SIGN UPLOG IN
X (Twitter)LinkedInGitHubDiscordYouTube

How to integrate Alttext ai MCP with Autogen

Connect Autogen to Alttext ai MCP. Generate alt text for new uploaded image, list images missing alt descriptions, and more using natural language, with authentication handled for you.

Get started for freeGet a demo
Alttext ai logoAlttext ai
Api Key

AltText.ai is a service that generates alt text for images automatically. It helps boost accessibility and SEO for your visual content.

10 Tools

Introduction

This guide walks you through connecting Alttext ai to AutoGen using the Composio tool router. By the end, you'll have a working Alttext ai agent that can generate alt text for images, process images in bulk, scrape pages for images, and search your image library through natural language commands.

This guide will help you understand how to give your AutoGen agent real control over a Alttext ai account through Composio's Alttext ai MCP server.

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

Also integrate Alttext ai with

Claude CodeClaude CoworkOpenAI Agents SDKClaude Agent SDKCodexOpenClawHermesAtomic AgentGoogle ADKLangChainVercel AI SDKMastra AILlamaIndexCrewAIPydantic AI

TL;DR

Here's what you'll learn:
  • Get and set up your OpenAI and Composio API keys
  • Install the required dependencies for Autogen and Composio
  • Initialize Composio and create a Tool Router session for Alttext ai
  • Wire that MCP URL into Autogen using McpWorkbench and StreamableHttpServerParams
  • Configure an Autogen AssistantAgent that can call Alttext ai tools
  • Run a live chat loop where you ask the agent to perform Alttext ai operations

What is AutoGen?

Autogen is a framework for building multi-agent conversational AI systems from Microsoft. It enables you to create agents that can collaborate, use tools, and maintain complex workflows.

Key features include:

  • Multi-Agent Systems: Build collaborative agent workflows
  • MCP Workbench: Native support for Model Context Protocol tools
  • Streaming HTTP: Connect to external services through streamable HTTP
  • AssistantAgent: Pre-built agent class for tool-using assistants

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

The AltText.ai MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your AltText.ai account. It provides structured and secure access to your image library and account settings, so your agent can generate alt text, process images in bulk, scan pages for images, search your library, and manage image details on your behalf.

  • Alt text generation: Have your agent submit an image to generate descriptive alt text for accessibility and SEO.
  • Bulk image processing: Direct your agent to upload a CSV of image URLs and queue them for alt text generation.
  • Web page image scanning: Let the agent scan a web page or HTML document and queue its images for alt text generation.
  • Image library management: Instruct your agent to list or search images, retrieve their alt text and metadata, update image details, or remove images you no longer need.
  • Account settings and usage: Have your agent check account usage and settings, then update details such as your account name or webhook URL.

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 step08 STEPS
1

Prerequisites

You will need:

  • A Composio API key
  • An OpenAI API key (used by Autogen's OpenAIChatCompletionClient)
  • A Alttext ai account you can connect to Composio
  • Some basic familiarity with Autogen and Python async
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

bash
pip install composio python-dotenv
pip install autogen-agentchat autogen-ext-openai autogen-ext-tools

Install Composio, Autogen extensions, and dotenv.

What's happening:

  • composio connects your agent to Alttext ai via MCP
  • autogen-agentchat provides the AssistantAgent class
  • autogen-ext-openai provides the OpenAI model client
  • autogen-ext-tools provides MCP workbench support

4

Set up environment variables

bash
COMPOSIO_API_KEY=your-composio-api-key
OPENAI_API_KEY=your-openai-api-key
USER_ID=your-user-identifier@example.com

Create a .env file in your project folder.

What's happening:

  • COMPOSIO_API_KEY is required to talk to Composio
  • OPENAI_API_KEY is used by Autogen's OpenAI client
  • USER_ID is how Composio identifies which user's Alttext ai connections to use
5

Import dependencies and create Tool Router session

python
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio

from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient
from autogen_ext.tools.mcp import McpWorkbench, StreamableHttpServerParams

load_dotenv()

async def main():
    # Initialize Composio and create a Alttext ai session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["alttext_ai"]
    )
    url = session.mcp.url
What's happening:
  • load_dotenv() reads your .env file
  • Composio(api_key=...) initializes the SDK
  • create(...) creates a Tool Router session that exposes Alttext ai tools
  • session.mcp.url is the MCP endpoint that Autogen will connect to
6

Configure MCP parameters for Autogen

python
# Configure MCP server parameters for Streamable HTTP
server_params = StreamableHttpServerParams(
    url=url,
    timeout=30.0,
    sse_read_timeout=300.0,
    terminate_on_close=True,
    headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")}
)

Autogen expects parameters describing how to talk to the MCP server. That is what StreamableHttpServerParams is for.

What's happening:

  • url points to the Tool Router MCP endpoint from Composio
  • timeout is the HTTP timeout for requests
  • sse_read_timeout controls how long to wait when streaming responses
  • terminate_on_close=True cleans up the MCP server process when the workbench is closed
7

Create the model client and agent

python
# Create model client
model_client = OpenAIChatCompletionClient(
    model="gpt-5",
    api_key=os.getenv("OPENAI_API_KEY")
)

# Use McpWorkbench as context manager
async with McpWorkbench(server_params) as workbench:
    # Create Alttext ai assistant agent with MCP tools
    agent = AssistantAgent(
        name="alttext_ai_assistant",
        description="An AI assistant that helps with Alttext ai operations.",
        model_client=model_client,
        workbench=workbench,
        model_client_stream=True,
        max_tool_iterations=10
    )

What's happening:

  • OpenAIChatCompletionClient wraps the OpenAI model for Autogen
  • McpWorkbench connects the agent to the MCP tools
  • AssistantAgent is configured with the Alttext ai tools from the workbench
8

Run the interactive chat loop

python
print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
print("Ask any Alttext ai related question or task to the agent.\n")

# Conversation loop
while True:
    user_input = input("You: ").strip()

    if user_input.lower() in ["exit", "quit", "bye"]:
        print("\nGoodbye!")
        break

    if not user_input:
        continue

    print("\nAgent is thinking...\n")

    # Run the agent with streaming
    try:
        response_text = ""
        async for message in agent.run_stream(task=user_input):
            if hasattr(message, "content") and message.content:
                response_text = message.content

        # Print the final response
        if response_text:
            print(f"Agent: {response_text}\n")
        else:
            print("Agent: I encountered an issue processing your request.\n")

    except Exception as e:
        print(f"Agent: Sorry, I encountered an error: {str(e)}\n")
What's happening:
  • The script prompts you in a loop with You:
  • Autogen passes your input to the model, which decides which Alttext ai tools to call via MCP
  • agent.run_stream(...) yields streaming messages as the agent thinks and calls tools
  • Typing exit, quit, or bye ends the loop

Complete Code

Here's the complete code to get you started with Alttext ai and AutoGen:

python
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio

from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient
from autogen_ext.tools.mcp import McpWorkbench, StreamableHttpServerParams

load_dotenv()

async def main():
    # Initialize Composio and create a Alttext ai session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["alttext_ai"]
    )
    url = session.mcp.url

    # Configure MCP server parameters for Streamable HTTP
    server_params = StreamableHttpServerParams(
        url=url,
        timeout=30.0,
        sse_read_timeout=300.0,
        terminate_on_close=True,
        headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")}
    )

    # Create model client
    model_client = OpenAIChatCompletionClient(
        model="gpt-5",
        api_key=os.getenv("OPENAI_API_KEY")
    )

    # Use McpWorkbench as context manager
    async with McpWorkbench(server_params) as workbench:
        # Create Alttext ai assistant agent with MCP tools
        agent = AssistantAgent(
            name="alttext_ai_assistant",
            description="An AI assistant that helps with Alttext ai operations.",
            model_client=model_client,
            workbench=workbench,
            model_client_stream=True,
            max_tool_iterations=10
        )

        print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
        print("Ask any Alttext ai related question or task to the agent.\n")

        # Conversation loop
        while True:
            user_input = input("You: ").strip()

            if user_input.lower() in ['exit', 'quit', 'bye']:
                print("\nGoodbye!")
                break

            if not user_input:
                continue

            print("\nAgent is thinking...\n")

            # Run the agent with streaming
            try:
                response_text = ""
                async for message in agent.run_stream(task=user_input):
                    if hasattr(message, 'content') and message.content:
                        response_text = message.content

                # Print the final response
                if response_text:
                    print(f"Agent: {response_text}\n")
                else:
                    print("Agent: I encountered an issue processing your request.\n")

            except Exception as e:
                print(f"Agent: Sorry, I encountered an error: {str(e)}\n")

if __name__ == "__main__":
    asyncio.run(main())

Conclusion

You now have an Autogen assistant wired into Alttext ai through Composio's Tool Router and MCP. From here you can:
  • Add more toolkits to the toolkits list, for example notion or hubspot
  • Refine the agent description to point it at specific workflows
  • Wrap this script behind a UI, Slack bot, or internal tool
Once the pattern is clear for Alttext ai, you can reuse the same structure for other MCP-enabled apps with minimal code changes.
TOOLS

Supported Tools

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

Bulk Create Images

Tool to bulk upload and process a CSV file of image URLs for alt text generation.

Create Image

Tool to add an image and generate alt text.

Delete Image by Asset ID

Tool to delete an image from your library by its asset ID.

Get Account

Tool to retrieve account settings and usage information.

Get Image by Asset ID

Tool to retrieve detailed information about a specific image using its asset ID.

Get Images

Tool to retrieve a paginated list of images in your library, including their alt text and metadata.

Scrape Page for Images

Scrape a web page or HTML document and queue eligible images for asynchronous alt text generation; some images may be skipped.

Search Images

Search for images in your AltText.

Update Account

Tool to update account settings (e.

Update Image by Asset ID

Update an existing image identified by its asset ID, including its asset ID, alt text, and metadata.

FRAMEWORKS

How to build Alttext ai MCP Agent with another framework

Claude Code logo

Claude Code

Use Alttext ai MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Alttext ai MCP with Claude Cowork

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Alttext ai MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Alttext ai MCP with Claude Agent SDK

Codex logo

Codex

Use Alttext ai MCP with Codex

OpenClaw logo

OpenClaw

Use Alttext ai MCP with OpenClaw

Hermes logo

Hermes

Use Alttext ai MCP with Hermes

Atomic Agent logo

Atomic Agent

Use Alttext ai MCP with Atomic Agent

Google ADK logo

Google ADK

Use Alttext ai MCP with Google ADK

LangChain logo

LangChain

Use Alttext ai MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Alttext ai MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Alttext ai MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Alttext ai MCP with LlamaIndex

CrewAI logo

CrewAI

Use Alttext ai MCP with CrewAI

Pydantic AI logo

Pydantic AI

Use Alttext ai MCP with Pydantic AI

FAQ

Frequently asked questions

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

Yes, you can. Autogen 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 Alttext ai tools.

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

Start with Alttext ai.It takes 30 seconds.

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

Start building