How to integrate Klipfolio MCP with OpenAI Agents SDK

This guide walks you through connecting Klipfolio to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working Klipfolio agent that can create a new dashboard for marketing kpis, list all available data sources in your account, append this week's sales csv to data source through natural language commands. This guide will help you understand how to give your OpenAI Agents SDK agent real control over a Klipfolio account through Composio's Klipfolio MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved.

Klipfolio logoKlipfolio
Api Key

Klipfolio is a cloud-based business intelligence platform for creating real-time dashboards and reports. It helps teams monitor metrics, visualize trends, and share analytics effortlessly.

50 Tools

Introduction

This guide walks you through connecting Klipfolio to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working Klipfolio agent that can create a new dashboard for marketing kpis, list all available data sources in your account, append this week's sales csv to data source through natural language commands.

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

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

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

The Klipfolio MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Klipfolio account. It provides structured and secure access to your dashboards and data sources, so your agent can perform actions like creating dashboards, updating data sources, retrieving analytics, and managing visualizations on your behalf.

  • Effortless dashboard creation and management: Ask your agent to create new dashboards (tabs), organize visualizations, or fetch detailed information about existing dashboards for instant business insights.
  • Comprehensive data source handling: Let your agent list, create, refresh, or delete data sources, ensuring your reports are always up to date and data flows smoothly.
  • Automated data updating: Instruct your agent to append fresh data to data sources or trigger refreshes across multiple sources simultaneously, keeping analytics current without manual effort.
  • Visualization and klip management: Retrieve a list of all your klips (visual components), enabling your agent to analyze, summarize, or reference the data visualizations you rely on most.
  • User profile and account verification: Have the agent check authentication or pull user profile details, helping you audit access and monitor account activity with ease.

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

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

Assign User Role

Tool to assign a role to a user in Klipfolio.

Create Data Source

This tool creates a new data source in Klipfolio.

Create Data Source Instance

Tool to create a new data source instance based on an existing data source in Klipfolio.

Create Group

Tool to create a new group in Klipfolio.

Create Role

Tool to create a new role in Klipfolio with optional permissions.

Create Tab (Dashboard)

This tool creates a new tab (dashboard) in Klipfolio.

Create User

Tool to create a new user in Klipfolio with optional roles and client association.

Delete Data Source

This tool permanently removes a specified data source from the Klipfolio account.

Delete Data Source Instance Property

Tool to delete a property from a data source instance in Klipfolio.

Delete Data Source Property

Tool to delete a property from a data source in Klipfolio.

Delete Data Source Share Right

Tool to delete a data source share right for a specific user or group.

Delete Group

Tool to permanently delete a specified group from the Klipfolio account.

Delete Role

Tool to delete a role from Klipfolio.

Disable Data Source

Tool to disable a data source in Klipfolio.

Enable Data Source

Tool to enable a disabled data source in Klipfolio.

Get Dashboard Details

This tool retrieves detailed information about a specific dashboard (formerly known as tab) in Klipfolio.

Get Data Source Details

Tool to retrieve detailed information about a specific data source in Klipfolio.

Get Data Source Instance Details

Tool to retrieve detailed information about a specific data source instance in Klipfolio.

Get Data Source Instance Data

Tool to retrieve the actual data from a specific data source instance in Klipfolio.

Get Data Source Instance Properties

Tool to retrieve configuration properties for a specific data source instance in Klipfolio.

Get Data Source Properties

Tool to retrieve properties for a specific data source in Klipfolio by its ID.

Get Data Source Share Rights

Tool to retrieve sharing permissions for a specific data source in Klipfolio.

Get Group Details

Tool to retrieve detailed information about a specific group in Klipfolio.

Get Group Default Tabs

Tool to retrieve the list of default tabs (dashboards) for a specific group.

Get Group Users

Tool to retrieve all users belonging to a specific group in Klipfolio.

Get Klips

This tool retrieves a list of all Klips accessible to the authenticated user.

Get User Profile

This tool is used to retrieve the authenticated user's profile information and test the authentication status.

Get Role Details

Tool to retrieve detailed information about a specific role in Klipfolio.

Get Role Permissions

Tool to retrieve the list of permissions assigned to a specific role in Klipfolio.

Get Role Users

Tool to retrieve all users associated with a specific role in Klipfolio.

Get User Details

Tool to retrieve detailed information about a specific user in Klipfolio.

Get User Groups

Tool to retrieve all groups that a specific user belongs to in Klipfolio.

Get User Properties

Tool to retrieve custom properties associated with a specific user in Klipfolio.

Get User Roles

Tool to retrieve all roles assigned to a specific user in Klipfolio.

Get User Tab Instances

Tool to retrieve all tab instances associated with a specific user.

List Data Source Instances

Tool to retrieve all data source instances accessible to the authenticated user.

List All Data Sources

This tool retrieves a list of all data sources associated with an authenticated Klipfolio account.

List All Groups

Tool to retrieve all groups from a Klipfolio account.

List All Roles

Tool to retrieve all roles in the company.

List All Users

Tool to retrieve all users in the company.

Refresh Data Source Instance

Tool to manually refresh a data source instance in Klipfolio.

Refresh Multiple Data Sources

This tool allows users to refresh multiple data sources in Klipfolio simultaneously.

Resend User Invite

Tool to resend a user invitation email in Klipfolio.

Reset User Password

Tool to reset a user's password in Klipfolio.

Update Data Source

This tool allows you to replace/update the data in an existing Klipfolio data source.

Update Data Source Instance Properties

Tool to update custom properties on a Klipfolio data source instance.

Update Data Source Metadata

Tool to update metadata (name, description, refresh_interval) of an existing data source.

Update Data Source Properties

Tool to update custom properties for a data source in Klipfolio.

Update Data Source Share Rights

Tool to update data source share rights in Klipfolio.

Update User Properties

Tool to update custom properties for a user in Klipfolio.

FAQ

Frequently asked questions

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

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

Start with Klipfolio.It takes 30 seconds.

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

Start building