How to integrate Runway MCP with OpenAI Agents SDK

This guide walks you through connecting Runway to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working Runway agent that can generate images, create videos, produce speech, make sound effects, and manage documents through natural language commands. This guide will help you understand how to give your OpenAI Agents SDK agent real control over a Runway account through Composio's Runway MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved.

Runway logoRunway
Api Key

Runway is a generative AI media platform for creating and transforming video, images, audio, avatars, voices, and creative workflows. It helps teams build high-quality visual content faster with API-driven media generation.

22 Tools

Introduction

This guide walks you through connecting Runway to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working Runway agent that can generate images, create videos, produce speech, make sound effects, and manage documents through natural language commands.

This guide will help you understand how to give your OpenAI Agents SDK agent real control over a Runway account through Composio's Runway MCP server.

Before we dive in, let's take a quick look at the key ideas and tools involved.

Also integrate Runway with

TL;DR

Here's what you'll learn:
  • Get and set up your OpenAI and Composio API keys
  • Install the necessary dependencies
  • Initialize Composio and create a Tool Router session for Runway
  • Configure an AI agent that can use Runway as a tool
  • Run a live chat session where you can ask the agent to perform Runway operations

What is OpenAI Agents SDK?

The OpenAI Agents SDK is a lightweight framework for building AI agents that can use tools and maintain conversation state. It provides a simple interface for creating agents with hosted MCP tool support.

Key features include:

  • Hosted MCP Tools: Connect to external services through hosted MCP endpoints
  • SQLite Sessions: Persist conversation history across interactions
  • Simple API: Clean interface with Agent, Runner, and tool configuration
  • Streaming Support: Real-time response streaming for interactive applications

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

The Runway MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Runway account. It provides structured and secure access to your generative media, workflows, knowledge documents, and account usage, so your agent can generate media, transform content, run workflows, manage documents, and monitor activity on your behalf.

  • Image and video generation: Have your agent create images from prompts, generate videos from text, or animate existing images with your chosen Runway model.
  • Media transformation and upscaling: Direct your agent to restyle existing videos or upscale images and videos for higher-quality results.
  • Speech and sound creation: Let the agent synthesize speech with supported voices or generate sound effects from written descriptions.
  • Workflow and knowledge management: Instruct your agent to inspect and run published workflows, then create, review, update, or delete knowledge documents used by avatar workflows.
  • Task, credit, and usage monitoring: Have your agent check generation progress, retrieve completed media, cancel running tasks, and review credit balances, quotas, and daily usage.

What is the Composio tool router, and how does it fit here?

What is Composio SDK?

Composio's Composio SDK helps agents find the right tools for a task at runtime. You can plug in multiple toolkits (like Gmail, HubSpot, and GitHub), and the agent will identify the relevant app and action to complete multi-step workflows. This can reduce token usage and improve the reliability of tool calls. Read more here: Getting started with Composio SDK

The tool router generates a secure MCP URL that your agents can access to perform actions.

How the Composio SDK works

The Composio SDK follows a three-phase workflow:

  1. Discovery: Searches for tools matching your task and returns relevant toolkits with their details.
  2. Authentication: Checks for active connections. If missing, creates an auth config and returns a connection URL via Auth Link.
  3. Execution: Executes the action using the authenticated connection.

Step-by-step Guide

Step by step09 STEPS
1

Prerequisites

Before starting, make sure you have:
  • Composio API Key and OpenAI API Key
  • Primary know-how of OpenAI Agents SDK
  • A live Runway project
  • Some knowledge of Python or Typescript
2

Getting API Keys for OpenAI and Composio

OpenAI API Key
  • Go to the OpenAI dashboard and create an API key. You'll need credits to use the models, or you can connect to another model provider.
  • Keep the API key safe.
Composio API Key
3

Install dependencies

npm install @composio/openai-agents @openai/agents dotenv

Install the Composio SDK and the OpenAI Agents SDK.

4

Set up environment variables

bash
OPENAI_API_KEY=sk-...your-api-key
COMPOSIO_API_KEY=your-api-key
USER_ID=composio_user@gmail.com

Create a .env file and add your OpenAI and Composio API keys.

5

Import dependencies

import 'dotenv/config';
import { Composio } from '@composio/core';
import { OpenAIAgentsProvider } from '@composio/openai-agents';
import { Agent, hostedMcpTool, run, OpenAIConversationsSession } from '@openai/agents';
import * as readline from 'readline';
What's happening:
  • You're importing all necessary libraries.
  • The Composio and OpenAIAgentsProvider classes are imported to connect your OpenAI agent to Composio tools like Runway.
6

Set up the Composio instance

dotenv.config();

const composioApiKey = process.env.COMPOSIO_API_KEY;
const userId = process.env.USER_ID;

if (!composioApiKey) {
  throw new Error('COMPOSIO_API_KEY is not set. Create a .env file with COMPOSIO_API_KEY=your_key');
}
if (!userId) {
  throw new Error('USER_ID is not set');
}

// Initialize Composio
const composio = new Composio({
  apiKey: composioApiKey,
  provider: new OpenAIAgentsProvider(),
});
What's happening:
  • dotenv.config() loads your .env file so COMPOSIO_API_KEY and USER_ID are available as environment variables.
  • Creating a Composio instance using the API Key and OpenAIAgentsProvider class.
7

Create a Tool Router session

// Create Tool Router session for Runway
const session = await composio.create(userId as string, {
  toolkits: ['runway'],
});
const mcpUrl = session.mcp.url;

What is happening:

  • You give the Tool Router the user id and the toolkits you want available. Here, it is only runway.
  • The router checks the user's Runway connection and prepares the MCP endpoint.
  • The returned session.mcp.url is the MCP URL that your agent will use to access Runway.
  • This approach keeps things lightweight and lets the agent request Runway tools only when needed during the conversation.
8

Configure the agent

// Configure agent with MCP tool
const agent = new Agent({
  name: 'Assistant',
  model: 'gpt-5',
  instructions:
    'You are a helpful assistant that can access Runway. Help users perform Runway operations through natural language.',
  tools: [
    hostedMcpTool({
      serverLabel: 'tool_router',
      serverUrl: mcpUrl,
      headers: { 'x-api-key': composioApiKey },
      requireApproval: 'never',
    }),
  ],
});
What's happening:
  • We're creating an Agent instance with a name, model (gpt-5), and clear instructions about its purpose.
  • The agent's instructions tell it that it can access Runway and help with queries, inserts, updates, authentication, and fetching database information.
  • The tools array includes a hostedMcpTool that connects to the MCP server URL we created earlier.
  • The headers object includes the Composio API key for secure authentication with the MCP server.
  • requireApproval: 'never' means the agent can execute Runway operations without asking for permission each time, making interactions smoother.
9

Start chat loop and handle conversation

// Keep conversation state across turns
const conversationSession = new OpenAIConversationsSession();

// Simple CLI
const rl = readline.createInterface({
  input: process.stdin,
  output: process.stdout,
  prompt: 'You: ',
});

console.log('\nComposio Tool Router session created.');
console.log('\nChat started. Type your requests below.');
console.log("Commands: 'exit', 'quit', or 'q' to end\n");

try {
  const first = await run(agent, 'What can you help me with?', { session: conversationSession });
  console.log(`Assistant: ${first.finalOutput}\n`);
} catch (e) {
  console.error('Error:', e instanceof Error ? e.message : e, '\n');
}

rl.prompt();

rl.on('line', async (userInput) => {
  const text = userInput.trim();

  if (['exit', 'quit', 'q'].includes(text.toLowerCase())) {
    console.log('Goodbye!');
    rl.close();
    process.exit(0);
  }

  if (!text) {
    rl.prompt();
    return;
  }

  try {
    const result = await run(agent, text, { session: conversationSession });
    console.log(`\nAssistant: ${result.finalOutput}\n`);
  } catch (e) {
    console.error('Error:', e instanceof Error ? e.message : e, '\n');
  }

  rl.prompt();
});

rl.on('close', () => {
  console.log('\n👋 Session ended.');
  process.exit(0);
});
What's happening:
  • The program prints a session URL that you visit to authorize Runway.
  • After authorization, the chat begins.
  • Each message you type is processed by the agent using run().
  • The responses are printed to the console.
  • Typing exit, quit, or q cleanly ends the chat.

Complete Code

Here's the complete code to get you started with Runway and OpenAI Agents SDK:

import 'dotenv/config';
import { Composio } from '@composio/core';
import { OpenAIAgentsProvider } from '@composio/openai-agents';
import { Agent, hostedMcpTool, run, OpenAIConversationsSession } from '@openai/agents';
import * as readline from 'readline';

const composioApiKey = process.env.COMPOSIO_API_KEY;
const userId = process.env.USER_ID;

if (!composioApiKey) {
  throw new Error('COMPOSIO_API_KEY is not set. Create a .env file with COMPOSIO_API_KEY=your_key');
}
if (!userId) {
  throw new Error('USER_ID is not set');
}

// Initialize Composio
const composio = new Composio({
  apiKey: composioApiKey,
  provider: new OpenAIAgentsProvider(),
});

async function main() {
  // Create Tool Router session
  const session = await composio.create(userId as string, {
    toolkits: ['runway'],
  });
  const mcpUrl = session.mcp.url;

