# How to integrate DEV Community MCP with Autogen

```json
{
  "title": "How to integrate DEV Community MCP with Autogen",
  "toolkit": "DEV Community",
  "toolkit_slug": "devto",
  "framework": "AutoGen",
  "framework_slug": "autogen",
  "url": "https://composio.dev/toolkits/devto/framework/autogen",
  "markdown_url": "https://composio.dev/toolkits/devto/framework/autogen.md",
  "updated_at": "2026-06-18T09:25:59.372Z"
}
```

## Introduction

This guide walks you through connecting DEV Community to AutoGen using the Composio tool router. By the end, you'll have a working DEV Community agent that can list your published dev articles, draft a tutorial post about docker, find trending javascript posts on dev through natural language commands.
This guide will help you understand how to give your AutoGen agent real control over a DEV Community account through Composio's DEV Community MCP server.
Before we dive in, let's take a quick look at the key ideas and tools involved.

## Also integrate DEV Community with

- [OpenAI Agents SDK](https://composio.dev/toolkits/devto/framework/open-ai-agents-sdk)
- [Claude Agent SDK](https://composio.dev/toolkits/devto/framework/claude-agents-sdk)
- [Claude Code](https://composio.dev/toolkits/devto/framework/claude-code)
- [Claude Cowork](https://composio.dev/toolkits/devto/framework/claude-cowork)
- [Codex](https://composio.dev/toolkits/devto/framework/codex)
- [OpenClaw](https://composio.dev/toolkits/devto/framework/openclaw)
- [Hermes](https://composio.dev/toolkits/devto/framework/hermes-agent)
- [CLI](https://composio.dev/toolkits/devto/framework/cli)
- [Google ADK](https://composio.dev/toolkits/devto/framework/google-adk)
- [LangChain](https://composio.dev/toolkits/devto/framework/langchain)
- [Vercel AI SDK](https://composio.dev/toolkits/devto/framework/ai-sdk)
- [Mastra AI](https://composio.dev/toolkits/devto/framework/mastra-ai)
- [LlamaIndex](https://composio.dev/toolkits/devto/framework/llama-index)
- [CrewAI](https://composio.dev/toolkits/devto/framework/crew-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 DEV Community
- Wire that MCP URL into Autogen using McpWorkbench and StreamableHttpServerParams
- Configure an Autogen AssistantAgent that can call DEV Community tools
- Run a live chat loop where you ask the agent to perform DEV Community 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 DEV Community MCP server, and what's possible with it?

The DEV Community MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your DEV Community account. It provides structured and secure access so your agent can perform DEV Community operations on your behalf.

