,
  "assigned_to": "Sam Okafor",
  "assigned_team": "Support",
  "customer": {
    "customer_id": "6712a0b4a1b2c3d4e5f60101",
    "name": "Dana Whitfield"
  },
  "tags": [
    "export",
    "bug"
  ],
  "merge_locked": false,
  "created_at": "2026-10-10T08:55:00Z",
  "updated_at": "2026-10-11T09:30:00Z"
}
```

### get_conversation_messages

The message thread of a conversation, oldest first, with channel and direction. Access: read. REST: `GET /api/v1/kustomer/conversations/{conversation_id}/messages`. MCP: `kustomer_read → get_conversation_messages`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `conversation_id` | string | yes | Conversation ID from search_conversations. |
| `direction` | enum | no | in or out. Default: both. |
| `channel` | string | no | Only messages on this channel, e.g. email or sms. |
| `cursor` | string | no | Next page cursor from the previous call. |

Returns the messages and internal notes of one conversation in chronological order. Each message says whether it is inbound or outbound, the channel (email, chat, SMS and so on) and who wrote it. Filter by channel or direction. Pass next_cursor back as cursor for the next page of a long thread.

Example response:

```json
{
  "messages": [
    {
      "message_id": "6718d2e4a1b2c3d4e5f60801",
      "direction": "in",
      "channel": "email",
      "author": "Dana Whitfield",
      "body": "Export to CSV fails every time.",
      "created_at": "2026-10-10T08:55:00Z"
    },
    {
      "message_id": "6718d2e4a1b2c3d4e5f60802",
      "direction": "out",
      "channel": "email",
      "author": "Sam Okafor",
      "body": "Sorry about that. Can you send the order number from your confirmation email?",
      "created_at": "2026-10-11T09:30:00Z"
    }
  ],
  "next_cursor": null
}
```

### search_customers

Customers by name, email, tag or company, with their open conversation count. Access: read. REST: `GET /api/v1/kustomer/customers/search`. MCP: `kustomer_read → search_customers`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `query` | string | yes | Name, email, phone or company name. |
| `tag` | string | no | Only customers with this tag. |
| `limit` | integer | no | Results per page. Default: 25. |
| `cursor` | string | no | Next page cursor from the previous call. |

Searches customer profiles by name, email address, phone, tag or company and returns the matches with contact details. Use customer_id with get_customer for the full profile or with search_conversations for their conversations. Pass next_cursor back as cursor for the next page.

Example response:

```json
{
  "customers": [
    {
      "customer_id": "6712a0b4a1b2c3d4e5f60101",
      "name": "Dana Whitfield",
      "email": "dana@example.com",
      "company": "Northwind Studio",
      "tags": [
        "vip"
      ]
    }
  ],
  "next_cursor": null
}
```

### get_customer

One customer profile with contact details, company, tags and recent conversations. Access: read. REST: `GET /api/v1/kustomer/customers/{customer_id}`. MCP: `kustomer_read → get_customer`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `customer_id` | string | yes | Customer ID from search_customers or get_conversation. |

Returns the profile of one customer: contact details, company, tags, custom attributes and their most recent conversations. Use it to give a note or a reply the context from the profile. Fields your Kustomer does not use come back empty.

Example response:

```json
{
  "customer_id": "6712a0b4a1b2c3d4e5f60101",
  "name": "Dana Whitfield",
  "emails": [
    "dana@example.com"
  ],
  "company": "Northwind Studio",
  "tags": [
    "vip"
  ],
  "recent_conversations": [
    {
      "conversation_id": "6718d2e4a1b2c3d4e5f60733",
      "name": "Export fails with an error",
      "status": "snoozed"
    },
    {
      "conversation_id": "6718d2e4a1b2c3d4e5f60711",
      "name": "Export fails",
      "status": "open"
    }
  ]
}
```

### list_tags

Active conversation tags with their names. Access: read. REST: `GET /api/v1/kustomer/tags`. MCP: `kustomer_read → list_tags`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `query` | string | no | Only tags whose name contains this text. |

Lists the conversation tags your organization uses. Tags are shared across the whole organization, and deactivated tags are left out because they can no longer be added or removed. Use the names with add_tags.

Example response:

