SIGN UPLOG IN
X (Twitter)LinkedInGitHubDiscordYouTube

How to integrate Mural MCP with LangChain

Connect LangChain to Mural MCP. Add sticky notes summarizing team feedback, list all image files on project mural, and more using natural language, with authentication handled for you.

Get started for freeGet a demo
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.

40 Tools

Introduction

This guide walks you through connecting Mural to LangChain using the Composio tool router. By the end, you'll have a working Mural agent that can create murals from templates, add sticky notes and shapes, search rooms and murals, and export murals through natural language commands.

This guide will help you understand how to give your LangChain 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

Claude CodeClaude CoworkOpenAI Agents SDKClaude Agent SDKCodexOpenClawHermesAtomic AgentGoogle ADKVercel AI SDKMastra AILlamaIndexCrewAIPydantic AIAutoGen

TL;DR

Here's what you'll learn:
  • Get and set up your OpenAI and Composio API keys
  • Connect your Mural project to Composio
  • Create a Tool Router MCP session for Mural
  • Initialize an MCP client and retrieve Mural tools
  • Build a LangChain agent that can interact with Mural
  • Set up an interactive chat interface for testing

What is LangChain?

LangChain is a framework for developing applications powered by language models. It provides tools and abstractions for building agents that can reason, use tools, and maintain conversation context.

Key features include:

  • Agent Framework: Build agents that can use tools and make decisions
  • MCP Integration: Connect to external services through Model Context Protocol adapters
  • Memory Management: Maintain conversation history across interactions
  • Multi-Provider Support: Works with OpenAI, Anthropic, and other LLM providers

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 step10 STEPS
1

Prerequisites

Before starting this tutorial, make sure you have:
  • Python 3.10 or higher installed on your system
  • A Composio account with an API key
  • An OpenAI API key
  • Basic familiarity with Python and async programming
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
  • Log in to the Composio dashboard.
  • Navigate to your API settings and generate a new API key.
  • Store this key securely as you'll need it for authentication.
3

Install dependencies

npm install @composio/langchain @langchain/core @langchain/openai @langchain/mcp-adapters dotenv

Install the required packages for LangChain with MCP support.

What's happening:

  • @composio/langchain provides Composio integration for LangChain
  • @langchain/mcp-adapters enables MCP client connections
  • @langchain/core is the core agent framework
  • dotenv/config loads environment variables
4

Set up environment variables

bash
COMPOSIO_API_KEY=your_composio_api_key_here
COMPOSIO_USER_ID=your_composio_user_id_here
OPENAI_API_KEY=your_openai_api_key_here

Create a .env file in your project root.

What's happening:

  • COMPOSIO_API_KEY authenticates your requests to Composio's API
  • COMPOSIO_USER_ID identifies the user for session management
  • OPENAI_API_KEY enables access to OpenAI's language models
5

Import dependencies

import { Composio } from '@composio/core';
import { LangchainProvider } from '@composio/langchain';
import { MultiServerMCPClient } from "@langchain/mcp-adapters";
import { createAgent } from "langchain";
import * as readline from 'readline';
import 'dotenv/config';

dotenv.config();
What's happening:
  • We're importing LangChain's MCP adapter and Composio SDK
  • The dotenv/config import loads environment variables from your .env file
  • This setup prepares the foundation for connecting LangChain with Mural functionality through MCP
6

Initialize Composio client

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

if (!composioApiKey) throw new Error('COMPOSIO_API_KEY is not set');
if (!userId) throw new Error('COMPOSIO_USER_ID is not set');

async function main() {
    const composio = new Composio({
        apiKey: composioApiKey as string,
        provider: new LangchainProvider()
    });
What's happening:
  • We're loading the COMPOSIO_API_KEY from environment variables and validating it exists
  • Creating a Composio instance that will manage our connection to Mural tools
  • Validating that COMPOSIO_USER_ID is also set before proceeding
7

Create a Tool Router session

const session = await composio.create(
    userId as string,
    {
        toolkits: ['mural']
    }
);

const url = session.mcp.url;
What's happening:
  • We're creating a Tool Router session that gives your agent access to Mural tools
  • The create method takes the user ID and specifies which toolkits should be available
  • The returned session.mcp.url is the MCP server URL that your agent will use
  • This approach allows the agent to dynamically load and use Mural tools as needed
8

Configure the agent with the MCP URL

const client = new MultiServerMCPClient({
    "mural-agent": {
        transport: "http",
        url: url,
        headers: {
            "x-api-key": process.env.COMPOSIO_API_KEY
        }
    }
});

const tools = await client.getTools();

const agent = createAgent({ model: "gpt-5", tools });
What's happening:
  • We're creating a MultiServerMCPClient that connects to our Mural MCP server via HTTP
  • The client is configured with a name and the URL from our Tool Router session
  • getTools() retrieves all available Mural tools that the agent can use
  • We're creating a LangChain agent using the GPT-5 model
9

Set up interactive chat interface

let conversationHistory: any[] = [];

console.log("Chat started! Type 'exit' or 'quit' to end the conversation.\n");
console.log("Ask any Mural related question or task to the agent.\n");

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

rl.prompt();

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

    if (['exit', 'quit', 'bye'].includes(trimmedInput.toLowerCase())) {
        console.log("\nGoodbye!");
        rl.close();
        process.exit(0);
    }

