[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)

# Gladly API and MCP server

> Gladly has a full REST API (version 1.0), but no official MCP server (checked 20 Oct 2026). The developer docs cover the REST API, webhooks and the Lookup API only. An administrator must give you the API User permission before you can create a token.

Customer service platform for retail and consumer brands: one lasting conversation per customer across email, chat, SMS, voice and social, with inboxes, topics and tasks.

## What is the Gladly API?

Cotlet's Gladly API exposes 13 endpoints for your own Gladly account: list my customers, list conversations, search customers, get customer, get conversation, list topics, list inboxes and agents, add note, reply to customer, apply topics, assign conversation, close conversation and create task. The list_my_customers endpoint returns customers with open Conversations and Tasks assigned to you, from your My Customers list. Each endpoint takes simple JSON inputs like conversation_id, body or inbox_id and works both as an operation of the gladly_read or gladly_write MCP tool for agents and as a REST call for scripts.

- **Category:** [Customer support](https://cotlet.dev/integrations/category/customer-support.md)
- **Endpoints:** 13 (7 read, 6 write)
- **Updated:** 2026-10-21

Gladly has a full REST API (version 1.0), but no official MCP server (checked 20 Oct 2026). Cotlet is a hosted MCP server and REST API for Gladly with 13 endpoints (7 read, 6 write): you sign in once in your own cloud browser, your AI agent does the work.

## Does Gladly have an official API?

Gladly has a full REST API (version 1.0), but no official MCP server (checked 20 Oct 2026). The developer docs cover the REST API, webhooks and the Lookup API only. An administrator must give you the API User permission before you can create a token.

| Task | Gladly official | Cotlet |
|---|---|---|
| Find a customer by email address or phone number | Yes: REST API, Find customers | Yes |
| Read a customer's conversations and the items of one conversation | Yes: REST API; the list of a customer's conversations is capped, so long histories come back cut | Yes |
| Reply to a customer | Yes: REST API; the docs say creation does not guarantee delivery | Yes |
| Add an internal note | Yes: REST API | Yes |
| Apply topics, assign or close a conversation | Yes: REST API; assignee and status in one update call | Yes |
| Create a task for a customer | Yes: REST API | Yes |
| List the New, Open and Waiting conversations of an inbox | Partly: The API lists conversations per customer; the status tabs come from the app, reports and webhooks | Yes |
| Read your My Customers list | No | Yes |

Sources: [Gladly developer docs: REST API](https://developer.gladly.com/rest/), [Gladly developer home](https://developer.gladly.com/), [Gladly Help: Conversation Status (New, Open, Waiting, Closed)](https://help.gladly.com/docs/conversation-status-new-open-waiting-closed), [Gladly Help: Manage Your My Customers List](https://help.gladly.com/docs/manage-your-my-customers-list)

## For AI agents

```text
Gladly has a full REST API (version 1.0), but no official MCP server (checked 20 Oct 2026). The developer docs cover the REST API, webhooks and the Lookup API only. An administrator must give you the API User permission before you can create a token.
Cotlet provides a hosted MCP server and REST API for Gladly: 13 tools (7 read, 6 write).
Access       Sign up at https://cotlet.dev/app/signup?app=gladly, then request the app and create API keys in the Cotlet console.

MCP server   https://cotlet.dev/mcp/v1
MCP tools    gladly_read, gladly_write, reads and writes apart; call one with {"operation": "<operation>", "arguments": {...}}
REST base    https://cotlet.dev/api/v1/gladly, each operation at its own route, e.g. POST /api/v1/gladly/conversations/{conversation_id}/notes
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_my_customers, list_conversations, search_customers, get_customer, get_conversation, list_topics, list_assignees, add_note, reply_to_customer, apply_topics, assign_conversation, close_conversation, create_task
Confirm      add_note, reply_to_customer, assign_conversation, close_conversation, create_task (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/gladly-api-mcp-server.md

How access works:
1. The user signs up at https://cotlet.dev/app/signup?app=gladly, requests Gladly in the Cotlet console and creates an API key there.
2. The user signs in to Gladly once in their Cotlet Cloud Browser (their own Chrome in the cloud, opened from the console) and enables Gladly 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 Gladly server that someone else maintains, including non-developers.

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 Gladly 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 Gladly 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 Gladly 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 Gladly's terms; Cotlet is not affiliated with Gladly.
```

## What can an AI agent do in Gladly?

Cotlet is best for support teams and managers who want an AI agent to tag, route, note and follow up on Gladly conversations without running or fixing a server.