```json
{
  "tags": [
    {
      "name": "billing"
    },
    {
      "name": "shipping"
    },
    {
      "name": "bug"
    },
    {
      "name": "feature-request"
    }
  ]
}
```

### reply_to_conversation

Send a reply to the customer on the channel of the last message. Access: write, asks the user first. REST: `POST /api/v1/kustomer/conversations/{conversation_id}/replies`. MCP: `kustomer_write → reply_to_conversation`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `conversation_id` | string | yes | Conversation ID from search_conversations. |
| `body` | string | yes | Reply text, sent to the customer. |

Sends a reply in the conversation, which reaches the customer on the channel of the last message. A reply is limited to 10,240 characters on email and chat, 1,600 on text/SMS and 2,000 on Facebook DM, and the call fails with the limit if your text is longer. The conversation status is not changed, so use snooze_conversation or mark_conversation_done after it. By default you confirm each call; you can switch that off for this tool.

Example response:

```json
{
  "conversation_id": "6718d2e4a1b2c3d4e5f60733",
  "message_id": "6720b1c7a1b2c3d4e5f60844",
  "channel": "email",
  "direction": "out",
  "status": "snoozed",
  "created_at": "2026-10-17T09:00:00Z"
}
```

### add_note

Add a note only people in your organization can see. Access: write, asks the user first. REST: `POST /api/v1/kustomer/conversations/{conversation_id}/notes`. MCP: `kustomer_write → add_note`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `conversation_id` | string | yes | Conversation ID from search_conversations. |
| `body` | string | yes | Note text, visible inside your organization only. |

Adds an internal note to the conversation, visible only to users in your organization and never sent to the customer. A note holds at most 10,240 characters. Mention a user or team with @ and the name: each mention is notified, up to 20 per note, which is why this call asks first. A note can be edited or deleted in Kustomer afterwards. By default you confirm each call; you can switch that off for this tool.

Example response:

```json
{
  "conversation_id": "6718d2e4a1b2c3d4e5f60711",
  "note_id": "6720b1d0a1b2c3d4e5f60855",
  "internal": true,
  "created_at": "2026-10-17T09:01:00Z"
}
```

### add_tags

Add existing tags to one conversation and keep the others. Access: write. REST: `POST /api/v1/kustomer/conversations/{conversation_id}/tags`. MCP: `kustomer_write → add_tags`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `conversation_id` | string | yes | Conversation ID from search_conversations. |
| `add_tags` | string[] | yes | Tag names to add. |
| `remove_tags` | string[] | no | Tag names to remove. |

Adds tags to a conversation and keeps the ones already there. A conversation holds at most 20 tags and a tag name is at most 64 characters. Use names from list_tags: a deactivated tag cannot be added. Tags reach no customer and one call removes them again with remove_tags, so this call does not ask for confirmation. Your business rules and workflows run as usual after a tag change.

Example response:

```json
{
  "conversation_id": "6718d2e4a1b2c3d4e5f60733",
  "tags": [
    "export",
    "bug",
    "billing"
  ],
  "updated_at": "2026-10-17T09:02:00Z"
}
```

### snooze_conversation

Snooze a conversation until a time or until the customer replies. Access: write. REST: `POST /api/v1/kustomer/conversations/{conversation_id}/snooze`. MCP: `kustomer_write → snooze_conversation`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `conversation_id` | string | yes | Conversation ID from search_conversations. |
| `until` | string | no | ISO date and time when it returns to Open. Leave out to snooze until the customer replies. |

Sets the status to Snoozed. Choose a date and time to return to Open, or snooze until the customer replies. When the snooze ends, the assigned user gets an email and a notification. Snoozing reaches no customer and one more call removes it, so this call does not ask for confirmation. Your workflows run as usual after the status change.

Example response:

```json
{
  "conversation_id": "6718d2e4a1b2c3d4e5f60733",
  "status": "snoozed",
  "snooze_until": "2026-10-20T09:00:00Z",
  "updated_at": "2026-10-17T09:03:00Z"
}
```

### mark_conversation_done

Set a conversation to Done. Access: write. REST: `POST /api/v1/kustomer/conversations/{conversation_id}/done/mark`. MCP: `kustomer_write → mark_conversation_done`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `conversation_id` | string | yes | Conversation ID from search_conversations. |

Sets the status to Done, meaning no further action is needed. A Done conversation can be reopened, and an email reply from the customer reopens it with no time limit. For chat and SMS a new conversation starts after about 24 hours of inactivity. This call reaches no one and is undone by reopening, so it does not ask for confirmation. Your workflows run as usual after the status change.

Example response:

