Zendesk MCP Server

由您的代理處理 Zendesk 中的工單、回覆、巨集和檢視。

託管 MCP 伺服器

npx add-mcp 'https://cotlet.dev/mcp/v1/zendesk'

可安裝到 Claude Code、Codex、Cursor 等客戶端

文件

Cotlet · Integrations · How it works · Security · For developers · For automation agencies · Blog · API docs · Help center · Changelog · Contact · Pricing · Sign up

Zendesk API and MCP server

Zendesk has a full REST API, the Support API (also called the Ticketing API), but no documented Zendesk-hosted MCP server for working tickets (checked 16 Oct 2026). Zendesk's MCP documentation covers the MCP client, where Zendesk calls other servers. API tokens are being removed: no new ones from 27 Oct 2026, all remaining ones stop on 30 Apr 2027, and OAuth takes over.

Tickets, replies, macros and views in your Zendesk, worked by your agent. Use it in ChatGPT, Claude or any AI agent over MCP, or in n8n, Make and scripts over REST.

MCP setup REST API guide

Cotlet is an independent service. It is not affiliated with, endorsed by or sponsored by Zendesk. Zendesk is a trademark of its owner. If Zendesk's own integrations cover what you need, use them first.

Customer support platform: tickets from email, chat and forms in one queue, with views, macros, triggers and automations that route and answer them.

What is the Zendesk API?

Cotlet's Zendesk API exposes 12 endpoints for your own Zendesk account: search tickets, get ticket, list views, list tickets in a view, list macros, list groups, list agents, reply to ticket, add internal note, update ticket, apply macro and merge tickets. The search_tickets endpoint returns tickets that match a Zendesk search query, with status, priority, requester and assignee. Each endpoint takes simple JSON inputs like ticket_id, query or limit and works both as an operation of the zendesk_read or zendesk_write MCP tool for agents and as a REST call for scripts.

  • Category: Customer support
  • Endpoints: 12 (7 read, 5 write)
  • Updated: 2026-11-16

Zendesk has a full REST API, the Support API (also called the Ticketing API), but no documented Zendesk-hosted MCP server for working tickets (checked 16 Oct 2026). Cotlet is a hosted MCP server and REST API for Zendesk with 12 endpoints (7 read, 5 write): you sign in once in your own cloud browser, your AI agent does the work.

Does Zendesk have an official API?

Zendesk has a full REST API, the Support API (also called the Ticketing API), but no documented Zendesk-hosted MCP server for working tickets (checked 16 Oct 2026). Zendesk's MCP documentation covers the MCP client, where Zendesk calls other servers. API tokens are being removed: no new ones from 27 Oct 2026, all remaining ones stop on 30 Apr 2027, and OAuth takes over.

TaskZendesk officialCotlet
Search tickets and list the tickets in a viewYes: Support API; you wire OAuth and paging yourselfYes
Read a ticket with its commentsYes: Support APIYes
Reply to the requesterYes: Support API, public comment; no MCP server for agentsYes
Add an internal noteYes: Support API, private commentYes
Update status, priority, assignee, group and tagsYes: Support APIYes
Apply a macroYes: Support API, in two steps: the macro result, then the ticket updateYes
Merge a ticket into anotherYes: Support APIYes
List macros, groups and agentsYes: Support APIYes

Sources: Zendesk Help: Announcing the removal of API tokens as an authentication method, Zendesk developers: Migrating from API tokens to OAuth access tokens, Zendesk Help: Connecting to MCP servers and using MCP tools in action flows, Zendesk developers: Support API rate limits

Quick reference

Zendesk has a full REST API, the Support API (also called the Ticketing API), but no documented Zendesk-hosted MCP server for working tickets (checked 16 Oct 2026). Zendesk's MCP documentation covers the MCP client, where Zendesk calls other servers. API tokens are being removed: no new ones from 27 Oct 2026, all remaining ones stop on 30 Apr 2027, and OAuth takes over.
Cotlet provides a hosted MCP server and REST API for Zendesk: 12 tools (7 read, 5 write).
Access       Sign up at https://cotlet.dev/app/signup?app=zendesk and request the app in the Cotlet console. ChatGPT and Claude connect with OAuth at https://cotlet.dev/mcp/v1/connect, no API key; code editors and scripts use an API key from the console.

