What environment variables are required?
The server requires `VAPI_ORG_ID`, `VAPI_PRIVATE_KEY`, `VAPI_KNOWLEDGE_ID`, `VAPI_JWT_PRIVATE`, and `NODE_ENV` (set to `development`).
@matthewdcage
基本情報
Vapi.ai MCP server & HTTP Server
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"vapi-mcp": {
"command": "node",
"args": [
"--trace-warnings",
"dist/index.js"
]
}
}
}ツール一覧はまだありません
この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。
ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。
Vapi MCP for Cursor is a Model Context Protocol (MCP) server that integrates Vapi's voice AI capabilities with the Cursor editor, allowing users to manage Vapi voice assistants, make outbound calls, and retrieve conversation details directly from Cursor.
Configure the server in Cursor's .cursor/mcp.json file with the required environment variables and working directory. Build the server with npm install && npm run build inside the vapi-mcp-server directory, then set the command to node, type to stdio, and provide the absolute path to dist/index.js along with the cwd parameter.
The server requires `VAPI_ORG_ID`, `VAPI_PRIVATE_KEY`, `VAPI_KNOWLEDGE_ID`, `VAPI_JWT_PRIVATE`, and `NODE_ENV` (set to `development`).
Ensure the `cwd` parameter is set correctly, all environment variables are passed in the MCP configuration, `package.json` has `"type": "module"`, and the `dist/index.js` file is executable. Test the server manually with `node --trace-warnings dist/index.js`.
The server uses the `stdio` transport type for proper integration with Cursor.
The server must be run from the `vapi-mcp/vapi-mcp-server` directory, and the `cwd` parameter in the MCP configuration must point to that directory.
If "Cannot find module" errors occur, check that the working directory is correct, rebuild with `npm run build`, and ensure all dependencies are installed with `npm install`.
Set up and manage the Eddyter AI rich text editor by talking to your AI agent — for Claude, Cursor, Codex and other MCP tools. A Model Context Protocol server that lets AI tools add Eddyter to a React, Next.js, Vite or R
MCP server that lets Claude Code, Cursor or Codex ask you for API keys on a local page and write them to .env. The agent only ever sees key names.
OrangePro local-first CLI + MCP server for behavior mapping, grounded test generation, and dynamic proof.

Modelglass turns "which model should I use?" into a lookup instead of a guess. Seven tools give your agent live pricing across image, language, video, and audio models. Sourced and versioned, not scraped once and forgott
コメント