Skip to main content
The Voiceflow MCP server is a remote Model Context Protocol (MCP) server that connects AI clients like Claude Code directly to your Voiceflow account. Once it’s connected, the assistant can work with your projects much like you would in Creator: listing projects, reading and editing prompts, building functions and tools, querying the knowledge base, pulling transcripts, running evaluations, and testing agents, all without copying anything back and forth. It’s a hosted server at https://mcp.voiceflow.com/mcp that authenticates with OAuth, so there are no API keys to manage. You sign in to Voiceflow once, and the assistant acts on the projects your account can access. The setup guide walks through connecting the server to Claude Code.

​
What you can do

The server exposes Voiceflow’s agent-management surface as tools, grouped by capability: The server provides both read and write access, so the assistant can inspect a project and make changes to it. A well-behaved client confirms changes with you before applying them.

​
How it works

  • Plain language, not tool names. Once connected, you don’t call tools directly. You describe what you want, for example “pull the last 50 transcripts for my support agent and find where it’s failing”, and the client picks the right tools.
  • Namespaced tools. Every tool is exposed to the client as mcp__voiceflow__*, so it never collides with other servers you’ve connected.
  • Scoped to your account. The assistant can only see and change the projects your signed-in Voiceflow account has access to.
Not sure where to start? After connecting, ask the assistant to “list my Voiceflow projects”. It’s the quickest way to confirm the server is working and see what’s available.

​
Get started

Set up Voiceflow in Claude Code

Connect the MCP server to Claude Code and sign in with your account.