- **[Triage new conversations](https://cotlet.dev/integrations/gladly-api-mcp-server/triage-new-conversations.md)** (runs: daily): "Go through the New conversations in the Email Inbox. Apply the topic that fits each one and assign order questions to the Orders inbox. Leave anything unclear for me." → `list_conversations`, `get_conversation`, `list_topics`, `list_assignees`, `apply_topics`, `assign_conversation`
- **[Close resolved conversations](https://cotlet.dev/integrations/gladly-api-mcp-server/close-resolved-conversations.md)** (runs: daily): "Look at the Waiting conversations in the Email Inbox. Close the ones where the customer has not written back in the last 3 days and say how many you closed." → `list_conversations`, `get_conversation`, `add_note`, `close_conversation`
- **[Create follow-up tasks](https://cotlet.dev/integrations/gladly-api-mcp-server/create-follow-up-tasks.md)** (runs: daily): "For every Open conversation tagged Refund Pending, create a task for the Billing inbox due on Friday: "Confirm refund went out". Skip customers who already have one." → `list_conversations`, `get_conversation`, `get_customer`, `create_task`
- **Brief me on a customer before I reply**: "Find the customer with email marco.silva@example.com in Gladly. Summarize their last three conversations, open tasks and what they asked for most recently, then add the summary as a note." → `search_customers`, `get_customer`, `get_conversation`, `add_note`
- **Draft replies for your review** (runs: daily): "Read my open conversations in Gladly. For the simple ones, write a reply in our tone and show it to me. Send only the ones I approve." → `list_my_customers`, `get_conversation`, `reply_to_customer`

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

Yes. Cotlet does not replace your automation platform: it gives it a Gladly 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 triage new 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/gladly/conversations. | 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/gladly/conversations with your API key. | cron or GitHub Actions. |

## Tools

**For AI agents:** Every endpoint and its schema is public. The 13 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 Gladly.

### list_my_customers

Customers with open Conversations and Tasks assigned to you, from your My Customers list. Access: read. REST: `GET /api/v1/gladly/my-customers`. MCP: `gladly_read → list_my_customers`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `kind` | enum | no | all, conversations or tasks. Default: all. |

Returns the entries of your My Customers list, the first screen Gladly shows an Agent. Each entry has the customer, the Channel the customer last used, and whether it is a Conversation or a Task. Task Users see only Tasks. Use conversation_id with get_conversation and customer_id with get_customer.

Example response:

```json
{
  "customers": [
    {
      "customer_id": "o2sg-TMTSD2rTwMuxzewbA",
      "name": "Marco Silva",
      "kind": "conversation",
      "conversation_id": "HXRqKC5GSV-jAlq0-sxYTA",
      "channel": "email"
    },
    {
      "customer_id": "gHufx-U3QqOmhvFuViceTw",
      "name": "Dana Reyes",
      "kind": "task",
      "conversation_id": null,
      "channel": "sms"
    }
  ]
}
```

### list_conversations

Conversations of an Inbox by status: new, open, waiting or closed. Administrators and Team Managers only. Access: read. REST: `GET /api/v1/gladly/conversations`. MCP: `gladly_read → list_conversations`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `status` | enum | yes | new, open, waiting or closed. |
| `inbox_id` | string | no | Inbox ID from list_assignees. Default: all Inboxes you can see. |
| `cursor` | string | no | Next page cursor from the previous call. |

Reads the status tab of the Gladly home page. New means no Agent has the Conversation yet; Open has an Agent and an open Contact; Waiting is a replied email or an ended call or chat that was not closed; Closed is closed by an Agent. Only Administrators and Team Managers see these tabs, so other roles get APP_PERMISSION_DENIED. Pass conversation_id to get_conversation.

Example response:

```json
{
  "conversations": [
    {
      "conversation_id": "HXRqKC5GSV-jAlq0-sxYTA",
      "customer_id": "o2sg-TMTSD2rTwMuxzewbA",
      "customer": "Marco Silva",
      "channel": "email",
      "status": "new",
      "inbox": "Email Inbox",
      "preview": "Where is my parcel? I ordered on the 9th."
    },
    {
      "conversation_id": "ZbT9m2QxR7iKd4WnHq0LpA",
      "customer_id": "gHufx-U3QqOmhvFuViceTw",
      "customer": "Dana Reyes",
      "channel": "email",
      "status": "new",
      "inbox": "Email Inbox",
      "preview": "I want a refund and a different size."
    }
  ],
  "next_cursor": null
}
```

### search_customers

Find Customer Profiles by email address or phone number. Access: read. REST: `GET /api/v1/gladly/customers/search`. MCP: `gladly_read → search_customers`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `email` | string | no | Email address saved on the profile. |
| `phone_number` | string | no | Phone number in international format, for example +14151234567. |

Searches Customer Profiles with one identifier at a time. Returns the matching profiles with name, emails and phones. When Gladly shows Matching customers found for a profile, the same person can have two profiles; the agent reports both and does not merge them, because Gladly cannot unmerge Customer Profiles.