MCP server   https://cotlet.dev/mcp/v1
MCP tools    zendesk_read, zendesk_write, reads and writes apart; call one with {"operation": "<operation>", "arguments": {...}}
REST base    https://cotlet.dev/api/v1/zendesk, each operation at its own route, e.g. POST /api/v1/zendesk/tickets/{ticket_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_tickets, get_ticket, list_views, list_view_tickets, list_macros, list_groups, list_agents, reply_to_ticket, add_internal_note, update_ticket, apply_macro, merge_tickets
Confirm      reply_to_ticket, add_internal_note, update_ticket, apply_macro, merge_tickets (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/zendesk-api-mcp-server.md

How access works:
1. The user signs up at https://cotlet.dev/app/signup?app=zendesk and requests Zendesk in the Cotlet console.
2. The user signs in to Zendesk once in their Cotlet Cloud Browser (their own Chrome in the cloud, opened from the console) and enables Zendesk for agents. An agent cannot do this step.
3. ChatGPT and Claude: the user adds https://cotlet.dev/mcp/v1/connect as a connector and signs in to Cotlet (OAuth). Code editors and scripts: an API key from the console goes into the MCP client or the REST call as a bearer token.

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

Policy: Cotlet never stores passwords and never bypasses MFA.
Company: legal details in the Terms of service at https://cotlet.dev/terms. Contact contact@cotlet.dev.
Sign-in: the user signs in to Zendesk 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 Zendesk 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 Zendesk 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 Zendesk's terms; Cotlet is not affiliated with Zendesk.

What can an AI agent do in Zendesk?

Cotlet is best for support leads and small teams who want an AI agent to triage tickets, chase pending ones and apply macros in Zendesk without running or fixing a server, or wiring their own OAuth client.

  • Triage new support tickets (runs: daily): "Go through new Zendesk tickets. Set priority from what the customer wrote, assign billing questions to the Billing group and bugs to Tier 2, add a tag, and leave a one-line internal note with the reason. Leave unclear ones for me." → search_tickets, get_ticket, list_groups, update_ticket, add_internal_note
  • Follow up on pending tickets (runs: daily): "Find Zendesk tickets that have been pending for more than 3 days with no reply from the customer. Send a short reminder that quotes what we asked for. If we already sent a reminder, tell me instead of sending a second one." → search_tickets, get_ticket, reply_to_ticket, update_ticket
  • Apply macros to tickets automatically (runs: daily): "Look at open Zendesk tickets without a reply. Where a macro clearly fits, such as Downgrade and inform for feature requests, apply it. Show me the ticket and the macro for anything uncertain." → list_macros, search_tickets, get_ticket, apply_macro
  • Merge duplicate tickets (runs: weekly): "Find open Zendesk tickets from the same requester about the same issue this week. Merge the newer ones into the oldest and leave an internal note on the survivor." → search_tickets, get_ticket, merge_tickets, add_internal_note
  • Weekly support backlog report (runs: weekly): "Every Monday, tell me how many Zendesk tickets are new, open and pending per group, the oldest unsolved ticket in each group, and anything high priority with no assignee." → list_groups, search_tickets

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

Yes. Cotlet does not replace your automation platform: it gives it a Zendesk 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 support tickets, and the schedule runs on its own. Cotlet runs in the cloud, so it keeps going while your computer is off.

WhereHow to connectHow to schedule
Your AI agentAdd https://cotlet.dev/mcp/v1 with your API key.A scheduled agent run, for example a Claude Code routine.
n8nMCP 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/zendesk/tickets/search.Schedule Trigger node.
MakeHTTP module: the endpoint's method and URL with an Authorization: Bearer header, and a JSON body for POST, PUT and PATCH.Scenario schedule.
ZapierWebhooks by Zapier, Custom Request: the same method, URL, header and body.Schedule by Zapier trigger.
Your own scriptGET https://cotlet.dev/api/v1/zendesk/tickets/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 Zendesk.

search_tickets

Tickets that match a Zendesk search query, with status, priority, requester and assignee. Access: read. REST: GET /api/v1/zendesk/tickets/search. MCP: zendesk_read → search_tickets.