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

    conversationHistory.push({ role: "user", content: trimmedInput });
    console.log("\nAgent is thinking...\n");

    const response = await agent.invoke({ messages: conversationHistory });
    conversationHistory = response.messages;

    const finalResponse = response.messages[response.messages.length - 1]?.content;
    console.log(`Agent: ${finalResponse}\n`);
        
        rl.prompt();
    });

    rl.on('close', () => {
        console.log('\n👋 Session ended.');
        process.exit(0);
    });
What's happening:
  • We initialize an empty conversationHistory list to maintain context across interactions
  • A readline interface is used to continuously accept user input from the command line
  • When a user types a message, it's added to the conversation history and sent to the agent
  • The agent processes the request using the invoke() method with the full conversation history
  • Users can type 'exit', 'quit', or 'bye' to end the chat session gracefully
10

Run the application

main().catch((err) => {
    console.error('Fatal error:', err);
    process.exit(1);
});
What's happening:
  • We call the main() function to start the application

Complete Code

Here's the complete code to get you started with Mural and LangChain:

import { Composio } from '@composio/core';
import { LangchainProvider } from '@composio/langchain';
import { MultiServerMCPClient } from "@langchain/mcp-adapters";  
import { createAgent } from "langchain";
import * as readline from 'readline';
import 'dotenv/config';

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

if (!composioApiKey) throw new Error('COMPOSIO_API_KEY is not set');
if (!userId) throw new Error('COMPOSIO_USER_ID is not set');

async function main() {
    const composio = new Composio({
        apiKey: composioApiKey as string,
        provider: new LangchainProvider()
    });

    const session = await composio.create(
        userId as string,
        {
            toolkits: ['mural']
        }
    );

    const url = session.mcp.url;
    
    const client = new MultiServerMCPClient({
        "mural-agent": {
            transport: "http",
            url: url,
            headers: {
                "x-api-key": process.env.COMPOSIO_API_KEY
            }
        }
    });
    
    const tools = await client.getTools();
  
    const agent = createAgent({ model: "gpt-5", tools });
    
    let conversationHistory: any[] = [];
    
    console.log("Chat started! Type 'exit' or 'quit' to end the conversation.\n");
    console.log("Ask any Mural related question or task to the agent.\n");
    
    const rl = readline.createInterface({
        input: process.stdin,
        output: process.stdout,
        prompt: 'You: '
    });

    rl.prompt();

    rl.on('line', async (userInput: string) => {
        const trimmedInput = userInput.trim();
        
        if (['exit', 'quit', 'bye'].includes(trimmedInput.toLowerCase())) {
            console.log("\nGoodbye!");
            rl.close();
            process.exit(0);
        }
        
        if (!trimmedInput) {
            rl.prompt();
            return;
        }
        
        conversationHistory.push({ role: "user", content: trimmedInput });
        console.log("\nAgent is thinking...\n");
        
        const response = await agent.invoke({ messages: conversationHistory });
        conversationHistory = response.messages;
        
        const finalResponse = response.messages[response.messages.length - 1]?.content;
        console.log(`Agent: ${finalResponse}\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

You've successfully built a LangChain agent that can interact with Mural through Composio's Tool Router.

Key features of this implementation:

  • Dynamic tool loading through Composio's Tool Router
  • Conversation history maintenance for context-aware responses
  • Async Python provides clean, efficient execution of agent workflows
You can extend this further by adding error handling, implementing specific business logic, or integrating additional Composio toolkits to create multi-app workflows.
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 area

Create an area widget that can organize content on a mural.

Create arrow

Create one arrow widget on a mural.

Create asset upload

Create a signed upload target for an image or file attached to a mural.

Create Image

Create an image widget from an uploaded Mural asset name.

Create mural

Create a new blank mural in a room owned by the connected user.

Create mural from template

Create a new mural in a room using an existing template.

Create shapes

Create between one and 1000 shape widgets on a mural in one request.

Create sticky note

Create one or more sticky note widgets on a mural.

Create text boxes

Create up to 1000 text box widgets on a mural.

Create title widgets

Create up to 1000 title widgets on a mural.

Delete widget

Permanently delete a widget and its content from a mural.

Export Mural

Queue a mural export to a PDF file and return its export process ID.

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

Retrieve metadata for a mural by its unique identifier.

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 widget

Get one widget by its mural and widget identifiers.

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.

Update area

Update documented properties of an existing area widget on a mural.

Update arrow

Update documented properties of an existing arrow widget on a mural.

Update shape

Update documented properties of an existing shape widget on a mural.

Update sticky note

Update documented properties of an existing sticky-note widget on a mural.

Update Textbox

Partially update a textbox widget's content, style, size, or position.

FRAMEWORKS

How to build Mural MCP Agent with another framework

Claude Code logo

Claude Code

Use Mural MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Mural MCP with Claude Cowork

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Mural MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Mural MCP with Claude Agent SDK

Codex logo

Codex

Use Mural MCP with Codex

OpenClaw logo

OpenClaw

Use Mural MCP with OpenClaw

Hermes logo

Hermes

Use Mural MCP with Hermes

Atomic Agent logo

Atomic Agent

Use Mural MCP with Atomic Agent

Google ADK logo

Google ADK

Use Mural MCP with Google ADK

Vercel AI SDK logo

Vercel AI SDK

Use Mural MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Mural MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Mural MCP with LlamaIndex

CrewAI logo

CrewAI

Use Mural MCP with CrewAI

Pydantic AI logo

Pydantic AI

Use Mural MCP with Pydantic AI

AutoGen logo

AutoGen

Use Mural MCP with AutoGen

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. LangChain 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