Example response:

```json
{
  "customers": [
    {
      "customer_id": "o2sg-TMTSD2rTwMuxzewbA",
      "name": "Marco Silva",
      "emails": [
        "marco.silva@example.com"
      ],
      "phones": [
        "+14155550142"
      ]
    }
  ]
}
```

### get_customer

A Customer Profile with contact details, current assignee, open Tasks and the list of their Conversations. Access: read. REST: `GET /api/v1/gladly/customers/{customer_id}`. MCP: `gladly_read → get_customer`.

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

Returns the profile as the Customer Profile screen shows it: name, emails, phones, address, who the customer is assigned to, open Tasks, and each Conversation with its status and Topics. A profile that was merged into another one returns the surviving profile. Use conversation_id with get_conversation.

Example response:

```json
{
  "customer_id": "o2sg-TMTSD2rTwMuxzewbA",
  "name": "Marco Silva",
  "emails": [
    "marco.silva@example.com"
  ],
  "phones": [
    "+14155550142"
  ],
  "assigned_to": {
    "inbox": "Email Inbox",
    "agent": "Priya Nair"
  },
  "open_tasks": [
    {
      "task_id": "pOVVdzweSumI4bFxjlT8LA",
      "body": "Call back about the exchange",
      "due_at": "2026-10-22T17:00:00Z",
      "owner": "Priya Nair"
    }
  ],
  "conversations": [
    {
      "conversation_id": "HXRqKC5GSV-jAlq0-sxYTA",
      "status": "open",
      "topics": [
        "Order Status"
      ]
    },
    {
      "conversation_id": "Qm4vT8cLw1RzNe6JhB3yUg",
      "status": "closed",
      "topics": [
        "Exchange > Size"
      ]
    }
  ]
}
```

### get_conversation

The Conversation Timeline of one Conversation: messages, notes, calls, assignment changes, Topics and status. Access: read. REST: `GET /api/v1/gladly/conversations/{conversation_id}`. MCP: `gladly_read → get_conversation`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `conversation_id` | string | yes | Conversation ID from list_my_customers, list_conversations or get_customer. |

Returns the items of the timeline oldest first, each with who wrote it (customer, Agent or Gladly AI), the Channel, the text and the time. Notes are marked internal. Attachments come as file names. A Conversation that was merged into another returns the surviving one. The agent reads the timeline before it replies, tags or closes.

Example response:

```json
{
  "conversation_id": "HXRqKC5GSV-jAlq0-sxYTA",
  "status": "new",
  "assignee": null,
  "topics": [],
  "items": [
    {
      "at": "2026-10-19T21:14:00Z",
      "from": "customer",
      "channel": "email",
      "text": "Where is my parcel? I ordered on the 9th."
    }
  ]
}
```

### list_topics

Topics your organization uses to tag Conversations, with their parent Topics. Access: read. REST: `GET /api/v1/gladly/topics`. MCP: `gladly_read → list_topics`.

No parameters.

Returns every enabled Topic with its ID and parent. Nested Topics show as parent > child, for example Exchange > Size. The agent only uses Topics from this list. Topics are created by administrators in Gladly, not by this tool.

Example response:

```json
{
  "topics": [
    {
      "topic_id": "Z_Oto7j-Sy2DlQdnZBDdDw",
      "name": "Order Status",
      "parent": null
    },
    {
      "topic_id": "8eiDakrnTgKa3HIxtgV5OA",
      "name": "Damaged Merchandise",
      "parent": "Order Return"
    }
  ]
}
```

### list_assignees

Inboxes and Agents a Conversation can be assigned to. Access: read. REST: `GET /api/v1/gladly/assignees`. MCP: `gladly_read → list_assignees`.

No parameters.

Returns the names and IDs the Conversation Assignment menu offers: Inboxes and Agents. Use inbox_id and agent_id with assign_conversation, create_task and list_conversations. Disabled Inboxes are marked.

