# How to integrate DEV Community MCP with LlamaIndex ```json { "title": "How to integrate DEV Community MCP with LlamaIndex", "toolkit": "DEV Community", "toolkit_slug": "devto", "framework": "LlamaIndex", "framework_slug": "llama-index", "url": "https://composio.dev/toolkits/devto/framework/llama-index", "markdown_url": "https://composio.dev/toolkits/devto/framework/llama-index.md", "updated_at": "2026-06-18T09:25:59.372Z" } ``` ## Introduction This guide walks you through connecting DEV Community to LlamaIndex 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 LlamaIndex 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) - [CrewAI](https://composio.dev/toolkits/devto/framework/crew-ai) ## TL;DR Here's what you'll learn: - Set your OpenAI and Composio API keys - Install LlamaIndex and Composio packages - Create a Composio Tool Router session for DEV Community - Connect LlamaIndex to the DEV Community MCP server - Build a DEV Community-powered agent using LlamaIndex - Interact with DEV Community through natural language ## What is LlamaIndex? LlamaIndex is a data framework for building LLM applications. It provides tools for connecting LLMs to external data sources and services through agents and tools. Key features include: - ReAct Agent: Reasoning and acting pattern for tool-using agents - MCP Tools: Native support for Model Context Protocol - Context Management: Maintain conversation context across interactions - Async Support: Built for async/await patterns ## 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 agent to DEV Community. It provides structured and secure access so your agent can perform DEV Community operations on your behalf through a secure, permission-based interface. 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 Before you begin, make sure you have: - Python 3.8/Node 16 or higher installed - A Composio account with the API key - An OpenAI API key - A DEV Community account and project - Basic familiarity with async Python/Typescript ### 1. Getting API Keys for OpenAI, Composio, and DEV Community No description provided. ### 2. Installing dependencies No description provided. ```python pip install composio-llamaindex llama-index llama-index-llms-openai llama-index-tools-mcp python-dotenv ``` ```typescript npm install @composio/llamaindex @llamaindex/openai @llamaindex/tools @llamaindex/workflow dotenv ``` ### 3. Set environment variables Create a .env file in your project root: These credentials will be used to: - Authenticate with OpenAI's GPT-5 model - Connect to Composio's Tool Router - Identify your Composio user session for DEV Community access ```bash OPENAI_API_KEY=your-openai-api-key COMPOSIO_API_KEY=your-composio-api-key COMPOSIO_USER_ID=your-user-id ``` ### 4. Import modules No description provided. ```python import asyncio import os import dotenv from composio import Composio from composio_llamaindex import LlamaIndexProvider from llama_index.core.agent.workflow import ReActAgent from llama_index.core.workflow import Context from llama_index.llms.openai import OpenAI from llama_index.tools.mcp import BasicMCPClient, McpToolSpec dotenv.load_dotenv() ``` ```typescript import "dotenv/config"; import readline from "node:readline/promises"; import { stdin as input, stdout as output } from "node:process"; import { Composio } from "@composio/core"; import { mcp } from "@llamaindex/tools"; import { agent as createAgent } from "@llamaindex/workflow"; import { openai } from "@llamaindex/openai"; dotenv.config(); ``` ### 5. Load environment variables and initialize Composio No description provided. ```python OPENAI_API_KEY = os.getenv("OPENAI_API_KEY") COMPOSIO_API_KEY = os.getenv("COMPOSIO_API_KEY") COMPOSIO_USER_ID = os.getenv("COMPOSIO_USER_ID") if not OPENAI_API_KEY: raise ValueError("OPENAI_API_KEY is not set in the environment") if not COMPOSIO_API_KEY: raise ValueError("COMPOSIO_API_KEY is not set in the environment") if not COMPOSIO_USER_ID: raise ValueError("COMPOSIO_USER_ID is not set in the environment") ``` ```typescript const OPENAI_API_KEY = process.env.OPENAI_API_KEY; const COMPOSIO_API_KEY = process.env.COMPOSIO_API_KEY; const COMPOSIO_USER_ID = process.env.COMPOSIO_USER_ID; if (!OPENAI_API_KEY) throw new Error("OPENAI_API_KEY is not set"); if (!COMPOSIO_API_KEY) throw new Error("COMPOSIO_API_KEY is not set"); if (!COMPOSIO_USER_ID) throw new Error("COMPOSIO_USER_ID is not set"); ``` ### 6. Create a Tool Router session and build the agent function What's happening here: - We create a Composio client using your API key and configure it with the LlamaIndex provider - We then create a tool router MCP session for your user, specifying the toolkits we want to use (in this case, dev community) - The session returns an MCP HTTP endpoint URL that acts as a gateway to all your configured tools - LlamaIndex will connect to this endpoint to dynamically discover and use the available DEV Community tools. - The MCP tools are mapped to LlamaIndex-compatible tools and plug them into the Agent. ```python async def build_agent() -> ReActAgent: composio_client = Composio( api_key=COMPOSIO_API_KEY, provider=LlamaIndexProvider(), ) session = composio_client.create( user_id=COMPOSIO_USER_ID, toolkits=["devto"], ) mcp_url = session.mcp.url print(f"Composio MCP URL: {mcp_url}") mcp_client = BasicMCPClient(mcp_url, headers={"x-api-key": COMPOSIO_API_KEY}) mcp_tool_spec = McpToolSpec(client=mcp_client) tools = await mcp_tool_spec.to_tool_list_async() llm = OpenAI(model="gpt-5") description = "An agent that uses Composio Tool Router MCP tools to perform DEV Community actions." system_prompt = """ You are a helpful assistant connected to Composio Tool Router. Use the available tools to answer user queries and perform DEV Community actions. """ return ReActAgent(tools=tools, llm=llm, description=description, system_prompt=system_prompt, verbose=True) ``` ```typescript async function buildAgent() { console.log(`Initializing Composio client...${COMPOSIO_USER_ID!}...`); console.log(`COMPOSIO_USER_ID: ${COMPOSIO_USER_ID!}...`); const composio = new Composio({ apiKey: COMPOSIO_API_KEY, provider: new LlamaindexProvider(), }); const session = await composio.create( COMPOSIO_USER_ID!, { toolkits: ["devto"], }, ); const mcpUrl = session.mcp.url; console.log(`Composio Tool Router MCP URL: ${mcpUrl}`); const server = mcp({ url: mcpUrl, clientName: "composio_tool_router_with_llamaindex", requestInit: { headers: { "x-api-key": COMPOSIO_API_KEY!, }, }, // verbose: true, }); const tools = await server.tools(); const llm = openai({ apiKey: OPENAI_API_KEY, model: "gpt-5" }); const agent = createAgent({ name: "composio_tool_router_with_llamaindex", description : "An agent that uses Composio Tool Router MCP tools to perform actions.", systemPrompt: "You are a helpful assistant connected to Composio Tool Router."+ "Use the available tools to answer user queries and perform DEV Community actions." , llm, tools, }); return agent; } ``` ### 7. Create an interactive chat loop No description provided. ```python async def chat_loop(agent: ReActAgent) -> None: ctx = Context(agent) print("Type 'quit', 'exit', or Ctrl+C to stop.") while True: try: user_input = input("\nYou: ").strip() except (KeyboardInterrupt, EOFError): print("\nBye!") break if not user_input or user_input.lower() in {"quit", "exit"}: print("Bye!") break try: print("Agent: ", end="", flush=True) handler = agent.run(user_input, ctx=ctx) async for event in handler.stream_events(): # Stream token-by-token from LLM responses if hasattr(event, "delta") and event.delta: print(event.delta, end="", flush=True) # Show tool calls as they happen elif hasattr(event, "tool_name"): print(f"\n[Using tool: {event.tool_name}]", flush=True) # Get final response response = await handler print() # Newline after streaming except KeyboardInterrupt: print("\n[Interrupted]") continue except Exception as e: print(f"\nError: {e}") ``` ```typescript async function chatLoop(agent: ReturnType) { const rl = readline.createInterface({ input, output }); console.log("Type 'quit' or 'exit' to stop."); while (true) { let userInput: string; try { userInput = (await rl.question("\nYou: ")).trim(); } catch { console.log("\nAgent: Bye!"); break; } if (!userInput) { continue; } const lower = userInput.toLowerCase(); if (lower === "quit" || lower === "exit") { console.log("Agent: Bye!"); break; } try { process.stdout.write("Agent: "); const stream = agent.runStream(userInput); let finalResult: any = null; for await (const event of stream) { // The event.data contains the streamed content