How to integrate Captions MCP with OpenClaw

OpenClaw is the fastest growing agent harness out there, which can work 24/7 to automate almost any kind of tasks. However, its capabilities are limited to the tools it has access to. Composio allows your OpenClaw to access Captions with authentication management handled for you. You can execute actions on Captions via your favorite OpenClaw interface (Telegram, WhatsApp, TUI, etc), whichever you prefer.

Captions logoCaptions
Api Key

Captions provides the Mirage API for generating videos, speech, and styled captions. Use it to automate polished video creation, voiceovers, and captioning from one API.

8 Tools

Introduction

OpenClaw is the fastest growing agent harness out there, which can work 24/7 to automate almost any kind of tasks. However, its capabilities are limited to the tools it has access to. Composio allows your OpenClaw to access Captions with authentication management handled for you. You can execute actions on Captions via your favorite OpenClaw interface (Telegram, WhatsApp, TUI, etc), whichever you prefer.

Also integrate Captions with

Why use Composio?

Apart from a managed and hosted MCP server, you will get:

  • Programmatic tool calling allows LLMs to write its code in a remote workbench to handle complex tool chaining. Reduces to-and-fro with LLMs for frequent tool calling.
  • Handling Large tool responses out of LLM context to minimize context rot.
  • Dynamic just-in-time access to 20,000 tools across 1000+ other Apps for cross-app workflows. It loads the tools you need, so LLMs aren't overwhelmed by tools you don't need.

How to install Captions with OpenClaw

Using Composio API Key and Setup Prompt

Copy the setup prompt from the OpenClaw dashboard
  • Run it in your OpenClaw chat interface.
  • Authenticate Captions from the dashboard
  • Go back to your OpenClaw interface and start asking questions.

Using OpenClaw/Composio Plugin

1. Install OpenClaw Composio plugin

bash
openclaw plugins install @composio/openclaw-plugin

2. Copy the API Key from dashboard.composio.dev

3. Setup OpenClaw Config

bash
openclaw config set plugins.entries.composio.config.consumerKey "ck_your_key_here"

4. Restart OpenClaw

bash
openclaw gateway restart

5. Go to your chat interface and start asking questions.

6. When prompted, authenticate the app and you're all set.

How It Works

The plugin connects to Composio's MCP server at https://connect.composio.dev/mcp and registers all available tools directly into the OpenClaw agent. Tools are called by name — no extra search or execute steps needed.

If a tool returns an auth error, the agent will prompt you to connect that toolkit at dashboard.composio.dev.

Configuration

bash
{
  "plugins": {
    "entries": {
      "composio": {
        "enabled": true,
        "config": {
          "consumerKey": "ck_your_key_here"
        }
      }
    }
  }
}
OptionDescriptionDefault
enabledEnable or disable the plugintrue
consumerKeyYour Composio consumer key (ck_...)—
mcpUrlMCP server URL (advanced)https://connect.composio.dev/mcp

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

The Captions MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Captions account. It provides structured and secure access to Mirage video, speech, and caption tools, so your agent can generate speech, create videos, add styled captions, track progress, and download completed videos on your behalf.

  • Speech generation: Have your agent turn written scripts into WAV speech using a known Mirage voice.
  • Portrait video creation: Direct your agent to animate a portrait image with speech audio and create a video.
  • Styled video captions: Let the agent browse available caption styles, review a chosen style, and add it to a video.
  • Job tracking: Instruct your agent to check video generation and captioning progress, including any errors that need attention.
  • Video library and downloads: Have your agent list your video jobs and download completed videos as MP4 files.

Conclusion

You've successfully integrated Captions with OpenClaw using Composio plugin. Now interact with Captions directly from your terminal, Web UI, or any messenger app using natural language commands.

Key benefits of this setup:

  • Seamless integration across TUI, Web UIs, and Messenger apps like Telegram, WhatsApp, Slack, etc.
  • Natural language commands for Captions operations
  • Managed authentication through Composio
  • Access to 20,000+ tools across 1000+ apps for cross-app workflows
  • Programmatic tool calling for complex tool chaining

Next steps:

  • Try asking OpenClaw to perform various Captions operations
  • Explore cross-app workflows by connecting more toolkits like Calendar, Slack, Notion, etc.
  • Build complex automation scripts that leverage OpenClaw's 24/7 running capabilities
TOOLS

Supported Tools

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

Add Captions

Start an asynchronous job that transcribes and renders a selected caption style onto an uploaded or existing completed video.

Download Video

Download the MP4 content of a completed video job and return an offloaded file reference.

Generate Speech

Generate WAV speech synchronously from text using a known Mirage voice ID and return an offloaded audio file reference.

Generate Video

Start an asynchronous Mirage Video 1 job that animates a portrait image using speech audio.

Get Caption Template

Retrieve one caption style by ID, including its name and preview video URL.

Get Video Status

Retrieve the current state, progress, and error details for a video generation or captioning job.

List Caption Templates

Return one page of available caption styles, including names and preview video URLs.

List Videos

Return one page of video jobs owned by the connected Mirage account, including each job's status and progress.

FAQ

Frequently asked questions

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

Yes, you can. OpenClaw 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 Captions tools.

Yes, absolutely. You can configure which Captions 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 Captions data and credentials are handled as safely as possible.

Start with Captions.It takes 30 seconds.

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

Start building