```json
{
  "conversation_id": "6718d2e4a1b2c3d4e5f60733",
  "status": "done",
  "updated_at": "2026-10-17T09:04:00Z"
}
```

### merge_conversations

Merge one conversation into another of the same customer. Access: write, asks the user first. REST: `POST /api/v1/kustomer/target-conversations/{target_conversation_id}/conversations/merge`. MCP: `kustomer_write → merge_conversations`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `target_conversation_id` | string | yes | Conversation that stays and receives the merge. |
| `source_conversation_id` | string | yes | Conversation that is merged into the target. |

Merges the source conversation into the target. A merge is permanent and cannot be undone: all messages and notes from both appear in one thread in chronological order, but data on the source conversation is not carried over. A conversation with mergeLocked set is refused. By default you confirm each call; you can switch that off for this tool.

Example response:

```json
{
  "target_conversation_id": "6718d2e4a1b2c3d4e5f60711",
  "source_conversation_id": "6719a8c0a1b2c3d4e5f60722",
  "status": "merged",
  "updated_at": "2026-10-17T09:05:00Z"
}
```

## How do I connect Kustomer to Claude Code, Codex or Cursor?

Connecting Kustomer takes three steps: sign up, sign in to Kustomer once in your Cloud Browser and enable it for agents, then add one MCP server or call the REST API with the same key.

### Connect Kustomer to your agent.

1. **Create an account** Sign up and add Kustomer in the console. Your API key is there too.

2. **Sign in to Kustomer in your Cloud Browser** Open your Cloud Browser in the console: your own Chrome in the cloud. Sign in to Kustomer 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.

3. **Add Cotlet to your agent** Paste the snippet for your client. The same server and key serve every app you connect, so you do this once.

   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"
```

4. **Ask your agent** Ask in plain words. Your agent finds the Kustomer 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.

```
Find customers in Kustomer who have two or more open conversations about the same issue this week. Merge the newer ones into the oldest and leave an internal note on the one that stays. List anything you are unsure about instead.
```

### Call Kustomer from your scripts.

1. **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_..."
```

2. **Call a tool** Every tool is an endpoint under /api/v1/kustomer 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/kustomer/conversations/6718d2e4a1b2c3d4e5f60733/replies \
  -H "Authorization: Bearer $COTLET_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"body":"Hi Dana, just checking in. To fix the export we still need the order number from your confirmation email. Reply here when you have it."}'
```

3. **Read the result** You get plain JSON back, ready for your script. A failed call costs nothing.

```
{
  "conversation_id": "6718d2e4a1b2c3d4e5f60733",
  "message_id": "6720b1c7a1b2c3d4e5f60844",
  "channel": "email",
  "direction": "out",
  "status": "snoozed",
  "created_at": "2026-10-17T09:00:00Z"
}
```

## Why use Cotlet for Kustomer?

**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 Claude Code, Codex and Cursor.

**Your login stays yours**

- You sign in to Kustomer 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 CAPTCHA solving, 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 Kustomer changes, the tool pauses until we fix it.
- Failed calls cost nothing.

## Is it safe to connect Kustomer to Cotlet?

Yes. You sign in to Kustomer yourself, in your own Cloud Browser, and we never save your password. Your agents only get Kustomer 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](https://www.ssllabs.com/ssltest/analyze.html?d=cotlet.dev)
- **A+ on securityheaders.com**: Browser protections sent with every page, all six headers present. [Live result](https://securityheaders.com/?q=cotlet.dev&followRedirects=on)
- **A+ on Mozilla Observatory**: Mozilla's web security baseline: score 120 of 100, 12 of 12 tests passed. [Live result](https://developer.mozilla.org/en-US/observatory/analyze?host=cotlet.dev)
- **Clean on Sucuri SiteCheck**: No malware, spam or defacement, and not on any of 9 blocklists, Google Safe Browsing included. [Live result](https://sitecheck.sucuri.net/results/cotlet.dev)

[How Cotlet protects your access](https://cotlet.dev/security.md)

### 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 Kustomer integration?**

No, Cotlet is independent of Kustomer. Kustomer's own API is too limited for this work. Cotlet works through your own Kustomer account, the way you use Kustomer in the browser, so you need no partner approval and no developer setup.

