Imagine you could ask your AI assistant to list open tickets from this morning, summarize a long customer thread, draft a reply for you to review, or pull up how many tickets your team closed last week — all without switching tabs or copying data out of NeetoDesk.
NeetoDesk works with AI assistants you may already be using, like Claude, Cursor, and GitHub Copilot. Once you connect them together, your AI assistant can read tickets, add comments, manage customers and team members, and fetch helpdesk reports. You simply ask in plain English, and the assistant does the work.
What is MCP?
MCP stands for Model Context Protocol. It is an open standard that lets AI assistants and apps like NeetoDesk speak the same language. You do not need to understand how it works to use any of the steps below — think of it as the plumbing that connects your AI assistant to your NeetoDesk workspace.
Why this is useful
Think of it as giving your AI a passcode to your NeetoDesk workspace. After that, the usual back-and-forth disappears. A few examples of what becomes possible:
You ask, "Show me all open tickets assigned to me." and the assistant lists them.
You say, "Get ticket #42 and summarize the conversation so far." and you get a quick recap.
You ask, "Draft a reply to ticket #42 thanking the customer and asking for their order number." and a draft is saved on the ticket.
You say, "How many tickets did we close this month?" and the assistant pulls up the numbers.
You ask, "List our enabled web forms." and the assistant returns the forms configured in your workspace.
You do not need to be technical to benefit from this. If you already talk to an AI assistant for other things, you can talk to it about your NeetoDesk tickets too.
What you need to get started
Two things:
An AI assistant that supports this kind of connection.
A NeetoDesk API key, which authenticates the assistant with your workspace.
See the API Keys help article for how to generate one.
That is it. Once you have both, you paste a small snippet of settings into your AI tool and you are done.
Connecting your AI assistant to NeetoDesk
Pick the tool you use. You only need to follow the steps for that one; you can skip the rest. Each section shows a small block of settings — copy it, replace YOUR_SUBDOMAIN with your NeetoDesk workspace subdomain, replace YOUR_API_KEY with your own key, and save.
Claude Code
Open the file ~/.claude.json and paste the following (if the file already has settings, add just the neetodesk entry inside mcpServers):
{
"mcpServers": {
"neetodesk": {
"type": "http",
"url": "https://YOUR_SUBDOMAIN.neetodesk.com/mcp/messages",
"headers": {
"Authorization": "Bearer YOUR_API_KEY"
}
}
}
}Save the file and restart Claude Code.
Cursor
Open ~/.cursor/mcp.json and paste the following:
{
"mcpServers": {
"neetodesk": {
"type": "http",
"url": "https://YOUR_SUBDOMAIN.neetodesk.com/mcp/messages",
"headers": {
"Authorization": "Bearer YOUR_API_KEY"
}
}
}
}Save it and restart Cursor (or reload the window via the command palette).
VS Code with GitHub Copilot
Create or open .vscode/mcp.json in your workspace and paste:
{
"servers": {
"neetodesk": {
"type": "http",
"url": "https://YOUR_SUBDOMAIN.neetodesk.com/mcp/messages",
"headers": {
"Authorization": "Bearer YOUR_API_KEY"
}
}
}
}VS Code will ask you for your API key the first time. You need VS Code 1.99 or newer, and you must be in the Copilot chat's Agent mode to use it.
Windsurf
Open ~/.codeium/windsurf/mcp_config.json and paste:
{
"mcpServers": {
"neetodesk": {
"serverUrl": "https://YOUR_SUBDOMAIN.neetodesk.com/mcp/messages",
"headers": {
"Authorization": "Bearer YOUR_API_KEY"
}
}
}
}Save it and make sure the connection is turned on in Settings > Cascade > MCP Servers. Windsurf has a limit of 100 total tools across all connected services, so if it complains, turn a few other connections off.
Try it out
Once you are connected, the easiest way to see what is possible is to just ask. Here are some prompts you can copy and paste to get a feel for it:
"List open tickets in my workspace."
"Show me ticket #42 with its full description."
"List all comments on ticket #42."
"Draft a reply on ticket #42 thanking the customer for their patience."
"Create a ticket for [email protected] with subject 'Login issue' and description 'Customer cannot reset password.'"
"Update ticket #42 status to closed."
"List team members in my workspace."
"How many tickets changed status in the last 7 days?"
"Show agent response-time reports for this month."
"List enabled web forms in my workspace."
What your AI assistant can actually do
Under the hood, the connection gives your AI assistant a set of abilities. You do not need to remember any of these names — just ask naturally and the assistant picks the right one. But here is the full list if you are curious.
Tickets: list tickets, get a single ticket by ticket number or ID, create a new ticket, and update a ticket's status, priority, category, agent, group, tags, or subject.
Ticket comments and drafts: list comments on a ticket, get a single comment, add a reply or internal note, and create or update a draft reply on a ticket.
Customers: create a new customer with emails, phones, links, and profile details.
Team members: list team members, get a single team member, invite new members by email, update a member's profile or role, and remove a member from the workspace.
Forms: list enabled web forms in the workspace.
Reports: fetch ticket status-change counts, ticket time-series (new and closed per day), agent performance metrics, group performance metrics, and customer satisfaction survey summaries over a date range.