MCP integration

Overview

The Model Context Protocol (MCP) integration transforms your IDE’s AI assistant into a Vapi expert. Once configured, your IDE gains complete, accurate knowledge of Vapi’s APIs, features, and best practices - eliminating AI hallucinations and outdated information.

In this guide, you’ll learn to:

• Set up MCP in supported IDEs
• Understand what knowledge is provided
• Use your enhanced IDE effectively
• Troubleshoot common issues

Quick start

Run the setup command to auto-configure all supported IDEs:

$
vapi mcp setup

Or configure a specific IDE:

$
vapi mcp setup cursor   # For Cursor
$
vapi mcp setup windsurf # For Windsurf  
$
vapi mcp setup vscode   # For VSCode with Copilot

What is MCP?

Model Context Protocol is a standard that allows AI assistants to access structured knowledge and tools. When you set up MCP for Vapi:

• Your IDE’s AI gains access to complete Vapi documentation
• Code suggestions become accurate and up-to-date
• Examples use real, working Vapi patterns
• API hallucinations are eliminated

Supported IDEs

How it works

What gets configured

The MCP setup creates configuration files that connect your IDE to the Vapi MCP server:

1
{
2
  "servers": {
3
    "vapi-docs": {
4
      "command": "npx",
5
      "args": ["@vapi-ai/mcp-server"]
6
    }
7
  }
8
}

What knowledge is provided

Your IDE gains access to:

• Complete API Reference - Every endpoint, parameter, and response
• Code Examples - Working samples for all features
• Integration Guides - Step-by-step implementation patterns
• Best Practices - Recommended approaches and patterns
• Latest Features - Always up-to-date with new releases
• Troubleshooting - Common issues and solutions

Using your enhanced IDE

Example prompts

Once MCP is configured, try these prompts in your IDE:

1
import { VapiClient } from "@vapi-ai/server-sdk";
2
3
const client = new VapiClient({ token: process.env.VAPI_API_KEY });
4
5
const assistant = await client.assistants.create({
6
  name: "Customer Support",
7
  model: {
8
    provider: "openai",
9
    model: "gpt-4",
10
    systemPrompt: "You are a helpful customer support agent..."
11
  },
12
  voice: {
13
    provider: "11labs",
14
    voiceId: "rachel"
15
  }
16
});

1
app.post('/webhook', async (req, res) => {
2
  const { type, call, assistant } = req.body;
3
  
4
  switch (type) {
5
    case 'call-started':
6
      console.log(`Call ${call.id} started`);
7
      break;
8
    case 'speech-update':
9
      console.log(`User said: ${req.body.transcript}`);
10
      break;
11
    case 'function-call':
12
      // Handle tool calls
13
      const { functionName, parameters } = req.body.functionCall;
14
      const result = await handleFunction(functionName, parameters);
15
      res.json({ result });
16
      return;
17
  }
18
  
19
  res.status(200).send();
20
});

1
const assistant = await client.assistants.create({
2
  name: "Recorded Assistant",
3
  recordingEnabled: true,
4
  artifactPlan: {
5
    recordingEnabled: true,
6
    videoRecordingEnabled: false,
7
    recordingPath: "s3://my-bucket/recordings/{call_id}"
8
  },
9
  credentialIds: ["aws-s3-credential-id"]
10
});

Best practices

Configuration options

Check status

View current MCP configuration:

$
vapi mcp status

Output:

MCP Configuration Status:
✓ Cursor: Configured (.cursor/mcp.json)
✗ Windsurf: Not configured
✓ VSCode: Configured (workspace settings)
Vapi MCP Server: v1.2.3 (latest)

Update server

Keep the MCP server updated:

$
# Update to latest version
$
npm update -g @vapi-ai/mcp-server
$
$
# Or reinstall
$
npm install -g @vapi-ai/mcp-server@latest

Remove configuration

Remove MCP configuration:

$
# Remove from all IDEs
$
vapi mcp remove
$
$
# Remove from specific IDE
$
vapi mcp remove cursor

How MCP tools work

The Vapi MCP server provides these tools to your IDE:

Troubleshooting

$
# Verify installation
$
npm list -g @vapi-ai/mcp-server

$
# Install with proper permissions
$
sudo npm install -g @vapi-ai/mcp-server
$
$
# Or use a Node version manager
$
nvm use 18
$
npm install -g @vapi-ai/mcp-server

$
npm update -g @vapi-ai/mcp-server

Advanced usage

Custom MCP configuration

Modify the generated MCP configuration for advanced needs:

1
{
2
  "servers": {
3
    "vapi-docs": {
4
      "command": "npx",
5
      "args": ["@vapi-ai/mcp-server"],
6
      "env": {
7
        "VAPI_MCP_LOG_LEVEL": "debug"
8
      }
9
    }
10
  }
11
}

Using with teams

Share MCP configuration with your team:

1. Commit the config files (.cursor/mcp.json, etc.)
2. Document the setup in your README
3. Include in onboarding for new developers

Example README section:

1
## Development Setup
2
3
This project uses Vapi MCP for enhanced IDE support:
4
5
1. Install Vapi CLI: `curl -sSL https://vapi.ai/install.sh | bash`
6
2. Set up MCP: `vapi mcp setup`
7
3. Restart your IDE

Next steps

Now that MCP is configured:

• Create assistants: Build your first voice AI
• Test webhooks locally: Debug webhooks with tunneling services
• Manage resources: Use CLI commands

Pro tip: After setting up MCP, try asking your IDE to “Create a complete Vapi voice assistant with error handling and logging” - watch it generate production-ready code with all the right patterns!