Example response:

```json
{
  "inboxes": [
    {
      "inbox_id": "vZgCEQlDR6aQz_0HeWZ9_Q",
      "name": "Email Inbox",
      "disabled": false
    },
    {
      "inbox_id": "E1nArq1uQAees_DogHB0MA",
      "name": "Orders",
      "disabled": false
    }
  ],
  "agents": [
    {
      "agent_id": "sHuXx-U3QqOmhvFusJGeBw",
      "name": "Priya Nair"
    }
  ]
}
```

### add_note

Add an internal Note to a Conversation Timeline. Access: write, asks the user first. REST: `POST /api/v1/gladly/conversations/{conversation_id}/notes`. MCP: `gladly_write → add_note`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `conversation_id` | string | yes | Conversation ID from list_my_customers, list_conversations or get_customer. |
| `body` | string | yes | Text of the note. |

Adds a Note that only your team sees; the customer never receives it. Gladly Notes cannot be edited, and only Administrators can delete them, so a wrong note stays on the timeline. Returns the note ID and time. By default you confirm each call; you can switch that off for this tool.

Example response:

```json
{
  "note_id": "aOVVdzweSumI4bFxjlT8LA",
  "conversation_id": "ZbT9m2QxR7iKd4WnHq0LpA",
  "added_at": "2026-10-20T09:12:00Z"
}
```

### reply_to_customer

Send a reply to the customer in a Conversation, on the Channel the Conversation uses. Access: write, asks the user first. REST: `POST /api/v1/gladly/conversations/{conversation_id}/customer/replies`. MCP: `gladly_write → reply_to_customer`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `conversation_id` | string | yes | Conversation ID from list_my_customers, list_conversations or get_customer. |
| `body` | string | yes | Text of the reply. |

Writes in the composer of the Conversation and sends. The reply goes out on the Channel of the Conversation, for example email or SMS, as the signed-in Agent. If no Agent has the Conversation, it becomes yours. Returns the item ID and the time. The customer reads it, so there is no undo. By default you confirm each call; you can switch that off for this tool.

Example response:

```json
{
  "item_id": "ybP4szYCSy6LdV4DNwEd6g",
  "conversation_id": "HXRqKC5GSV-jAlq0-sxYTA",
  "channel": "email",
  "sent_at": "2026-10-20T09:31:00Z"
}
```

### apply_topics

Add Topics to a Conversation, or remove them. Access: write. REST: `POST /api/v1/gladly/conversations/{conversation_id}/topics/apply`. MCP: `gladly_write → apply_topics`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `conversation_id` | string | yes | Conversation ID from list_my_customers, list_conversations or get_customer. |
| `add` | array | no | Topic IDs from list_topics to add. |
| `remove` | array | no | Topic IDs to remove. |

Sets the Topics at the bottom of the Conversation, as the Topics menu does. A Topic already on the Conversation is ignored. Returns the Topics now on it. It reaches no one and one call undoes it, so it needs no confirmation.

Example response:

```json
{
  "conversation_id": "HXRqKC5GSV-jAlq0-sxYTA",
  "topics": [
    "Order Status"
  ]
}
```

### assign_conversation

Move a Conversation to another Inbox or Agent. Access: write, asks the user first. REST: `POST /api/v1/gladly/conversations/{conversation_id}/assign`. MCP: `gladly_write → assign_conversation`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `conversation_id` | string | yes | Conversation ID from list_my_customers, list_conversations or get_customer. |
| `inbox_id` | string | no | Inbox ID from list_assignees. |
| `agent_id` | string | no | Agent ID from list_assignees. |

Uses the Conversation Assignment menu: the new Inbox or Agent replaces the previous one, and the change shows in the Conversation Timeline. Returns the new assignee. A colleague receives the customer. By default you confirm each call; you can switch that off for this tool.

Example response:

```json
{
  "conversation_id": "HXRqKC5GSV-jAlq0-sxYTA",
  "assignee": {
    "inbox": "Orders",
    "agent": null
  }
}
```

### close_conversation

Close a Conversation without sending anything to the customer. Access: write, asks the user first. REST: `POST /api/v1/gladly/conversations/{conversation_id}/close`. MCP: `gladly_write → close_conversation`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `conversation_id` | string | yes | Conversation ID from list_my_customers, list_conversations or get_customer. |

Does what Close does in Gladly. It does not message the customer, and Gladly will not close a Conversation during an active phone call. Returns the new status. A closed Conversation can be reopened, but your team sees the change. By default you confirm each call; you can switch that off for this tool.

