How to integrate ConfigCat MCP with OpenAI Agents SDK

This guide walks you through connecting ConfigCat to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working ConfigCat agent that can list production feature flags currently enabled, create staging flag for beta checkout, audit rollout rules for mobile app through natural language commands. This guide will help you understand how to give your OpenAI Agents SDK agent real control over a ConfigCat account through Composio's ConfigCat MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved.

ConfigCat logoConfigCat
Api Key

ConfigCat is a feature flag management service for rollouts, configs, environments, and team access. Use it to ship safely, test changes, and control releases without redeploying.

10 Tools

Introduction

This guide walks you through connecting ConfigCat to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working ConfigCat agent that can list production feature flags currently enabled, create staging flag for beta checkout, audit rollout rules for mobile app through natural language commands.

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

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

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

The ConfigCat MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your ConfigCat account. It provides structured and secure access to your products, configurations, environments, feature flags, settings, segments, and tags, so your agent can inspect configurations, create flags, update environment values, manage targeting rules, and edit flag metadata on your behalf.

  • Account and product discovery: Have your agent list accessible organizations and products, then review their configurations, environments, segments, and tags.
  • Feature flag and setting management: Let the agent list existing flags and typed settings, create new ones, or permanently delete those you no longer need.
  • Environment value inspection: Instruct your agent to review a flag's value and complete evaluation logic in a selected environment.
  • Targeting and rollout updates: Direct your agent to change selected flag values or replace complete evaluation rules for a specific environment.
  • Flag metadata maintenance: Have your agent update flag names, descriptions, and tag assignments while keeping other metadata unchanged.

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

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

Create Flag or Setting

Create a feature flag or typed setting in a Config.

Delete Flag or Setting

Permanently delete one ConfigCat feature flag or setting by ID.

Get Product Context

Return a ConfigCat Product's configs, environments, segments, and tags, including the identifiers and evaluation versions needed to manage flags and targeting.

Get Environment Setting Value V2

Get one Config V2 flag or setting's complete evaluation formula in an Environment, including its optimistic-concurrency version.

List Account Hierarchy

List accessible ConfigCat organizations and products so an agent can resolve the IDs needed by product-scoped tools.

List Environment Values V2

Return every Config V2 feature flag and setting evaluation formula for one Config and Environment, preserving ordered targeting rules and concurrency versions while omitting parent objects and updater data.

List Flags and Settings

List feature flags and settings in one Config, including IDs, keys, types, tags, and metadata needed by value operations.

Patch Environment Setting Value V2

Update selected typed fields of one Config V2 evaluation formula while preserving every field the caller omits.

Replace Environment Setting Value V2

Completely replace one Config V2 flag or setting evaluation formula in an Environment.

Update Flag Metadata

Partially update a flag or setting's name, hint, or complete tag assignment without resetting untouched metadata.

FAQ

Frequently asked questions

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

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

Start with ConfigCat.It takes 30 seconds.

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

Start building