**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 Kustomer in your console: your agents lose access at once and you stay signed in. Signing out of Kustomer in the browser works too, and Reset browser deletes the whole profile.

## Is there a Kustomer MCP server on GitHub?

Yes. Community Kustomer MCP servers and scripts exist on GitHub, usually maintained by one person. You install one yourself, give it an API key, and fix it when Kustomer changes. Cotlet hosts the same kind of server for you, signs in as your agent user, and our team keeps it working.

|  | GitHub MCP server | Cotlet |
|---|---|---|
| Setup | Clone the repo, ask an admin for an API key with the right roles, store it, add the server to each MCP client | Sign up, sign in to Kustomer once, add one MCP server or API key |
| When Kustomer 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 Kustomer access | An org API key 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 someone creates a new key or you sign in again by hand | Your Cloud Browser keeps you signed in; if Kustomer 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 Kustomer 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 Kustomer API cost?

Free 7-day trial with 2,000 credits, no card needed. After that, the Kustomer 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 20 to 30 credits (25 for most tools, about $0.10 to $0.15), 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 25 credits | Per 1,000 credits |
|---|---|---|---|
| 5,000 | $29 | 200 | $5.80 |
| 15,000 | $79 | 600 | $5.27 |
| 32,000 | $149 | 1,280 | $4.66 |
| 60,000 | $249 | 2,400 | $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](https://cotlet.dev/pricing.md)

## How Cotlet holds your access

Cotlet hosts MCP servers and REST APIs for apps with no usable API. Your agent works in your own Kustomer 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](https://cotlet.dev/terms)
- **Your sign-in:** You sign in to Kustomer 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 Kustomer only after you enable it. When Kustomer signs you out, your agent gives you a link to sign in again. [Security](https://cotlet.dev/security.md)
- **Revoking access:** Press Disable for agents next to Kustomer, sign out of Kustomer 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, solve CAPTCHAs or bypass MFA.
- **Kustomer's terms:** You use your own Kustomer account and stay responsible for following Kustomer's terms. Cotlet is independent and not affiliated with Kustomer. [Terms](https://cotlet.dev/terms)
- **Contact:** Questions about the company, security or an app: [contact@cotlet.dev](mailto:contact@cotlet.dev)

## Frequently asked questions

**How do I get access?**

Sign up free, open Kustomer in the console and press Request access. Then you create your API key and connect Kustomer there.

**Do I need to be technical?**

No. You sign in to Kustomer 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 Kustomer to Cotlet?**

Yes. You sign in to Kustomer yourself, in your own Cloud Browser in the EU, and we never save your password. Your agents only get Kustomer 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 Kustomer 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 Kustomer 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 Kustomer's pages. It sends the same requests your browser would, from your browser's IP with its cookies, without opening a window. Kustomer 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 Kustomer 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?**

Kustomer 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).

**Can the official Kustomer MCP server do this?**

It reads, it does not write. The tools search and read conversations, messages, customers, companies, notes, custom objects and workflows. Setup also needs an admin to install the Kustomer MCP server app from the Application Store and an admin workspace in ChatGPT or Claude (Kustomer Help: Using the Kustomer MCP Server).

**Do I need an API key for Cotlet?**

No. Cotlet works through your own Kustomer login, so nobody creates an API key under Settings > Security > API Keys or picks its roles. API keys have their own limits per plan, from 300 to 2,000 requests per minute (Kustomer developers: Rate limiting).

**Will my agent message customers without asking?**

Only if you switch confirmation off. By default every reply, note and merge waits for your OK. A merge is permanent (Kustomer Help: Merging conversations).

**Can my agent post or send messages in Kustomer without asking me?**

No. Every call to reply_to_conversation, add_note or merge_conversations waits for your OK by default. For scheduled automations you can switch confirmation off per tool in your dashboard, for example only for approvals. add_tags, snooze_conversation, mark_conversation_done runs without asking, because it sends nothing to anyone and one call undoes it.

**Can I use the Kustomer 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/kustomer from the HTTP Request node.

---

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.