How to Use the Desku.io MCP in VS Code Copilot

Q: How do teams share the Desku.io config in VS Code Copilot?

You can commit a .vscode/mcp.json file directly to your Git repository. This MCP Server setup removes the need for manual, individual setup steps and ensures every engineer on the team automatically gets access to the Desku.io tools when they open the project.

Equip your engineering team to manage Desku.io support tickets inside VS Code Copilot.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Desku.io MCP to VS Code Copilot

Create your Vinkius account to connect Desku.io to VS Code Copilot and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Desku.io with VS Code Copilot

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Manage support queues inside VS Code Copilot

The `list_tickets` and `get_ticket` tools give your engineering team immediate access to live customer issues directly within VS Code Copilot. Activating this MCP Server lets developers inspect ticket details, read customer complaints, and check severity levels without leaving their IDE. This keeps technical teams close to customer pain points. When a developer is assigned to a bug, they can query the exact ticket history to find reproduction steps. The agent pulls the data and displays it inline. It eliminates the friction of switching between development tools and support dashboards.

Resolve customer conversations with code context

The `create_conversation` and `update_ticket` tools allow your agent to reply to support threads and close resolved tickets. After fixing a bug, a developer can ask Copilot to draft a technical explanation and send it back to the customer. This closes the loop between code deployment and user notification. The agent uses the context of your recent git commits to write accurate, helpful updates. Once the message is sent, it updates the ticket status to resolved. Your team handles support and development in a single unified flow.

Inspect customer profiles to debug account issues

The `get_customer` and `list_customers` tools let your development team look up user accounts directly from Copilot Chat. When troubleshooting database mismatches or permission errors, developers can quickly verify a user's plan and account status in Desku.io. It provides instant context for system-level debugging. This is configured team-wide by committing a `.vscode/mcp.json` file to your repository. Every developer gets instant access to these diagnostic tools upon opening the workspace. It standardizes support troubleshooting across your entire engineering department.

Setup guide

Set up Desku.io MCP in VS Code Copilot

Prerequisites

VS Code 1.99 or later with GitHub Copilot extension
Active Vinkius subscription with a valid endpoint token

1

Open MCP configuration

Open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and run "MCP: Add Server". Select HTTP (Streamable) as the server type. VS Code will create .vscode/mcp.json in your workspace.
2

Add the Desku.io MCP

Paste the JSON snippet shown on the right into your .vscode/mcp.json. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Switch to Agent mode

Open Copilot Chat (Cmd+Shift+I / Ctrl+Shift+I) and switch to Agent mode using the dropdown. MCP tools are only available in Agent mode — they do not appear in Edit or Ask modes.
4

Verify the connection

In the Copilot Chat input, type # to list available tools. You should see the Desku.io tools listed. Try asking: "List my recent Desku.io transactions" and Copilot will invoke them automatically.

.vscode/mcp.json

{
  "mcpServers": {
    "deskuio-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Desku.io. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Desku.io now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Desku.io MCP in VS Code Copilot

You can commit a `.vscode/mcp.json` file directly to your Git repository. This MCP Server setup removes the need for manual, individual setup steps and ensures every engineer on the team automatically gets access to the Desku.io tools when they open the project.

Yes, you must run Copilot in Agent mode to allow it to invoke these tools. Once enabled, the agent can autonomously fetch tickets, lookup customers, or post replies based on your chat instructions. You will see a prompt to approve any write actions before they run.

Yes, permissions are controlled by the API credentials you supply to the configuration. If you provide a read-only token, Copilot will only be able to view tickets and customer profiles. It will not be able to update statuses or post replies.

You need VS Code version 1.96 or higher to support custom MCP configurations. Make sure your Copilot Chat extension is fully updated as well. Once updated, you can configure the server globally or per workspace.

All ticket details and conversation histories are fetched directly via local API calls from your workstation. No support data is sent to external caching servers or used to train public AI models. The integration adheres strictly to your local system's security policies and repository-level access controls.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript