How to integrate Chameleon MCP with Claude Agent SDK

This guide walks you through connecting Chameleon to the Claude Agent SDK using the Composio tool router. By the end, you'll have a working Chameleon agent that can search your customer records, count customers, review experiences, inspect analytics, and track deliveries through natural language commands. This guide will help you understand how to give your Claude Agent SDK agent real control over a Chameleon account through Composio's Chameleon MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved.

Get started for freeGet a demo
Chameleon logoChameleon
Api Key

Chameleon is a product adoption platform for building in-app experiences, managing customer data, and analyzing user engagement. It helps teams improve onboarding, feature discovery, and product adoption with targeted user experiences.

14 Tools

Introduction

This guide walks you through connecting Chameleon to the Claude Agent SDK using the Composio tool router. By the end, you'll have a working Chameleon agent that can search your customer records, count customers, review experiences, inspect analytics, and track deliveries through natural language commands.

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

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

Also integrate Chameleon with

OpenAI Agents SDKClaude CodeClaude CoworkCodexOpenClawHermesCLIGoogle ADKLangChainVercel AI SDKMastra AILlamaIndexCrewAI

TL;DR

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

What is Claude Agent SDK?

The Claude Agent SDK is Anthropic's official framework for building AI agents powered by Claude. It provides a streamlined interface for creating agents with MCP tool support and conversation management.

Key features include:

  • Native MCP Support: Built-in support for Model Context Protocol servers
  • Permission Modes: Control tool execution permissions
  • Streaming Responses: Real-time response streaming for interactive applications
  • Context Manager: Clean async context management for sessions

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

The Chameleon MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Chameleon account. It provides structured and secure access to your in-app experiences, customer records, delivery activity, and engagement data, so your agent can review experiences, analyze engagement, find or update customer records, track customer events, and inspect deliveries on your behalf.

  • Experience discovery and review: Have your agent list and review tours, microsurveys, launchers, embeds, and tooltips without changing or publishing them.
  • Engagement and response analysis: Let the agent examine tour interactions and microsurvey responses to understand how customers engage with your experiences.
  • Customer record management: Direct your agent to find, count, create, or update customer profiles and companies using external references and structured criteria.
  • Customer event tracking: Instruct your agent to record named events for customer profiles, such as completing onboarding or activating a feature.
  • Delivery and account oversight: Have your agent review scheduled experience deliveries, change history, configured domains or environments, and targeting metadata such as segments, tags, themes, events, and properties.

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 Claude/Anthropic API Key
  • Primary know-how of Claude Agents SDK
  • A Chameleon account
  • Some knowledge of Python
2

Getting API Keys for Claude/Anthropic and Composio

Claude/Anthropic API Key
  • Go to the Anthropic Console and create an API key. You'll need credits to use the models.
  • 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 @anthropic-ai/claude-agent-sdk @composio/core dotenv

Install the Composio SDK and the Claude Agents SDK.

What's happening:

  • @composio/core provides Composio integration for Anthropic
  • @anthropic-ai/claude-agent-sdk is the core agent framework
  • dotenv/config loads environment variables
4

Set up environment variables

bash
COMPOSIO_API_KEY=your_composio_api_key_here
USER_ID=your_user_id_here
ANTHROPIC_API_KEY=your_anthropic_api_key_here

Create a .env file in your project root.

What's happening:

  • COMPOSIO_API_KEY authenticates with Composio
  • USER_ID identifies the user for session management
  • ANTHROPIC_API_KEY authenticates with Anthropic/Claude
5

Import dependencies

import 'dotenv/config';
import readline from 'node:readline';
import { Composio } from '@composio/core';
import { query, type Options } from "@anthropic-ai/claude-agent-sdk";

dotenv.config();
What's happening:
  • We're importing all necessary libraries including the Claude Agent SDK and Composio
  • The dotenv.config() function loads environment variables from your .env file
  • This setup prepares the foundation for connecting Claude with Chameleon functionality
6

Create a Composio instance and Tool Router session

async function chat() {
  const { COMPOSIO_API_KEY, USER_ID } = process.env;
  if (!COMPOSIO_API_KEY || !USER_ID) {
    throw new Error('COMPOSIO_API_KEY and USER_ID required in .env');
  }

  const composio = new Composio({ apiKey: COMPOSIO_API_KEY });

  // Create Tool Router session for Chameleon
  const session = await composio.create(USER_ID, {
    toolkits: ['chameleon'],
  });
  const mcpUrl = session?.mcp.url;
What's happening:
  • The function checks for the required COMPOSIO_API_KEY environment variable
  • We're creating a Composio instance using our API key
  • The create method creates a Tool Router session for Chameleon
  • The returned url is the MCP server URL that your agent will use
7