ParameterTypeRequiredDescription
querystringyesZendesk search query, e.g. 'status:new' or 'status:pending updated<2026-10-13'.
sort_byenumnocreated_at or updated_at. Default: updated_at.
sort_orderenumnoasc or desc. Default: desc.
limitintegerno1 to 100. Default: 25.
cursorstringnoNext page cursor from the previous call.

Runs a Zendesk ticket search and returns the matches without comments. The query uses Zendesk's own keywords, for example status:new, status:pending updated<2026-10-13, assignee:none or requester:amy@example.com. Sorted by the field you pick, newest first by default. Pages hold up to 100 tickets; pass next_cursor back as cursor for the next page. Use get_ticket for the full thread.

Example response:

{
  "tickets": [
    {
      "ticket_id": 48230,
      "subject": "Refund for double charge",
      "status": "new",
      "priority": null,
      "requester": "Maya Brandt",
      "assignee": null,
      "group": null,
      "tags": [],
      "created_at": "2026-10-16T06:41:00Z",
      "updated_at": "2026-10-16T06:41:00Z"
    }
  ],
  "next_cursor": null
}

get_ticket

One ticket with its fields, tags and every comment, public and internal. Access: read. REST: GET /api/v1/zendesk/tickets/{ticket_id}. MCP: zendesk_read → get_ticket.

ParameterTypeRequiredDescription
ticket_idintegeryesTicket ID from search_tickets or list_view_tickets.

Returns one ticket with subject, status, priority, requester, assignee, group, tags and all comments in order, oldest first. Each comment says whether it is public or an internal note and who wrote it. The first comment is the description. Use it before replying so your agent sees the whole thread.

Example response:

{
  "ticket_id": 48102,
  "subject": "Export fails with an error",
  "status": "pending",
  "priority": "normal",
  "requester": {
    "name": "Dana Whitfield",
    "email": "dana@example.com"
  },
  "assignee": "Sam Okafor",
  "group": "Support",
  "tags": [
    "export",
    "web"
  ],
  "updated_at": "2026-10-12T09:30:00Z",
  "comments": [
    {
      "comment_id": 9120001204,
      "author": "Dana Whitfield",
      "public": true,
      "body": "Export to CSV fails every time.",
      "created_at": "2026-10-12T08:55:00Z"
    },
    {
      "comment_id": 9120001877,
      "author": "Sam Okafor",
      "public": true,
      "body": "Sorry about that. What error text do you see after clicking Export?",
      "created_at": "2026-10-12T09:30:00Z"
    }
  ]
}

list_views

Ticket views you can open: shared views and your personal ones. Access: read. REST: GET /api/v1/zendesk/views. MCP: zendesk_read → list_views.

No parameters.

Lists the active views your agent user can see, both shared views and personal views, with their IDs and titles. Pass view_id to list_view_tickets to read the tickets in one.

Example response:

{
  "views": [
    {
      "view_id": 7790214,
      "title": "New tickets to triage",
      "shared": true
    },
    {
      "view_id": 7790288,
      "title": "My pending tickets",
      "shared": false
    }
  ]
}

list_view_tickets

Tickets in one view, in the view's own order. Access: read. REST: GET /api/v1/zendesk/view-tickets. MCP: zendesk_read → list_view_tickets.

ParameterTypeRequiredDescription
view_idintegeryesView ID from list_views.
limitintegerno1 to 100. Default: 25.
cursorstringnoNext page cursor from the previous call.

Returns the tickets a view shows, in the order the view defines, with status, priority, requester and assignee. Use it when your team already built the queue you want worked. Pages hold up to 100 tickets; pass next_cursor back as cursor for the next page.

Example response:

{
  "tickets": [
    {
      "ticket_id": 48244,
      "subject": "Chargeback if no refund today",
      "status": "new",
      "priority": null,
      "requester": "Jon Reyes",
      "assignee": null,
      "updated_at": "2026-10-16T07:02:00Z"
    }
  ],
  "next_cursor": null
}

list_macros

Active macros with ID, title and description. Access: read. REST: GET /api/v1/zendesk/macros. MCP: zendesk_read → list_macros.

