voiceflow -client
MCP server from voiceflow-community/voiceflow-mcp-server-client
claude mcp add --transport stdio voiceflow-community-voiceflow-mcp-server-client node path/to/server.js
How to use
This Voiceflow MCP Client acts as a Node.js client that connects to remote MCP servers to expose tools for your Voiceflow Agent. It supports managing multiple remote MCP servers and communicates over HTTP, enabling tool discovery and integration with Claude AI. Use this client to orchestrate different MCP servers (such as weather, calendar, or other domain-specific tools) under a unified Voiceflow experience. The client is designed to be configured dynamically via environment variables and a servers-config.json file, allowing you to enable, disable, or pre-approve tools from each server as needed. Resources from the remote MCP servers are surfaced with prefixed tool names to avoid collisions, ensuring clear attribution like weather_getWeather or calendar_createEvent in your agent’s tooling surface.
How to install
Prerequisites:
- Node.js 20.x or higher
- npm
Installation steps:
-
Clone the repository with submodules: git clone --recursive https://github.com/voiceflow-gallagan/voiceflow-mcp-server-client.git
Or, if you already cloned it: git submodule update --init --recursive
-
Install dependencies: npm install
-
Build the MCP servers (if required by the project setup): npm run build Note: The build process may initialize submodules and dependencies for remote MCP servers. Follow any prompts in the console.
-
Set up environment variables (copy template and customize): cp .env.template .env
Edit .env to add your actual keys and settings
-
Run the client server: npm start
Optional: If you need to customize server configurations, add a servers-config.json in the project root with entries for each remote MCP server, following the documented schema in the repository.
Additional notes
Tips and considerations:
- You can enable or disable individual remote MCP servers via the servers-config.json or via environment-driven dynamic configuration (e.g., Zapier server URL) without code changes.
- Ensure you provide required API keys and tokens in environment variables (e.g., ANTHROPIC_API_KEY, BRAVE_API_KEY, etc.) as described in the README.
- When using dynamic server configuration, remember that only the Zapier server supports runtime configuration via ZAPIER_MCP_URL at this time.
- If you encounter Chrome/Playwright setup prompts, you may need elevated privileges to install browser binaries during build; run with appropriate permissions.
- Tool naming prefixes (per server) help avoid conflicts in the Voiceflow agent tooling surface.
Related MCP Servers
zen
Selfhosted notes app. Single golang binary, notes stored as markdown within SQLite, full-text search, very low resource usage
MCP -Deepseek_R1
A Model Context Protocol (MCP) server implementation connecting Claude Desktop with DeepSeek's language models (R1/V3)
mcp-fhir
A Model Context Protocol implementation for FHIR
mcp
Inkdrop Model Context Protocol Server
mcp-appium-gestures
This is a Model Context Protocol (MCP) server providing resources and tools for Appium mobile gestures using Actions API..
dubco -npm
The (Unofficial) dubco-mcp-server enables AI assistants to manage Dub.co short links via the Model Context Protocol. It provides three MCP tools: create_link for generating new short URLs, update_link for modifying existing links, and delete_link for removing short links.