SIGN UPLOG IN
X (Twitter)LinkedInGitHubDiscordYouTube

How to integrate Textcortex MCP with Autogen

Connect Autogen to Textcortex MCP. Summarize this research article for me, generate a follow-up email to a client, and more using natural language, with authentication handled for you.

Get started for freeGet a demo
Textcortex logoTextcortex
Api Key

Textcortex is an AI-powered text generation platform that provides powerful language model APIs for developers. It enables rapid, high-quality content creation and paraphrasing at scale.

7 Tools

Introduction

This guide walks you through connecting Textcortex to AutoGen using the Composio tool router. By the end, you'll have a working Textcortex agent that can draft emails and social posts, write product titles and video descriptions, summarize and translate text, and generate code through natural language commands.

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

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

Also integrate Textcortex 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 Textcortex
  • Wire that MCP URL into Autogen using McpWorkbench and StreamableHttpServerParams
  • Configure an Autogen AssistantAgent that can call Textcortex tools
  • Run a live chat loop where you ask the agent to perform Textcortex 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 Textcortex MCP server, and what's possible with it?

The Textcortex MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Textcortex account. It provides structured and secure access to advanced text generation and summarization capabilities, so your agent can perform actions like drafting emails, paraphrasing content, summarizing long texts, and personalizing communication on your behalf.

  • Automated email generation: Instantly draft personalized email subjects and bodies based on your prompts or specific instructions.
  • Concise text summarization: Have your agent quickly distill long articles, documents, or messages into clear, actionable summaries.
  • Content rephrasing and paraphrasing: Get alternative phrasings or rewording suggestions for existing text, tailored for clarity or tone.
  • Personalized content creation: Ask your agent to compose unique written content for outreach, marketing, or daily communication needs.

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 Textcortex 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 Textcortex 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 Textcortex 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 Textcortex session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["textcortex"]
    )
    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 Textcortex 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 Textcortex assistant agent with MCP tools
    agent = AssistantAgent(
        name="textcortex_assistant",
        description="An AI assistant that helps with Textcortex 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 Textcortex 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 Textcortex 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 Textcortex 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 Textcortex 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 Textcortex session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["textcortex"]
    )
    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 Textcortex assistant agent with MCP tools
        agent = AssistantAgent(
            name="textcortex_assistant",
            description="An AI assistant that helps with Textcortex 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 Textcortex 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 Textcortex 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 Textcortex, you can reuse the same structure for other MCP-enabled apps with minimal code changes.
TOOLS

Supported Tools

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

Create Product Title

Tool to generate catchy product titles for listings.

Create Social Media Post

Tool to generate engaging social media posts for Twitter and LinkedIn.

Create Video Description

Generate video descriptions from a title and context, with optional keywords and tone.

Generate Code

Tool to generate code for a given programming language.

Generate Email

Tool to generate email body and subject based on provided details.

Summarize Text

Summarize longer content from supplied text or a file ID.

Translate Text

Tool to translate text into another language.

FRAMEWORKS

How to build Textcortex MCP Agent with another framework

Claude Code logo

Claude Code

Use Textcortex MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Textcortex MCP with Claude Cowork

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Textcortex MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Textcortex MCP with Claude Agent SDK

Codex logo

Codex

Use Textcortex MCP with Codex

OpenClaw logo

OpenClaw

Use Textcortex MCP with OpenClaw

Hermes logo

Hermes

Use Textcortex MCP with Hermes

Atomic Agent logo

Atomic Agent

Use Textcortex MCP with Atomic Agent

Google ADK logo

Google ADK

Use Textcortex MCP with Google ADK

LangChain logo

LangChain

Use Textcortex MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Textcortex MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Textcortex MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Textcortex MCP with LlamaIndex

CrewAI logo

CrewAI

Use Textcortex MCP with CrewAI

Pydantic AI logo

Pydantic AI

Use Textcortex MCP with Pydantic AI

FAQ

Frequently asked questions

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

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

Start with Textcortex.It takes 30 seconds.

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

Start building