How to Use the DoiT MCP in VS Code Copilot

Q: How do I set up the DoiT MCP Server for my entire team in VS Code Copilot?

Create a .vscode/mcp.json file in your repository root and add the server configuration. Once committed, any developer on your team using VS Code 1.96+ with Copilot can run tools like getbillingcostsummary automatically.

Track cloud budgets and inspect multi-cloud assets as a team directly 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 DoiT MCP to VS Code Copilot

Create your Vinkius account to connect DoiT 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 DoiT with VS Code Copilot

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Aligning teams on budgets in VS Code Copilot

Share cost visibility across your entire engineering team by committing your configuration to git. This MCP Server lets your team use VS Code Copilot to run `list_cost_budgets` and check spending limits during code reviews. It prevents budget surprises by making financial guardrails part of the development cycle. When a budget is breached, Copilot can run `list_exceeded_cost_budgets` to identify which team or project exceeded its limits. This keeps everyone accountable without requiring manual reports from the finance team.

Auditing cloud infrastructure during development

Developers can verify their active cloud resources without logging into external management consoles. VS Code Copilot uses `list_cloud_assets` to fetch a real-time list of your AWS, GCP, and Azure assets. This keeps your team updated on what is running in your staging and production environments. If you need to check a specific resource, the agent runs `get_asset_details` to pull its configuration and cost history. This helps your team identify orphaned or oversized resources during sprint planning.

Proactive anomaly detection in the team workspace

Catch unexpected spending spikes before they escalate into massive bills. VS Code Copilot uses `list_cost_anomalies` to scan your accounts for unusual cost trends directly from your terminal or chat panel. It turns cost monitoring into a natural part of your daily engineering workflow using this MCP configuration. If a major spike occurs, the `list_critical_cost_spikes` tool highlights high-severity issues that need immediate triage. Your team can quickly identify the root cause and collaborate on a fix without leaving the editor.

Setup guide

Set up DoiT 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 DoiT 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 DoiT tools listed. Try asking: "List my recent DoiT transactions" and Copilot will invoke them automatically.

.vscode/mcp.json

{
  "mcpServers": {
    "doit-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 DoiT. 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 DoiT 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 DoiT MCP in VS Code Copilot

Create a `.vscode/mcp.json` file in your repository root and add the server configuration. Once committed, any developer on your team using VS Code 1.96+ with Copilot can run tools like `get_billing_cost_summary` automatically.

Yes, your team can ask Copilot to search for resources using `search_cloud_assets` and evaluate their usage. Copilot then calls `get_asset_details` to help you identify idle or underutilized instances that should be shut down.

The server uses a single secure token managed by Vinkius to retrieve organization data via `get_doit_account_metadata`. Developers do not need to manage individual API keys or share sensitive credentials.

Yes, the integration queries all connected platforms simultaneously. Copilot runs `list_connected_cloud_accounts` to verify which AWS, GCP, or Azure accounts are currently being tracked for cost anomalies.

All communication between VS Code Copilot and the billing API is encrypted in transit and runs within an isolated MCP sandbox. Your organization's cloud spending metrics and asset configurations are never stored or used for model training.

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