ParameterTypeRequiredDescription
querystringnoOnly macros whose title contains this text.
limitintegerno1 to 100. Default: 50.

Lists the active macros your agent user can apply, shared and personal, with title and description when one exists. Filter by part of the title. Use the macro_id with apply_macro.

Example response:

{
  "macros": [
    {
      "macro_id": 360011204873,
      "title": "Downgrade and inform",
      "description": "Sets priority to low and tells the requester about possible delay."
    },
    {
      "macro_id": 360011204912,
      "title": "Requester not responding",
      "description": "Reminder for a pending ticket where the requester has not answered."
    }
  ]
}

list_groups

Support groups with ID and name. Access: read. REST: GET /api/v1/zendesk/groups. MCP: zendesk_read → list_groups.

No parameters.

Lists the groups in your Zendesk, with their IDs and names. Use group_id with update_ticket to route a ticket. Private groups appear only if your agent user is a member.

Example response:

{
  "groups": [
    {
      "group_id": 3341,
      "name": "Billing"
    },
    {
      "group_id": 3342,
      "name": "Tier 2"
    },
    {
      "group_id": 3300,
      "name": "Support"
    }
  ]
}

list_agents

Agents and admins who can be assigned tickets, with role. Access: read. REST: GET /api/v1/zendesk/agents. MCP: zendesk_read → list_agents.

ParameterTypeRequiredDescription
querystringnoOnly agents whose name or email contains this text.

Lists agents and admins in your Zendesk with ID, name and role. Light agents and collaborators are left out, because tickets cannot be assigned to them. Use assignee_id with update_ticket.

Example response:

{
  "agents": [
    {
      "user_id": 20118842,
      "name": "Sam Okafor",
      "role": "agent"
    },
    {
      "user_id": 20118001,
      "name": "Lena Ortiz",
      "role": "admin"
    }
  ]
}

reply_to_ticket

Add a public reply to a ticket and optionally set its status in the same call. Access: write, asks the user first. REST: POST /api/v1/zendesk/tickets/{ticket_id}/replies. MCP: zendesk_write → reply_to_ticket.

ParameterTypeRequiredDescription
ticket_idintegeryesTicket ID from search_tickets or list_view_tickets.
bodystringyesReply text, sent to the requester.
statusenumnoopen, pending, hold or solved. Default: leave the status as it is. hold only if an admin enabled On-hold.

Adds a public comment to the ticket, which emails the requester unless the notification trigger is disabled in your Zendesk. A comment cannot be removed afterwards. Set status in the same call to move the ticket to pending or solved with the reply. By default you confirm each call; you can switch that off for this tool.

Example response:

{
  "ticket_id": 48102,
  "comment_id": 9120044471,
  "public": true,
  "status": "pending",
  "created_at": "2026-10-16T09:00:00Z"
}

add_internal_note

Add a private note only agents can see. Access: write, asks the user first. REST: POST /api/v1/zendesk/tickets/{ticket_id}/internal-notes. MCP: zendesk_write → add_internal_note.

ParameterTypeRequiredDescription
ticket_idintegeryesTicket ID from search_tickets or list_view_tickets.
bodystringyesNote text, visible to agents only.

Adds a private comment, shown with a yellow background and visible to agents only, never to the requester. A comment cannot be removed afterwards, so each note stays in the ticket history. It can still notify followers on the ticket. By default you confirm each call; you can switch that off for this tool.

Example response:

{
  "ticket_id": 48230,
  "comment_id": 9120044502,
  "public": false,
  "created_at": "2026-10-16T09:01:00Z"
}

update_ticket

Change status, priority, assignee, group, subject or tags of one ticket. Access: write, asks the user first. REST: PATCH /api/v1/zendesk/tickets/{ticket_id}. MCP: zendesk_write → update_ticket.

ParameterTypeRequiredDescription
ticket_idintegeryesTicket ID from search_tickets or list_view_tickets.
statusenumnoopen, pending, hold or solved. hold only if an admin enabled On-hold.
priorityenumnolow, normal, high or urgent.
assignee_idintegernoAgent user ID from list_agents.
group_idintegernoGroup ID from list_groups.
add_tagsstring[]noTags to add, keeping the existing ones.
remove_tagsstring[]noTags to remove.
subjectstringnoNew subject.

