Vapi Voice AI
Vapi MCP for Cursor integrates Vapi's voice AI capabilities with the Cursor editor through the Model Context Protocol, enabling AI assistants to make outbound calls, manage voice assistants, and retrieve conversation transcripts. The implementation consists of two server components: a core MCP server that handles direct communication with Cursor, and an HTTP server that provides RESTful API endpoints for broader integration with services like n8n. Built with TypeScript and leveraging the Vapi Server SDK, this implementation supports creating customizable voice assistants with different voices and models, initiating phone calls with AI-driven conversations, and analyzing call transcripts—making it particularly useful for automated customer outreach, sales calls, and support interactions.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately.
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- api-integration
- Source
- PulseMCP
- Repository
- github.com/matthewdcage/vapi-mcp
- Author type
- human
- Updated
- 2026-04-25
Use via MCP
Resolve Vapi Voice AI from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.