How to Use the Voiceflow MCP in Claude Code

Q: How do I use Voiceflow and Claude Code in a CI/CD pipeline?

You treat it like any other API call. Your script calls interact to make the agent perform an action, captures the output, and then runs further steps based on that result. It's completely headless.

Q: Can Voiceflow and Claude Code manage conversation state?

Yes. You use getstate to read variables at a specific point in the script execution, or you can proactively set new values using savestate. This lets your automation track progress across multiple steps.

Q: What is the process for Voiceflow and Claude Code when querying knowledge?

First, run listkbtags to determine which categories are available. Then, use querykb with a targeted question. The script receives clean text output it can pass directly into other tools.

Q: Does Voiceflow and Claude Code support viewing transcripts?

It does. You can list all conversation records using listtranscripts, or if you need the full payload for a single run, use gettranscript. This is great for logging failed jobs.

Q: What data privacy information is touched by Voiceflow and Claude Code?

The server interacts with conversation state variables (getstate) and reads the text content of knowledge base documents via querykb. These are the primary pieces of user data handled.

Run Voiceflow agent logic headless in Claude Code for CI/CD pipelines.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Voiceflow MCP to Claude Code

Create your Vinkius account to connect Voiceflow to Claude Code and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Voiceflow with Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate knowledge base retrieval.

In a pipeline script, you don't want manual input. Use `list_kb_docs` to check what documentation exists before running the query. Then, pipe your actual question through `query_kb` to get clean, structured data into your build process.

Simulate and test agent communication.

You can write scripts that simulate user behavior by calling `interact`. After the action completes, you run `get_state` to verify that the variables updated correctly. This lets you validate flow logic without a UI.

Audit agent status and project metadata.

Before deploying or running a job, check what agents exist using `list_projects`. Need historical proof? Run `list_transcripts` to pull a list of past conversations for logging purposes. This is essential for auditing.

Setup guide

Set up Voiceflow MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see voiceflow-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest Voiceflow transactions." It will automatically discover and invoke the available Voiceflow tools.

Terminal

claude mcp add --transport http voiceflow-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
2

Add the Voiceflow MCP

Paste the JSON snippet shown on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "voiceflow-mcp": {
      "type": "url",
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Voiceflow. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Voiceflow now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Voiceflow MCP in Claude Code

You treat it like any other API call. Your script calls `interact` to make the agent perform an action, captures the output, and then runs further steps based on that result. It's completely headless.

Yes. You use `get_state` to read variables at a specific point in the script execution, or you can proactively set new values using `save_state`. This lets your automation track progress across multiple steps.

First, run `list_kb_tags` to determine which categories are available. Then, use `query_kb` with a targeted question. The script receives clean text output it can pass directly into other tools.

It does. You can list all conversation records using `list_transcripts`, or if you need the full payload for a single run, use `get_transcript`. This is great for logging failed jobs.

The server interacts with conversation state variables (`get_state`) and reads the text content of knowledge base documents via `query_kb`. These are the primary pieces of user data handled.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript