How to integrate Mural MCP with OpenAI Agents SDK

This guide walks you through connecting Mural to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working Mural agent that can add sticky notes summarizing team feedback, list all image files on project mural, show all widgets in today's brainstorming board through natural language commands. This guide will help you understand how to give your OpenAI Agents SDK agent real control over a Mural account through Composio's Mural MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved.

Mural logoMural
Oauth2

Mural is a digital whiteboard platform for distributed visual collaboration. It helps teams brainstorm, map ideas, and diagram together in real time.

22 Tools

Introduction

This guide walks you through connecting Mural to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working Mural agent that can add sticky notes summarizing team feedback, list all image files on project mural, show all widgets in today's brainstorming board through natural language commands.

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

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

Also integrate Mural 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 Mural
  • Configure an AI agent that can use Mural as a tool
  • Run a live chat session where you can ask the agent to perform Mural 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 Mural MCP server, and what's possible with it?

The Mural MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Mural account. It provides structured and secure access to your digital whiteboards, so your agent can perform actions like creating sticky notes, retrieving board widgets, managing files, and accessing user info on your behalf.

  • Automated sticky note creation: Instantly add one or more sticky notes to any mural for fast brainstorming, idea capture, or task tracking via your agent.
  • Widget and content retrieval: Have your agent fetch all widgets within a specific mural, making it easy to analyze, summarize, or organize the board's contents programmatically.
  • File management on murals: Let your agent list all file attachments within a mural, so you can monitor, catalog, or process embedded documents and images effortlessly.
  • User information access: Retrieve details about the current authenticated user, enabling personalized actions and tailored workflows across your Mural workspace.
  • Seamless OAuth authorization: Easily initiate secure, managed authentication flows so your agent can access and act on your behalf without manual credential handling.

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 Mural 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 Mural.
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 Mural
const session = await composio.create(userId as string, {
  toolkits: ['mural'],
});
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 mural.
  • The router checks the user's Mural connection and prepares the MCP endpoint.
  • The returned session.mcp.url is the MCP URL that your agent will use to access Mural.
  • This approach keeps things lightweight and lets the agent request Mural 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 Mural. Help users perform Mural 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 Mural 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 Mural 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 Mural.
  • 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 Mural 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: ['mural'],
  });
  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 Mural. Help users perform Mural 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 Mural MCP with OpenAI Agents SDK to build a functional AI agent that can interact with Mural.

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 Mural action and event your agent gets out of the box.

MURAL Authorization Request

Tool to initiate the OAuth 2.

Create sticky note

Create one or more sticky note widgets on a mural.

Get current user

Tool to retrieve information about the currently authenticated user.

Get files for a mural

Tool to retrieve a list of file widgets in a mural.

Get Mural Widgets

Tool to retrieve all widgets within a specified mural.

Get room by ID

Tool to retrieve information about a specific room by its ID.

Get workspace by ID

Tool to retrieve information about a specific workspace by its ID.

Get workspaces

Tool to retrieve all workspaces the authenticated user is a member of.

List folders in room

Tool to list all folders within a room that the authenticated user has access to.

List open rooms in workspace

Tool to list all discoverable open rooms within a workspace.

List recent murals in workspace

Tool to list recently opened active murals for the authenticated user in a workspace.

List recent templates

Tool to retrieve recent templates used by a user for a workspace.

List murals in room

Tool to list all murals for a room that the authenticated user has read access to.

List rooms in workspace

Tool to list all rooms within a workspace.

List users in room

Tool to list all members and guests for a room.

List tags in a mural

Tool to retrieve all tags in a mural.

List default templates

Tool to retrieve all default templates available in Mural.

List workspace murals

Tool to list all murals in a workspace that the authenticated user owns or is a member of.

List workspace templates

Tool to get default and custom templates for a workspace.

Search murals in workspace

Tool to search for murals within a workspace.

Search rooms in workspace

Tool to search for rooms within a workspace by name or description.

Search templates in workspace

Tool to search templates within a workspace that the authenticated user owns or has access to.

FAQ

Frequently asked questions

With a standalone Mural MCP server, the agents and LLMs can only access a fixed set of Mural tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Mural 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 Mural tools.

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

Start with Mural.It takes 30 seconds.

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

Start building