Updates the fields you pass and leaves the rest. Priority accepts low, normal, high or urgent if your admin allows them. Tickets cannot be assigned to light agents. Triggers and automations in your Zendesk run as usual after the update, so a status change can email the requester. A ticket cannot return to new once it has left it. By default you confirm each call; you can switch that off for this tool.

Example response:

{
  "ticket_id": 48230,
  "status": "new",
  "priority": "high",
  "assignee_id": null,
  "group_id": 3341,
  "group": "Billing",
  "tags": [
    "billing",
    "refund"
  ],
  "updated_at": "2026-10-16T09:02:00Z"
}

apply_macro

Apply a macro to one ticket and save the result. Access: write, asks the user first. REST: POST /api/v1/zendesk/tickets/{ticket_id}/macros/{macro_id}/apply. MCP: zendesk_write → apply_macro.

ParameterTypeRequiredDescription
ticket_idintegeryesTicket ID from search_tickets or list_view_tickets.
macro_idintegeryesMacro ID from list_macros.

Applies the macro's actions to the ticket: it can set fields, add tags and insert a comment, then saves the ticket. The response lists what changed. A macro that adds a public comment emails the requester. If the macro changes a field that is not on the ticket form, or your user lacks permission for the change, that action does not happen. If the ticket changed in the meantime, the call fails and asks you to read the ticket again. By default you confirm each call; you can switch that off for this tool.

Example response:

{
  "ticket_id": 48177,
  "macro": {
    "macro_id": 360011204873,
    "title": "Downgrade and inform"
  },
  "changes": {
    "priority": "low"
  },
  "comment": {
    "public": true,
    "body": "Thanks for the idea. We have lowered the priority of your request to low, so it may take longer to get to."
  },
  "updated_at": "2026-10-16T09:03:00Z"
}

merge_tickets

Merge one ticket into another and close the source ticket. Access: write, asks the user first. REST: POST /api/v1/zendesk/target-tickets/{target_ticket_id}/tickets/merge. MCP: zendesk_write → merge_tickets.

ParameterTypeRequiredDescription
target_ticket_idintegeryesTicket that stays open and receives the merge.
source_ticket_idintegeryesTicket that is closed by the merge.

Merges the source ticket into the target ticket. A merge is permanent and cannot be undone. Both tickets must be below solved, but you can merge into a solved target without reopening it. The source's most recent public comment is carried to the target with a link, other comments are not, and fields such as tags and priority are not carried over. The source is closed and gets the tag closed_by_merge. Without CCs enabled in your Zendesk, both tickets must have the same requester. By default you confirm each call; you can switch that off for this tool.

Example response:

{
  "target_ticket_id": 48102,
  "source_ticket_id": 48260,
  "source_status": "closed",
  "source_tags": [
    "closed_by_merge"
  ]
}

How do I connect Zendesk to ChatGPT, Claude, Cursor or Codex?

Connecting Zendesk takes three steps: sign up, sign in to Zendesk once in your Cloud Browser and enable it for agents, then add Cotlet to ChatGPT or Claude as a connector, with no API key, or add one MCP server or call the REST API with an API key.

Connect Zendesk to your agent.

  1. Create an account Sign up and add Zendesk in the console. ChatGPT and Claude need no API key: you sign in to Cotlet when you add the connector. Code editors and scripts take an API key from the console.

  2. Sign in to Zendesk in your Cloud Browser Open your Cloud Browser in the console: your own Chrome in the cloud. Sign in to Zendesk 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 ChatGPT, Claude or your agent Paste the snippet for your client. The same server and key serve every app you connect, so you do this once.