  // Configure agent with MCP tool
  const agent = new Agent({
    name: 'Assistant',
    model: 'gpt-5',
    instructions:
      'You are a helpful assistant that can access Runway. Help users perform Runway operations through natural language.',
    tools: [
      hostedMcpTool({
        serverLabel: 'tool_router',
        serverUrl: mcpUrl,
        headers: { 'x-api-key': composioApiKey },
        requireApproval: 'never',
      }),
    ],
  });

  // Keep conversation state across turns
  const conversationSession = new OpenAIConversationsSession();

  // Simple CLI
  const rl = readline.createInterface({
    input: process.stdin,
    output: process.stdout,
    prompt: 'You: ',
  });

  console.log('\nComposio Tool Router session created.');
  console.log('\nChat started. Type your requests below.');
  console.log("Commands: 'exit', 'quit', or 'q' to end\n");

  try {
    const first = await run(agent, 'What can you help me with?', { session: conversationSession });
    console.log(`Assistant: ${first.finalOutput}\n`);
  } catch (e) {
    console.error('Error:', e instanceof Error ? e.message : e, '\n');
  }

  rl.prompt();

  rl.on('line', async (userInput) => {
    const text = userInput.trim();

    if (['exit', 'quit', 'q'].includes(text.toLowerCase())) {
      console.log('Goodbye!');
      rl.close();
      process.exit(0);
    }

    if (!text) {
      rl.prompt();
      return;
    }

    try {
      const result = await run(agent, text, { session: conversationSession });
      console.log(`\nAssistant: ${result.finalOutput}\n`);
    } catch (e) {
      console.error('Error:', e instanceof Error ? e.message : e, '\n');
    }

    rl.prompt();
  });

  rl.on('close', () => {
    console.log('\nSession ended.');
    process.exit(0);
  });
}

main().catch((err) => {
  console.error('Fatal error:', err);
  process.exit(1);
});

Conclusion

This was a starter code for integrating Runway MCP with OpenAI Agents SDK to build a functional AI agent that can interact with Runway.

Key features:

  • Hosted MCP tool integration through Composio's Tool Router
  • SQLite session persistence for conversation history
  • Simple async chat loop for interactive testing
You can extend this by adding more toolkits, implementing custom business logic, or building a web interface around the agent.
TOOLS

Supported Tools

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

Cancel Task

Cancel a running Runway task or delete its task record.

Create Document

Create a Runway knowledge document from markdown or plain text for reuse by avatar workflows.

Create Ephemeral Upload

Create only a temporary Runway media upload slot and return its presigned multipart form details and runway:// URI.

Delete Document

Permanently delete a Runway knowledge document by its ID.

Generate Image

Start a Runway text-to-image or reference-guided image generation task and return its task ID and estimated credit cost.

Generate Sound Effect

Generate an audio effect from a text prompt and return the task ID and estimated credit cost.

Generate Speech

Synthesize speech with Runway using an exact model-specific voice and option contract, then return the task ID and estimated credit cost.

Generate Video from Image

Animate one or more input images with a selected Runway model and return the task ID and estimated credit cost.

Generate Video from Text

Start a Runway text-to-video task with a model-specific typed request and return its task ID and estimated credit cost.

Get Document

Get one Runway knowledge document, including its full content and the avatars that currently use it.

Get Organization

Return the connected Runway organization's credit balance, monthly credit spend cap, exact per-model quotas, and current daily generation usage.

Get Task

Get the current status, cost, output URLs, and failure details for a Runway generation task.

Get Usage

Return daily Runway credit usage by model for an optional UTC date range of up to 90 days.

Get Workflow

Get a published Runway workflow version and its graph so node IDs and output keys can be inspected before running the workflow.

Get Workflow Invocation

Get the current status, completed node output URLs, and node or invocation failure details for a Runway workflow invocation.

List Documents

List Runway knowledge documents one page at a time, with sorting and an opaque continuation cursor.

List Workflows

List the connected account's published Runway workflows and their available versions, ordered as returned by Runway.

Run Workflow

Invoke a published Runway workflow, optionally overriding graph node outputs, and return the created workflow invocation ID.

Transform Video

Transform or restyle an existing video with Runway and return the created task ID and estimated credit cost.

Update Document

Change the name, content, or both for an existing Runway knowledge document.

Upscale Image

Start a Runway image upscaling task and return its task ID and estimated credit cost.

Upscale Video

Start a Runway video upscaling task and return its task ID and estimated credit cost.

FAQ

Frequently asked questions

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

Yes, you can. OpenAI Agents SDK 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 Runway tools.

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

Start with Runway.It takes 30 seconds.

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

Start building