MCP.so
ログイン

Voiceflow MCP Client

@voiceflow-gallagan

基本情報

カテゴリ

その他

トランスポート

stdio

作者

voiceflow-gallagan

Voiceflow MCP Client について

概要はまだありません

Voiceflow MCP Client の設定

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": {
    "voiceflow-mcp-server-client": {
      "command": "docker",
      "args": [
        "build",
        "-t",
        "mcp-client",
        "."
      ]
    }
  }
}

Voiceflow MCP Client のツール

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。

概要

What is Voiceflow MCP Client?

A Node.js client for the Model Context Protocol (MCP) that integrates with remote MCP servers to provide tools for your Voiceflow Agent.

How to use Voiceflow MCP Client?

Install Node.js 20+, clone the repository with submodules, install dependencies, build MCP servers, set up a .env file with required keys, configure servers-config.json, then run npm start to start the API server on the configured port.

Key features of Voiceflow MCP Client

  • Support for multiple remote MCP servers via HTTP transport
  • Tool discovery and integration with Claude AI
  • Dynamic server configuration (Zapier) through environment variables
  • Automatic error handling and retries
  • Docker support with health check and volume mounting
  • Command-based and environment-variable-substituted server configuration

Use cases of Voiceflow MCP Client

  • Building Voiceflow agents that can search the web via Brave Search
  • Integrating Google Calendar management into a Voiceflow agent
  • Combining weather data lookups with conversational AI
  • Using Playwright for headless web browsing within a Voiceflow agent
  • Automating workflows by connecting to Zapier MCP server

よくある質問

1

What is the Model Context Protocol (MCP)?

MCP is a protocol that allows AI agents to discover and invoke tools from remote servers. This client connects to MCP servers and makes their tools available to a Voiceflow agent via Claude AI.

2

What are the prerequisites to run the client?

Node.js 20.x or higher and npm are required. For Google Calendar, OAuth 2.0 credentials from Google Cloud Console are needed. An Anthropic API key and a Brave Search API key are also required.

3

How do I configure Google Calendar integration?

Set the `GCP_SAVED_TOKENS` and `GCP_OAUTH_KEYS` environment variables with the full JSON objects from the OAuth flow and client configuration file.

4

Can I add other MCP servers dynamically?

Dynamic server configuration via environment variables is currently only available for the Zapier server using `ZAPIER_MCP_URL`. Other servers are configured in `servers-config.json`.

5

How do I run the client with Docker?

Build the image with `docker build -t mcp-client .` and run with `docker run -p 3000:3000 --env-file .env --name mcp-client mcp-client`. A health check endpoint is available at `/health`.

コメント

「その他」の他のコンテンツ