Configure Claude Agent with MCP

const options: Options = {
  permissionMode: 'bypassPermissions',
  mcpServers: {
    composio: {
      type: 'http',
      url: mcpUrl,
      headers: { 'x-api-key': COMPOSIO_API_KEY }
    }
  },
  systemPrompt: 'You are a helpful assistant with access to Chameleon tools via Composio.',
  maxTurns: 10,
};
What's happening:
  • We're configuring the Claude Agent options with the MCP server URL
  • permissionMode: 'bypassPermissions' allows the agent to execute operations without asking for permission each time
  • The system prompt instructs the agent that it has access to Chameleon
  • maxTurns: 10 limits the conversation length to prevent excessive API usage
8

Create client and start chat loop

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

  console.log('\nChat started. Type "exit" to quit.\n');

  let isProcessing = false;

  async function ask(prompt: string) {
    isProcessing = true;
    rl.pause();

    process.stdout.write('Claude is thinking...');
    const stream = query({ prompt, options });

    let firstChunk = true;
    for await (const msg of stream) {
      const content = (msg as any).message?.content || (msg as any).content;
      if (Array.isArray(content)) {
        for (const block of content) {
          if (block.type === 'text' && block.text) {
            if (firstChunk) {
              process.stdout.write('\r\x1b[K');
              process.stdout.write('Claude: ');
              firstChunk = false;
            }
            process.stdout.write(block.text);
          }
        }
      }
    }
    process.stdout.write('\n\n');

    isProcessing = false;
    rl.resume();
    rl.prompt();
  }

  rl.on('line', async (line) => {
    if (isProcessing) return;

    const input = line.trim();
    if (input === 'exit') {
      rl.close();
      process.exit(0);
    }
    if (input) await ask(input);
    else rl.prompt();
  });

  await ask('What can you help me with?');
}
What's happening:
  • The readline interface is created to handle user input and output
  • The query function is used to send the user's input to the agent
  • The chat loop continues until the user types 'exit' or 'quit'
9

Run the application

try {
  await chat();
} catch (error) {
  console.error(error);
  process.exit(1);
}
What's happening:
  • The chat function is the entry point for the application
  • The try-catch block is used to handle any errors that occur

Complete Code

Here's the complete code to get you started with Chameleon and Claude Agent SDK:

import 'dotenv/config';
import readline from 'node:readline';
import { Composio } from '@composio/core';
import { query, type Options } from "@anthropic-ai/claude-agent-sdk";

async function chat() {
  const { COMPOSIO_API_KEY, USER_ID } = process.env;
  if (!COMPOSIO_API_KEY || !USER_ID) {
    throw new Error('COMPOSIO_API_KEY and USER_ID required in .env');
  }

  const composio = new Composio({ apiKey: COMPOSIO_API_KEY });
  const session = await composio.create(USER_ID, {
    toolkits: ['chameleon']
  });
  const mcp_url = session?.mcp.url;

  const options: Options = {
    permissionMode: 'bypassPermissions',
    mcpServers: {
      composio: {
        type: 'http',
        url: mcp_url,
        headers: { 'x-api-key': COMPOSIO_API_KEY }
      }
    },
    systemPrompt: 'You are a helpful assistant with access to Chameleon tools via Composio.',
    maxTurns: 10,
  };

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

  console.log('\nChat started. Type "exit" to quit.\n');

  let isProcessing = false;

  async function ask(prompt: string) {
    isProcessing = true;
    rl.pause();

    process.stdout.write('Claude is thinking...');
    const stream = query({ prompt, options });

    let firstChunk = true;
    for await (const msg of stream) {
      const content = (msg as any).message?.content || (msg as any).content;
      if (Array.isArray(content)) {
        for (const block of content) {
          if (block.type === 'text' && block.text) {
            if (firstChunk) {
              process.stdout.write('\r\x1b[K');
              process.stdout.write('Claude: ');
              firstChunk = false;
            }
            process.stdout.write(block.text);
          }
        }
      }
    }
    process.stdout.write('\n\n');

    isProcessing = false;
    rl.resume();
    rl.prompt();
  }

  rl.on('line', async (line) => {
    if (isProcessing) return;

    const input = line.trim();
    if (input === 'exit') {
      rl.close();
      process.exit(0);
    }
    if (input) await ask(input);
    else rl.prompt();
  });

  await ask('What can you help me with?');
}

try {
  await chat();
} catch (error) {
  console.error(error);
  process.exit(1);
}

Conclusion

You've successfully built a Claude Agent SDK agent that can interact with Chameleon through Composio's Tool Router.