    ChatGPT:

Settings > Apps & Connectors > Create
MCP server URL: https://cotlet.dev/mcp/v1/connect
Authentication: OAuth

Claude:

Settings > Connectors > Add custom connector
URL: https://cotlet.dev/mcp/v1/connect

Claude Code:

claude mcp add --transport http cotlet \
  https://cotlet.dev/mcp/v1 \
  --header "Authorization: Bearer $COTLET_API_KEY"

Cursor:

{
  "mcpServers": {
    "cotlet": {
      "url": "https://cotlet.dev/mcp/v1",
      "headers": {
        "Authorization": "Bearer ${COTLET_API_KEY}"
      }
    }
  }
}

Codex:

# ~/.codex/config.toml
[mcp_servers.cotlet]
url = "https://cotlet.dev/mcp/v1"
bearer_token_env_var = "COTLET_API_KEY"
  1. Ask your agent Ask in plain words. Your agent finds the Zendesk 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 new Zendesk tickets. Set priority from what the customer wrote, assign billing questions to the Billing group and bugs to Tier 2, add a tag, and leave a one-line internal note with the reason. Leave unclear ones for me.

Call Zendesk 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_..."
  1. Call a tool Every tool is an endpoint under /api/v1/zendesk 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/zendesk/tickets/48102/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 exact error text you see after clicking Export. A screenshot works too.","status":"pending"}'
  1. Read the result You get plain JSON back, ready for your script. A failed call costs nothing.
{
  "ticket_id": 48102,
  "comment_id": 9120044471,
  "public": true,
  "status": "pending",
  "created_at": "2026-10-16T09:00:00Z"
}

How to use the Zendesk REST API

Create your Cotlet API key

Create a Cotlet API key with access to Zendesk and its read operations. Store it as COTLET_API_KEY in your environment or automation platform's credential store.

Connect Zendesk in Cotlet and enable it for agents. Account access: Your own Zendesk agent login on your subdomain (agent or admin). What your agent can do follows your role. You sign in in your own browser and keep your SSO or 2-step verification.

Make your first Zendesk API request

REST:

curl https://cotlet.dev/api/v1/zendesk/views \
  -H "Authorization: Bearer $COTLET_API_KEY"

Read views and apply the operation limits

A successful REST call puts the tool output in result. This illustrative response excerpt omits call IDs, messages and credit details.

Illustrative response excerpt:

{
  "status": "success",
  "app": "zendesk",
  "tool": "list_views",
  "result": {
    "views": [
      {
        "view_id": 7790214,
        "title": "New tickets to triage",
        "shared": true
      },
      {
        "view_id": 7790288,
        "title": "My pending tickets",
        "shared": false
      }
    ]
  }
}

Lists the active views your agent user can see, both shared views and personal views, with their IDs and titles. Pass view_id to list_view_tickets to read the tickets in one.

Keep the same selection when continuing a list. Compare changed record values as well as identifiers when refreshing your destination.

Zendesk workflows for agents and automations

ToolConnect throughExample workflow
n8nHTTP RequestTickets that match a Zendesk search query, with status, priority, requester and assignee. Use search_tickets in your configured support report.
MakeHTTP > Make a requestOne ticket with its fields, tags and every comment, public and internal. Use get_ticket in your configured support report.
Python or Node.jsREST APIActive macros with ID, title and description. Use list_macros in your configured support report.

Send Authorization: Bearer <your Cotlet API key> in request headers. You configure the schedule, destination and record comparisons.

Cotlet reads Zendesk; your workflow steps write to your chosen destination. These HTTP workflows do not require a native Cotlet connector or a prebuilt template.

Python and Node.js can use the same HTTP requests without an AI agent. Keep access keys in credentials, outside shared workflow exports.

The API and MCP reference lists operations and inputs. The REST API guide explains authentication, errors and approvals.

Why use Cotlet for Zendesk?

Built for agents

  • One MCP server for every app you connect.
  • The same tools as a REST API for scripts and cron jobs.
  • Works with ChatGPT, Claude, Claude Code, Codex and Cursor.

Your login stays yours

  • You sign in to Zendesk yourself, in your own Cloud Browser. We never save your password; the profile is encrypted with AES-256-GCM, the cipher 1Password uses.
  • A+ on Qualys SSL Labs, securityheaders.com and Mozilla Observatory.
  • The model never sees a login.
  • No stored passwords, no MFA bypass.

You stay in control

  • Scope each API key: its apps, its tools, read only or read and write.
  • Anything that reaches other people waits for your OK, so a leaked key cannot post or message as you.
  • Every background request listed in your Background activity. Disable for agents in one click.

