How to Use the Vapi MCP in VS Code Copilot

Q: How do I configure Vapi across my team using VS Code Copilot?

You commit the .vscode/mcp.json file to the repository root. This ensures every developer on the team automatically gets access to the MCP Server tools.

Q: Does the MCP Server support multi-agent workflows with Vapi in VS Code Copilot?

Yes. You can list all multi-agent squads using listsquads, allowing your team to manage complex, multi-step processes through a single configuration.

Team-wide Vapi voice management via GitHub Copilot in VS Code, right from your codebase.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Vapi MCP to VS Code Copilot

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Define AI Assistant Personas

For consistency across the team, you can define new assistant personas using `create_assistant`. Just supply a JSON payload detailing the model, voice, and transcriber. This tool keeps your entire engineering group on the same page.

Manage Calls & Web Links

Need to generate an endpoint? The `create_web_call` tool handles that easily. Alternatively, you can start a live test call using `create_phone_call`, passing the required number ID and customer details.

Get Call Metrics & History

The MCP Server gives visibility into all communication channels. Use `list_calls` to see recent activity, or run `get_call_details` when you need the full transcript and performance metrics for a specific call.

Setup guide

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

.vscode/mcp.json

{
  "mcpServers": {
    "vapi-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 Vapi. 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 Vapi 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 Vapi MCP in VS Code Copilot

You commit the `.vscode/mcp.json` file to the repository root. This ensures every developer on the team automatically gets access to the MCP Server tools.

The agent calls the available functions, and the results are fed back into the chat context. You see live data responses from the MCP Server without leaving your editor.

Yes. The server manages call details, transcripts, and phone numbers. Since configuration is repo-level, governance over this communication data is centralized.

Yes. You can list all multi-agent squads using `list_squads`, allowing your team to manage complex, multi-step processes through a single configuration.

The tool is designed for this. By committing the config file, you ensure every developer uses the exact same, approved set of tools and endpoints.

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