Key features:

  • Native MCP support through Claude's agent framework
  • Streaming responses for real-time interaction
  • Permission bypass for smooth automated workflows
You can extend this by adding more toolkits, implementing custom business logic, or building a web interface around the agent.
TOOLS

Supported Tools

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

Count Customer Records

Count Chameleon profiles or companies matching structured filters without retrieving the matching records.

Get Account Identity

Return the Chameleon account ID and admin user ID associated with the connected Account Secret.

Get Delivery

Retrieve one Chameleon experience delivery by ID without triggering, changing, or cancelling it.

Get Experience

Retrieve one Chameleon tour, microsurvey, launcher, embed, or tooltip by ID without modifying or publishing it.

List Changes

List one page of Chameleon change history across the account or for one supported experience.

List Deliveries

List one page of scheduled Chameleon experience deliveries, optionally filtered by experience or profile, without triggering a new delivery.

List Domains or Environments

List one page of configured Chameleon domains or environments without changing account routing configuration.

List Experience Analytics

List one page of tour interactions or microsurvey responses for a specific Chameleon experience.

List Experiences

List one page of Chameleon tours, microsurveys, launchers, embeds, or tooltips without modifying or publishing them.

List Targeting Metadata

List one page of Chameleon segments, tags, themes, tracked event names, or profile/company property definitions used to interpret targeting and analytics data.

Lookup Customer Record

Retrieve one Chameleon profile or company by its Chameleon ID or external identifier.

Search Customer Records

Search Chameleon profiles or companies with structured filters and return one offset-paginated page of matching records.

Track Event

Irreversibly record one named event for a Chameleon profile identified by ID or external UID; provide exactly one identifier.

Upsert Customer Record

Create or update one Chameleon profile or company by external UID and return its Chameleon ID.

FRAMEWORKS

How to build Chameleon MCP Agent with another framework

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Chameleon MCP with OpenAI Agents SDK

Claude Code logo

Claude Code

Use Chameleon MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Chameleon MCP with Claude Cowork

Codex logo

Codex

Use Chameleon MCP with Codex

OpenClaw logo

OpenClaw

Use Chameleon MCP with OpenClaw

Hermes logo

Hermes

Use Chameleon MCP with Hermes

CLI logo

CLI

Use Chameleon MCP with CLI

Google ADK logo

Google ADK

Use Chameleon MCP with Google ADK

LangChain logo

LangChain

Use Chameleon MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Chameleon MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Chameleon MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Chameleon MCP with LlamaIndex

CrewAI logo

CrewAI

Use Chameleon MCP with CrewAI

FAQ

Frequently asked questions

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

Yes, you can. Claude Agent 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 Chameleon tools.

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

Start with Chameleon.It takes 30 seconds.

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

Start building
Customer stories

Teams ship real agents on Composio

GET STARTED FOR FREEBOOK A DEMO
agent.aiZoomLettaGleanHubSpotAWSWabi

Karan skipped his own birthday party to fix our critical issue. It was 10pm and he diverted his Waymo to help us instead. This really sets the bar — it shows the commitment you need when users rely on your software.

Harsha Gaddipati
Harsha Gaddipati
Co-founder, Slashy

A lot of students tell us that the moment their connected tools start talking to each other inside Opennote feels almost magical. The agent just knows them, and it's immensely helped keep new users on the platform.

Abhi Arya
Abhi Arya
Co-founder, Opennote

We chose Composio over Pipedream because it delivered depth where it mattered — niche tools and tricky edge cases other platforms simply ignored. That gave us confidence to scale without compromising.

Nirman Dave
Nirman Dave
CEO, Zams

As a solo builder, shipping fast is life or death. The only way I can outcompete incumbents is by outmanoeuvring them. Getting bogged down managing agent auth would have been a death sentence.

Ryan Yu
Ryan Yu
Founder, Extra Thursday

Before Composio, adding tool integrations was slow and resource-intensive. Each one could take weeks of engineering time, and maintaining them meant constantly keeping up with API changes.

Tomisin Jenrola
Tomisin Jenrola
Founder & CEO, SwarmZero

With hands-on help from their founder, we integrated Gmail and Google Drive in just 30 minutes. This level of personal support and commitment is exactly what startups should strive for.

Jerome Leclanche
Jerome Leclanche
Co-Founder, Ingram Technologies