SIGN UPLOG IN
X (Twitter)LinkedInGitHubDiscordYouTube

How to integrate Voiceflow MCP with Atomic Agent

Connect Atomic Agent to Voiceflow MCP. Start a voiceflow test run now, deploy latest voiceflow version to staging, and more using natural language, with authentication handled for you.

Get started for freeGet a demo
Voiceflow logoVoiceflow
Api Key

Voiceflow is a platform for building, deploying, testing, and analyzing conversational AI agents. Use it to design voice and chat experiences with visual flows and real-time analytics.

20 Tools

Introduction

Atomic Agent is an open-source AI agent that runs on your machine and supports local models through llama.cpp. Connect it to 1,500+ apps through Composio, including Voiceflow.

This guide uses Atomic Agent's built-in Composio integration. You need Atomic Agent v0.5.6 or later, your own Composio API key, and a Voiceflow account. See the Atomic Agent documentation for installation instructions.

Also integrate Voiceflow with

ChatGPTClaude CoworkHermes

How Atomic Agent connects to Voiceflow

Atomic Agent connects to Composio's Tool Router over Streamable HTTP MCP. It discovers the tools needed for your request, and Composio handles account authentication.

Execution and account-connection tools follow Atomic Agent's configured approval policy. Review any approval prompt before allowing an action on your connected account.

Connect Voiceflow to Atomic Agent

  1. Sign up or sign in to the Composio dashboard. Copy your API key.
  2. In Atomic Agent, open the Integrations tab and select Composio. Select API key, press e, paste the key, and press Enter. The tools become available immediately, without a restart.
  3. Ask Atomic Agent to do something in Voiceflow. It searches Composio for the right tool.
  4. On first use, open the sign-in link returned in the chat. Connect your Voiceflow account, then return to Atomic Agent to continue.

Headless setup

Add the following line to ~/.atomic-agent/.env, replacing YOUR_COMPOSIO_API_KEY with your key. Start Atomic Agent after saving the file.

bash
COMPOSIO_API_KEY=YOUR_COMPOSIO_API_KEY

What is the Voiceflow MCP server, and what's possible with it?

The Voiceflow MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Voiceflow account. It provides structured and secure access so your agent can perform Voiceflow operations on your behalf.

Use Voiceflow from Atomic Agent

With your account connected, ask Atomic Agent to work with Voiceflow in natural language. You can connect more apps through the same Composio integration as you need them.

Visit the Atomic Agent website or inspect the Atomic Agent source code.

Troubleshooting

Why is my API key rejected?

Copy the key directly from the Composio dashboard. Atomic Agent requires ASCII characters because it sends the key in an HTTP header. Remove any extra characters introduced when copying.

Why are Composio tools unavailable after saving a key?

Check that you use Atomic Agent v0.5.6 or later and that Composio is enabled in your configuration. A "composio": { "enabled": false } setting disables the integration while keeping the saved key on disk.

Does Composio have a free plan?

The Hobby plan includes 100,000 tool calls per month. Composio-managed OAuth apps have a lower included allowance. See Composio pricing for the current limits that apply to your connection.

TOOLS

Supported Tools

Every Voiceflow action and event your agent gets out of the box.

Create Variable

Create one user-defined variable in a Voiceflow project environment and return its assigned ID and configuration.

Delete Variable

Permanently delete one user-defined variable by ID.

Export Environment

Return a complete JSON snapshot of one Voiceflow environment, including agent, workflows, tools, functions, variables, and knowledge-base records.

Get Agent Configuration

Return one project environment's agent configuration; optionally include its large global prompt and instructions.

Get Conversation State

Read a user's Voiceflow conversation variables, storage, and execution stack for a draft or published environment.

Get Transcript

Return one transcript with its full conversation logs, properties, evaluations, and recording URL.

Import Knowledge Document from URL

Crawl one public web URL into a Voiceflow knowledge base and return the created document and ingestion status.

List Agent Components

List playbooks, API tools, functions, project-level evaluations, MCP servers or tools, attached tools, or tests for a Voiceflow project and, where applicable, an environment.

List Environments

Return a project's environments, aliases, release history, and live traffic percentages.

List Knowledge Documents

Return all knowledge-base documents in one project environment with their IDs, sources, ingestion status, and chunking settings.

List Projects

Return every Voiceflow project in one workspace, including project IDs used by agent, runtime, and authoring tools.

List Variables

Return system and user-defined variables in one project environment with IDs, defaults, descriptions, and ownership flags.

List Workspaces

Return every Voiceflow workspace accessible to the connected account, including IDs needed to list projects.

Publish Environment

Publish a Voiceflow environment as a named release.

Query Knowledge Base

Retrieve relevant document chunks and optionally synthesize an answer from a project's draft or published Voiceflow knowledge base.

Query Project Analytics

Return one Voiceflow project-level analytics metric as a time series for a requested date range and interval.

Search Transcripts

Search a project's conversation transcripts by time, environment, version, session, and transcript-property filters, returning one bounded page.

Send Conversation Message

Send one text turn to a Voiceflow agent and return its typed response traces; this invokes the agent and may consume model usage.

Update Conversation Variables

Merge named variable values into one user's existing conversation state without replacing storage or the execution stack.

Update Variable

Update selected editable fields of one user-defined variable; omitted fields remain unchanged.

FRAMEWORKS

How to build Voiceflow MCP Agent with another framework

ChatGPT logo

ChatGPT

Use Voiceflow MCP with ChatGPT

Claude Cowork logo

Claude Cowork

Use Voiceflow MCP with Claude Cowork

Hermes logo

Hermes

Use Voiceflow MCP with Hermes

FAQ

Frequently asked questions

With a standalone Voiceflow MCP server, the agents and LLMs can only access a fixed set of Voiceflow tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Voiceflow and many other apps based on the task at hand, all through a single MCP endpoint.

Yes, you can. Atomic Agent fully supports MCP integration. You get structured tool calling, message history handling, and model orchestration while Tool Router takes care of discovering and serving the right Voiceflow tools.

Yes, absolutely. You can configure which Voiceflow scopes and actions are allowed when connecting your account to Composio. You can also bring your own OAuth credentials or API configuration so you keep full control over what the agent can do.

All sensitive data such as tokens, keys, and configuration is fully encrypted at rest and in transit. Composio is SOC 2 Type 2 compliant and follows strict security practices so your Voiceflow data and credentials are handled as safely as possible.

Start with Voiceflow.It takes 30 seconds.

Managed auth, hosted MCP servers, and every Voiceflow tool your agent needs.Free to start.

Start building