Kept working for you

  • We test every integration every 6 hours.
  • When Zendesk changes, the tool pauses until we fix it.
  • Failed calls cost nothing.

Is it safe to connect Zendesk to Cotlet?

Yes. You sign in to Zendesk yourself, in your own Cloud Browser, and we never save your password. Your agents only get Zendesk once you enable it, and every background request is listed. The browser profile is stored encrypted with AES-256-GCM, the same cipher 1Password uses for its vaults and Apple for iCloud Keychain. Independent public scanners grade cotlet.dev A+ and find it clean; click a result to rerun it yourself.

  • A+ on Qualys SSL Labs: Encryption in transit: TLS setup and certificates, on all four server addresses. Live result
  • A+ on securityheaders.com: Browser protections sent with every page, all six headers present. Live result
  • A+ on Mozilla Observatory: Mozilla's web security baseline: score 120 of 100, 12 of 12 tests passed. Live result
  • Clean on Sucuri SiteCheck: No malware, spam or defacement, and not on any of 9 blocklists, Google Safe Browsing included. Live result

How Cotlet protects your access

Common concerns

Who runs Cotlet?

Cotlet is run by Take Group, a Polish software company working since 2019. Take Group runs about 3,200 websites on its own systems and has its own DevOps team for infrastructure security. We built and used integrations like this inside the company for years before opening them as Cotlet.

Is this an official Zendesk integration?

No, Cotlet is independent of Zendesk. Zendesk's own API is too limited for this work. Cotlet works through your own Zendesk account, the way you use Zendesk in the browser.

What about client data and GDPR?

Cotlet is run from the EU and follows the GDPR. Cloud Browsers run in Finland, a Tier 1 country in the ITU Global Cybersecurity Index 2024. Data passes through a call and is not kept after it.

Can I start with read only?

Yes. Enable the app for agents as read only, or make the API key read only, and anything that reaches other people waits for your OK unless you switch that off per tool.

Is it reliable?

Every Cotlet service is checked every 3 minutes from Europe, North America, Asia and Australia. The live results and any outage are public at status.cotlet.dev.

How do I stop?

Press Disable for agents next to Zendesk in your console: your agents lose access at once and you stay signed in. Signing out of Zendesk in the browser works too, and Reset browser deletes the whole profile.

Is there a Zendesk MCP server on GitHub?

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

GitHub MCP serverCotlet
SetupClone the repo, create an OAuth client in Admin Center, store its secret, add the server to each MCP clientSign up, sign in to Zendesk once, add one MCP server or API key
When Zendesk changesIt breaks until you or the maintainer fix it; the API token to OAuth change forces a rewrite of token handlingOur team tests it daily and fixes it for you; failed calls are free
Your Zendesk accessOAuth client secret or token in a file on your computer, readable by any program you runSigned 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 expiresTools fail until you renew the token or sign in again by handYour Cloud Browser keeps you signed in; if Zendesk logs you out, your agent gets a link to sign in again
UpkeepYou update, monitor and debug it yourselfNothing to host or update
Where it runsYour computer, while it is onHosted: Claude Code, Codex, Cursor, n8n and scripts, also on a schedule
PriceFree, paid for with your timeFree 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 Zendesk 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 Zendesk API cost?

Free 7-day trial with 2,000 credits, no card needed. After that, the Zendesk API is pay as you go with no limit on apps: Credit packs from $29 for 5,000 credits, one-time, no subscription. A successful call uses 10 to 100 credits (10 for most tools, about $0.04 to $0.06), your Cloud Browser uses 50 credits a day while it has an app enabled for agents, however many apps that is, and an agent driving the browser itself uses 5 credits a minute. Credit packs stay valid for 12 months and stack, so unused credits carry over.

CreditsPrice, one timeCalls at 10 creditsPer 1,000 credits
5,000$29500$5.80
15,000$791,500$5.27
32,000$1493,200$4.66
60,000$2496,000$4.15

Only successful calls use credits; failed calls and timeouts cost nothing. At a balance of 0 calls pause, never a surprise charge. Authenticate with the Authorization: Bearer header. See full pricing

How Cotlet holds your access

Cotlet hosts MCP servers and REST APIs for apps with no usable API. Your agent works in your own Zendesk account.

  • Company details: Cotlet is run by Take Group sp. z o.o., a company registered in Poland. Its full address and registration numbers are in the Terms of service. Terms of service
  • Your sign-in: You sign in to Zendesk 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 Zendesk only after you enable it. When Zendesk signs you out, your agent gives you a link to sign in again. Security
  • Revoking access: Press Disable for agents next to Zendesk, sign out of Zendesk in your Cloud Browser, or reset the browser. Every background request is listed in your Background activity. Actions that reach other people wait for your OK unless you switch that off per tool.
  • What we never do: Store passwords or bypass MFA.
  • Zendesk's terms: You use your own Zendesk account and stay responsible for following Zendesk's terms. Cotlet is independent and not affiliated with Zendesk. Terms
  • Contact: Questions about the company, security or an app: contact@cotlet.dev

Also listed on: Odel, mcpbeat

Zendesk API and MCP: questions

How do I get access?

Sign up free, open Zendesk in the console and press Activate. Then you create your API key and connect Zendesk there.

Do I need to be technical?

No. You sign in to Zendesk 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 Zendesk to Cotlet?

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

Zendesk offers no OAuth token you can simply grant for these tools: its official API leaves them out or needs a developer app, a plan or an approval first (see the official API section above). That is why Cotlet sets the limits itself: per key, per tool, with your approval before anything reaches other people. Cotlet is run by Take Group sp. z o.o., an EU company (VAT PL6342984273).

How do I connect Zendesk to ChatGPT or Claude?

Sign up at cotlet.dev, log in to Zendesk once in its Cloud Browser and add Cotlet to ChatGPT or Claude, following the steps in your console. No API key is needed. ChatGPT and Claude then work in your Zendesk account through Cotlet, in their phone apps too.

What can ChatGPT do in Zendesk?

With Cotlet, ChatGPT, Claude and other AI agents handle jobs like these in Zendesk: triage new support tickets; follow up on pending tickets; apply macros to tickets automatically. You ask in plain words, and anything that reaches other people waits for your OK first.

Do I need an OAuth app or an API token for Cotlet?

No. Cotlet works through your own agent login, so you do not create an OAuth client in Admin Center and the API token removal does not touch it. Zendesk stops new API tokens on 27 Oct 2026 and all remaining ones on 30 Apr 2027 (Zendesk announcement of 1 Jun 2026).

Will my agent send replies to customers without asking?

Only if you switch confirmation off. By default every reply, note, update, macro and merge waits for your OK. A public reply emails the requester and a comment cannot be removed from a ticket afterwards (Zendesk Help: Adding comments to tickets).

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

No. Every call to reply_to_ticket, add_internal_note, update_ticket, apply_macro or merge_tickets waits for your OK by default. For scheduled automations you can switch confirmation off per tool in your dashboard, for example only for approvals.

Can I use the Zendesk 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/zendesk from the HTTP Request node.

Can I use the Zendesk API without an AI agent?

Yes. Call Cotlet's REST API from a script or an HTTP step in n8n, Make or Zapier with your Cotlet key. MCP is the alternative for AI agents; you do not need to connect an agent to use REST.


Give your AI agents your signed-in browser.

Product: Integrations · How it works · Pricing · Security

Resources: Blog · API docs · Help center · Changelog · GitHub

Solutions: For developers · For automation agencies

Company: About · AI info: company facts · Contact

Legal: Terms of service · Privacy policy · Refund policy · Acceptable use · Cookie policy · DPA · Subprocessors

Elsewhere: Status page · Cotlet on GitHub · Cotlet on X · Cotlet on LinkedIn · Cotlet on Product Hunt · Cotlet on Crunchbase · Cotlet on SaaSHub

Cotlet.dev is built by Bart Krawczyk and Jake Slugocki, the founders of Take Group sp. z o.o., ul. Wincentego Janasa 4, 40-855 Katowice, Poland. KRS 0000871398, NIP 6342984273, VAT EU: PL6342984273. About us

Cotlet is an independent service. It is not affiliated with, endorsed by or sponsored by any of the products listed on this site. Product names are trademarks of their respective owners.