## Supported Tools

| Tool slug | Name | Description |
|---|---|---|
| `DEVTO_CREATE_ARTICLE` | Create Article | Create a new article on DEV Community. Use this action to create a new article on behalf of the authenticated user. The article can be published immediately by setting published=true, or saved as a draft by setting published=false (which is the default). Required fields are title and body_markdown. Optional fields include description, main_image, tags, series, canonical_url, and organization_id. |
| `DEVTO_GET_ARTICLE` | Get Article By ID | Returns a single published article by its ID, including full body content. Use this action when you know the unique ID of the article you want to retrieve. The response includes complete article details such as title, full HTML and markdown body content, author information, reaction counts, comments count, and reading time. |
| `DEVTO_GET_ARTICLE_BY_PATH` | Get Article By Path | Returns a single published article by username and slug path. Use this action when you know the username of the author and the article's slug. The response includes full article details including title, content, author info, reactions count, comments count, and reading time. |
| `DEVTO_GET_COMMENT` | Get Comment by ID | Returns a single comment and its descendants (replies) by comment ID. Use this action when you need to retrieve a specific comment along with all its replies from DEV Community. The response includes the comment content, author information, and nested child comments. Note: The comment ID is the id_code field (e.g., "1", "32k5a"), not the numeric user_id. |
| `DEVTO_GET_CURRENT_USER` | Get Current User | Tool to get the currently authenticated user's profile information. Use when you need to retrieve the profile of the user associated with the provided API key. Returns user details including username, name, bio, location, and profile image. |
| `DEVTO_GET_LISTING` | Get Listing | Returns a single classified listing by its ID. Use this action to retrieve detailed information about a specific listing on DEV Community, including the title, description, category, tags, and information about the user who posted it. |
| `DEVTO_GET_ORGANIZATION` | Get Organization | Returns a single organization by its username. Use this action when you need to retrieve organization profile information from DEV Community. Returns organization details including name, summary, social links, and profile image. |
| `DEVTO_GET_PROFILE_IMAGE` | Get Profile Image | Returns the profile image URL for a user or organization by username. Use this action to retrieve the profile picture(s) for a specific user or organization on DEV Community. The API returns both the full-size image URL and a 90px thumbnail. |
| `DEVTO_GET_USER` | Get user | Tool to get a single user by their ID or username. Use when you need to retrieve user profile information from DEV Community. Returns user details including username, name, bio, location, and profile image. |
| `DEVTO_LIST_ARTICLES` | List Articles | Returns a list of published articles, optionally filtered by tags, username, state, or top articles. Supports pagination. Use when you need to browse or search for articles on DEV Community. Examples: - Get latest articles: omit all filters - Get articles by tag: set tag="javascript" - Get top articles: set state="all" and top=7 - Get rising articles: set state="rising" - Get articles from user: set username="ben" |
| `DEVTO_LIST_COMMENTS` | List Comments | Tool to list comments for a specified article or podcast episode on DEV Community. Use when you need to retrieve all comments for a particular article or podcast episode. Requires either a_id (article ID) or p_id (podcast episode ID) parameter. |
| `DEVTO_LIST_FOLLOWED_TAGS` | List Followed Tags | Returns a list of tags followed by the authenticated user. Use this action to retrieve the tags that the currently authenticated user has followed on DEV.to. The response includes the tag ID, name, and points. |
| `DEVTO_LIST_FOLLOWERS` | List Followers | Tool to retrieve a list of users who follow the authenticated user. Supports pagination with 80 followers per page by default. Use when you need to see who is following the authenticated user's profile. |
| `DEVTO_LIST_LATEST_ARTICLES` | List latest DEV Community articles | Tool to retrieve a list of published articles sorted by descending publish date. Use when you need to fetch the latest articles from DEV Community with pagination support. Returns articles with full details including author info, tags, and engagement metrics. |
| `DEVTO_LIST_LISTINGS` | List Listings | Returns a list of classified listings for jobs, mentors, products, etc. Use this action to browse available listings on DEV Community. Supports pagination and filtering by category to find specific types of listings (jobs, mentors, events, etc.). |
| `DEVTO_LIST_LISTINGS_BY_CATEGORY` | List Listings By Category | Returns a list of classified listings filtered by category. Use this action to browse listings on DEV Community for a specific category (jobs, mentors, products, events, etc.). The category is a required path parameter. Supports pagination via page and per_page parameters. |
| `DEVTO_LIST_ORGANIZATION_ARTICLES` | List Organization Articles | Tool to list articles published by a specific organization on DEV.to. Use when you need to retrieve all articles published by an organization. The results are paginated and can be filtered by page number and items per page. |
| `DEVTO_LIST_ORGANIZATION_USERS` | List organization users on DEV.to | Tool to list users belonging to a specified organization on DEV.to. Use when you need to retrieve all members/users of a particular organization. Returns a list of user objects with their profile information including username, name, profile image, and social links. |
| `DEVTO_LIST_PODCAST_EPISODES` | List podcast episodes on DEV.to | Tool to retrieve a list of podcast episodes from DEV.to. Use when you need to browse or search for podcast episodes on DEV.to. Returns a list of podcast episodes, optionally filtered by podcast username. Supports pagination to navigate through large result sets. |
| `DEVTO_LIST_READING_LIST` | List DEVTO Reading List | Returns the articles in the authenticated user's reading list. Requires authentication via API key. The reading list contains articles that the authenticated user has saved for later reading. |
| `DEVTO_LIST_TAGS` | List Tags | Returns a list of tags with their names, background colors, and text colors. Use this action to retrieve available tags from DEV Community for filtering articles or discovering topics. Supports pagination to handle large numbers of tags. |
| `DEVTO_LIST_USER_ALL_ARTICLES` | List User All Articles | Tool to list all articles (both published and unpublished) for the authenticated user. Use when you need to retrieve all articles belonging to the authenticated user's account, including draft and unpublished articles. |
| `DEVTO_LIST_USER_ARTICLES` | List User Articles | Tool to list published articles for the authenticated user. Use when you need to retrieve only the published articles belonging to the authenticated user's account. For unpublished/draft articles, use the List User All Articles action instead. |
| `DEVTO_LIST_USER_PUBLISHED_ARTICLES` | List user's published articles | Returns a list of the authenticated user's published articles only. Use when you need to retrieve articles that the current user has published on DEV Community. Supports pagination via page and per_page parameters. |
| `DEVTO_LIST_USER_UNPUBLISHED_ARTICLES` | List user's unpublished articles | Returns a list of the authenticated user's unpublished (draft) articles. Use when you need to retrieve draft articles that have not yet been published. Supports pagination via page and per_page parameters. |
| `DEVTO_LIST_VIDEOS` | List Videos | Tool to retrieve a list of articles that contain videos. Use when you need to browse video content on DEV Community. Supports pagination via page and per_page parameters. |
| `DEVTO_UPDATE_ARTICLE` | Update Article | Update an existing article on DEV Community. Only the article owner can update it. Use this action to modify article properties like title, body content, description, cover image, tags, and publication status. Only provide the fields you want to update. |
| `DEVTO_UPDATE_LISTING` | Update Listing | Updates an existing classified listing on DEV Community. Use this action to modify a listing's title, body, category, tags, or status. The 'bump' action refreshes the listing's timestamp, 'publish' sets it to published, and 'unpublish' sets it to unpublished. Requires API key authentication. |

## Supported Triggers

None listed.

## Creating MCP Server - Stand-alone vs Composio SDK

The DEV Community MCP server is an implementation of the Model Context Protocol that connects your AI agents and assistants directly to DEV Community. Instead of manually wiring DEV Community APIs, OAuth, and scopes yourself, you get a structured, tool-based interface that an LLM can call safely.
With Composio's managed implementation, you don't have to create your own developer app. For production, if you're building an end product, we recommend using your own credentials. The managed server helps you prototype fast and go from 0-1 faster.

## Step-by-step Guide

### 1. Prerequisites

You will need:
- A Composio API key
- An OpenAI API key (used by Autogen's OpenAIChatCompletionClient)
- A DEV Community account you can connect to Composio
- Some basic familiarity with Autogen and Python async

### 1. Getting API Keys for OpenAI and Composio

OpenAI API Key
- Go to the [OpenAI dashboard](https://platform.openai.com/settings/organization/api-keys) 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](https://dashboard.composio.dev?utm_source=toolkits&utm_medium=framework_docs).
- Navigate to your API settings and generate a new API key.
- Store this key securely as you'll need it for authentication.

### 2. Install dependencies

Install Composio, Autogen extensions, and dotenv.
What's happening:
- composio connects your agent to DEV Community via MCP
- autogen-agentchat provides the AssistantAgent class
- autogen-ext-openai provides the OpenAI model client
- autogen-ext-tools provides MCP workbench support
```bash
pip install composio python-dotenv
pip install autogen-agentchat autogen-ext-openai autogen-ext-tools
```

### 3. Set up environment variables

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 DEV Community connections to use
```bash
COMPOSIO_API_KEY=your-composio-api-key
OPENAI_API_KEY=your-openai-api-key
USER_ID=your-user-identifier@example.com
```

### 4. Import dependencies and create Tool Router session

What's happening:
- load_dotenv() reads your .env file
- Composio(api_key=...) initializes the SDK
- create(...) creates a Tool Router session that exposes DEV Community tools
- session.mcp.url is the MCP endpoint that Autogen will connect to
```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 DEV Community session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["devto"]
    )
    url = session.mcp.url
```

### 5. Configure MCP parameters for Autogen

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
```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")}
)
```

### 6. Create the model client and agent

What's happening:
- OpenAIChatCompletionClient wraps the OpenAI model for Autogen
- McpWorkbench connects the agent to the MCP tools
- AssistantAgent is configured with the DEV Community tools from the workbench
```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 DEV Community assistant agent with MCP tools
    agent = AssistantAgent(
        name="devto_assistant",
        description="An AI assistant that helps with DEV Community operations.",
        model_client=model_client,
        workbench=workbench,
        model_client_stream=True,
        max_tool_iterations=10
    )
```

### 7. Run the interactive chat loop

What's happening:
- The script prompts you in a loop with You:
- Autogen passes your input to the model, which decides which DEV Community 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
```python
print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
print("Ask any DEV Community 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")
```

## Complete Code

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

## How to build DEV Community MCP Agent with another framework

- [OpenAI Agents SDK](https://composio.dev/toolkits/devto/framework/open-ai-agents-sdk)
- [Claude Agent SDK](https://composio.dev/toolkits/devto/framework/claude-agents-sdk)
- [Claude Code](https://composio.dev/toolkits/devto/framework/claude-code)
- [Claude Cowork](https://composio.dev/toolkits/devto/framework/claude-cowork)
- [Codex](https://composio.dev/toolkits/devto/framework/codex)
- [OpenClaw](https://composio.dev/toolkits/devto/framework/openclaw)
- [Hermes](https://composio.dev/toolkits/devto/framework/hermes-agent)
- [CLI](https://composio.dev/toolkits/devto/framework/cli)
- [Google ADK](https://composio.dev/toolkits/devto/framework/google-adk)
- [LangChain](https://composio.dev/toolkits/devto/framework/langchain)
- [Vercel AI SDK](https://composio.dev/toolkits/devto/framework/ai-sdk)
- [Mastra AI](https://composio.dev/toolkits/devto/framework/mastra-ai)
- [LlamaIndex](https://composio.dev/toolkits/devto/framework/llama-index)
- [CrewAI](https://composio.dev/toolkits/devto/framework/crew-ai)

## Related Toolkits

- [Twitter](https://composio.dev/toolkits/twitter) - Twitter is a social media platform for sharing real-time updates, conversations, and news. Stay connected, informed, and engaged with communities worldwide.
- [Instagram](https://composio.dev/toolkits/instagram) - Instagram is a social platform for sharing photos, videos, and stories with your audience. It helps brands and creators engage, grow, and analyze their online presence.
- [Ayrshare](https://composio.dev/toolkits/ayrshare) - Ayrshare is a Social Media API for managing, automating, and analyzing posts across multiple platforms. It helps you streamline social media workflows and centralize analytics.
- [Dotsimple](https://composio.dev/toolkits/dotsimple) - Dotsimple is a social media management platform for planning, creating, and publishing content. It helps teams boost their reach with AI-powered content generation and actionable analytics.
- [Strava](https://composio.dev/toolkits/strava) - Strava is a social fitness network and app for cyclists and runners. It's perfect for tracking workouts, sharing progress, and joining active communities.
- [Tiktok](https://composio.dev/toolkits/tiktok) - Tiktok is a short-form video platform for creating, sharing, and discovering viral content. It helps creators and brands reach massive audiences with creative tools and global social features.
- [Gmail](https://composio.dev/toolkits/gmail) - Gmail is Google's email service with powerful spam protection, search, and G Suite integration. It keeps your inbox organized and makes communication fast and reliable.
- [Google Calendar](https://composio.dev/toolkits/googlecalendar) - Google Calendar is a time management service for scheduling meetings, events, and reminders. It streamlines personal and team organization with integrated notifications and sharing options.
- [Google Drive](https://composio.dev/toolkits/googledrive) - Google Drive is a cloud storage platform for uploading, sharing, and collaborating on files. It's perfect for keeping your documents accessible and organized across devices.
- [Outlook](https://composio.dev/toolkits/outlook) - Outlook is Microsoft's email and calendaring platform for unified communications and scheduling. It helps users stay organized with powerful email, contacts, and calendar management.
- [Google Sheets](https://composio.dev/toolkits/googlesheets) - Google Sheets is a cloud-based spreadsheet tool for real-time collaboration and data analysis. It lets teams work together from anywhere, updating information instantly.
- [Supabase](https://composio.dev/toolkits/supabase) - Supabase is an open-source backend platform offering scalable Postgres databases, authentication, storage, and real-time APIs. It lets developers build modern apps without managing infrastructure.
- [Composio](https://composio.dev/toolkits/composio) - Composio is an integration platform that connects AI agents with hundreds of business tools. It streamlines authentication and lets you trigger actions across services—no custom code needed.
- [Notion](https://composio.dev/toolkits/notion) - Notion is a collaborative workspace for notes, docs, wikis, and tasks. It streamlines team knowledge, project tracking, and workflow customization in one place.
- [Slack](https://composio.dev/toolkits/slack) - Slack is a channel-based messaging platform for teams and organizations. It helps people collaborate in real time, share files, and connect all their tools in one place.
- [Airtable](https://composio.dev/toolkits/airtable) - Airtable combines the flexibility of spreadsheets with the power of a database for easy project and data management. Teams use Airtable to organize, track, and collaborate with custom views and automations.
- [Google Docs](https://composio.dev/toolkits/googledocs) - Google Docs is a cloud-based word processor that enables document creation and real-time collaboration. Its seamless sharing and version history make team editing and content management a breeze.
- [Google Super](https://composio.dev/toolkits/googlesuper) - Google Super is an all-in-one suite combining Gmail, Drive, Calendar, Sheets, Analytics, and more. It gives you a unified platform to manage your digital life, boosting productivity and organization.
- [Hubspot](https://composio.dev/toolkits/hubspot) - HubSpot is an all-in-one marketing, sales, and customer service platform. It lets teams nurture leads, automate outreach, and track every customer interaction in one place.
- [Codeinterpreter](https://composio.dev/toolkits/codeinterpreter) - Codeinterpreter is a Python-based coding environment with built-in data analysis and visualization. It lets you instantly run scripts, plot results, and prototype solutions inside supported platforms.

## Frequently Asked Questions

### What are the differences in Tool Router MCP and DEV Community MCP?

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

### Can I use Tool Router MCP with Autogen?

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 DEV Community tools.

### Can I manage the permissions and scopes for DEV Community while using Tool Router?

Yes, absolutely. You can configure which DEV Community 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.

### How safe is my data with Composio Tool Router?

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 DEV Community data and credentials are handled as safely as possible.

---
[See all toolkits](https://composio.dev/toolkits) · [Composio docs](https://docs.composio.dev/llms.txt)