Example response:

```json
{
  "conversation_id": "ZbT9m2QxR7iKd4WnHq0LpA",
  "status": "closed"
}
```

### create_task

Create a Task on a customer's timeline for an Inbox or an Agent. Access: write, asks the user first. REST: `POST /api/v1/gladly/customers/{customer_id}/tasks`. MCP: `gladly_write → create_task`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `customer_id` | string | yes | Customer ID from search_customers or list_my_customers. |
| `body` | string | yes | What the Task asks for. |
| `assignee_inbox_id` | string | no | Inbox ID from list_assignees. |
| `assignee_agent_id` | string | no | Agent ID from list_assignees. |
| `due_at` | datetime | yes | Due date and time in ISO 8601. |

Uses the Task Composer. The owner sees the Task in My Customers if they are assigned to that Inbox. Gladly cannot delete a Task after it is created, so check get_customer for an existing one first. Returns the Task ID. By default you confirm each call; you can switch that off for this tool.

Example response:

```json
{
  "task_id": "pOVVdzweSumI4bFxjlT8LA",
  "customer_id": "o2sg-TMTSD2rTwMuxzewbA",
  "owner": "Billing inbox",
  "due_at": "2026-10-23T17:00:00Z"
}
```

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

Connecting Gladly takes three steps: sign up, sign in to Gladly 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 Gladly to your agent.

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

2. **Sign in to Gladly in your Cloud Browser** Open your Cloud Browser in the console: your own Chrome in the cloud. Sign in to Gladly 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 Gladly 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 the New conversations in the Email Inbox. Apply the topic that fits each one and assign order questions to the Orders inbox. Leave anything unclear for me.
```

### Call Gladly 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/gladly 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/gladly/conversations/ZbT9m2QxR7iKd4WnHq0LpA/notes \
  -H "Authorization: Bearer $COTLET_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"body":"Customer asked for a refund and a different size. Refund approved by Priya."}'
```

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

```
{
  "note_id": "aOVVdzweSumI4bFxjlT8LA",
  "conversation_id": "ZbT9m2QxR7iKd4WnHq0LpA",
  "added_at": "2026-10-20T09:12:00Z"
}
```

## Why use Cotlet for Gladly?

**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 Gladly 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 Gladly changes, the tool pauses until we fix it.
- Failed calls cost nothing.

## Is it safe to connect Gladly to Cotlet?

Yes. You sign in to Gladly yourself, in your own Cloud Browser, and we never save your password. Your agents only get Gladly 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 Gladly integration?**

No, Cotlet is independent of Gladly. Gladly's own API is too limited for this work. Cotlet works through your own Gladly account, the way you use Gladly 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 Gladly in your console: your agents lose access at once and you stay signed in. Signing out of Gladly in the browser works too, and Reset browser deletes the whole profile.

## Is there a Gladly MCP server on GitHub?

Yes, but they are API gateways, not servers for your own login. Hosted gateways wrap the REST API as MCP tools; they need an API token and the API User permission. Open-source servers for Gladly are rare. Cotlet works in your own signed-in Gladly session, so it needs no API token, and our team keeps it working when the app changes. The REST API is the better fit for a bulk export or a webhook receiver.

|  | Gladly REST API | Cotlet |
|---|---|---|
| Setup | Ask an administrator for the API User permission, create a token, write the client and the agent tools | Sign up, sign in to Gladly once, add one MCP server or API key |
| When Gladly changes | The API is versioned; you update your client when a field changes | Our team tests it daily and fixes it for you; failed calls are free |
| Your Gladly session | A token tied to one user that can make any API request without restriction | In your own Cloud Browser in the EU, profile encrypted, only for the apps you enable, disabled for agents in one click |
| When the session expires | The token works until you rotate it | Your Cloud Browser keeps you signed in; if Gladly logs you out, your agent gets a link to sign in again |
| Upkeep | You host the client, handle 429 responses and rotate tokens | Nothing to host or update |
| Where it runs | Wherever you deploy your code | Hosted: Claude Code, Codex, Cursor, n8n and scripts, also on a schedule |
| Price | Free to call, 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 Gladly 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 Gladly API cost?

Free 7-day trial with 2,000 credits, no card needed. After that, the Gladly 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 Gladly 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 Gladly 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 Gladly only after you enable it. When Gladly 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 Gladly, sign out of Gladly 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.
- **Gladly's terms:** You use your own Gladly account and stay responsible for following Gladly's terms. Cotlet is independent and not affiliated with Gladly. [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 Gladly in the console and press Request access. Then you create your API key and connect Gladly there.

**Do I need to be technical?**

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

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

Gladly 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).

**Which Gladly role does my agent need?**

The role of the account you sign in with. Gladly shows the status tabs of an Inbox only to Administrators and Team Managers, so list_conversations needs one of them. Task Users see only Tasks in My Customers.

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

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

**Can I use the Gladly 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/gladly 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.