const data: any = event.data; // Check for streaming delta content if (data?.delta) { process.stdout.write(data.delta); } // Store final result for fallback if (data?.result || data?.message) { finalResult = data; } } // If no streaming happened, show the final result if (finalResult) { const answer = finalResult.result ?? finalResult.message?.content ?? finalResult.message ?? ""; if (answer && typeof answer === "string" && !answer.includes("[object")) { process.stdout.write(answer); } } console.log(); // New line after streaming completes } catch (err: any) { console.error("\nAgent error:", err?.message ?? err); } } rl.close(); } ``` ### 8. Define the main entry point What's happening here: - We're orchestrating the entire application flow - The agent gets built with proper error handling - Then we kick off the interactive chat loop so you can start talking to DEV Community ```python async def main() -> None: agent = await build_agent() await chat_loop(agent) if __name__ == "__main__": # Handle Ctrl+C gracefully signal.signal(signal.SIGINT, lambda s, f: (print("\nBye!"), exit(0))) try: asyncio.run(main()) except KeyboardInterrupt: print("\nBye!") ``` ```typescript async function main() { try { const agent = await buildAgent(); await chatLoop(agent); } catch (err) { console.error("Failed to start agent:", err); process.exit(1); } } main(); ``` ### 9. Run the agent When prompted, authenticate and authorise your agent with DEV Community, then start asking questions. ```bash python llamaindex_agent.py ``` ```typescript npx ts-node llamaindex-agent.ts ``` ## Complete Code ```python import asyncio import os import signal import dotenv from composio import Composio from composio_llamaindex import LlamaIndexProvider from llama_index.core.agent.workflow import ReActAgent from llama_index.core.workflow import Context from llama_index.llms.openai import OpenAI from llama_index.tools.mcp import BasicMCPClient, McpToolSpec dotenv.load_dotenv() OPENAI_API_KEY = os.getenv("OPENAI_API_KEY") COMPOSIO_API_KEY = os.getenv("COMPOSIO_API_KEY") COMPOSIO_USER_ID = os.getenv("COMPOSIO_USER_ID") if not OPENAI_API_KEY: raise ValueError("OPENAI_API_KEY is not set") if not COMPOSIO_API_KEY: raise ValueError("COMPOSIO_API_KEY is not set") if not COMPOSIO_USER_ID: raise ValueError("COMPOSIO_USER_ID is not set") async def build_agent() -> ReActAgent: composio_client = Composio( api_key=COMPOSIO_API_KEY, provider=LlamaIndexProvider(), ) session = composio_client.create( user_id=COMPOSIO_USER_ID, toolkits=["devto"], ) mcp_url = session.mcp.url print(f"Composio MCP URL: {mcp_url}") mcp_client = BasicMCPClient(mcp_url, headers={"x-api-key": COMPOSIO_API_KEY}) mcp_tool_spec = McpToolSpec(client=mcp_client) tools = await mcp_tool_spec.to_tool_list_async() llm = OpenAI(model="gpt-5") description = "An agent that uses Composio Tool Router MCP tools to perform DEV Community actions." system_prompt = """ You are a helpful assistant connected to Composio Tool Router. Use the available tools to answer user queries and perform DEV Community actions. """ return ReActAgent( tools=tools, llm=llm, description=description, system_prompt=system_prompt, verbose=True, ); async def chat_loop(agent: ReActAgent) -> None: ctx = Context(agent) print("Type 'quit', 'exit', or Ctrl+C to stop.") while True: try: user_input = input("\nYou: ").strip() except (KeyboardInterrupt, EOFError): print("\nBye!") break if not user_input or user_input.lower() in {"quit", "exit"}: print("Bye!") break try: print("Agent: ", end="", flush=True) handler = agent.run(user_input, ctx=ctx) async for event in handler.stream_events(): # Stream token-by-token from LLM responses if hasattr(event, "delta") and event.delta: print(event.delta, end="", flush=True) # Show tool calls as they happen elif hasattr(event, "tool_name"): print(f"\n[Using tool: {event.tool_name}]", flush=True) # Get final response response = await handler print() # Newline after streaming except KeyboardInterrupt: print("\n[Interrupted]") continue except Exception as e: print(f"\nError: {e}") async def main() -> None: agent = await build_agent() await chat_loop(agent) if __name__ == "__main__": # Handle Ctrl+C gracefully signal.signal(signal.SIGINT, lambda s, f: (print("\nBye!"), exit(0))) try: asyncio.run(main()) except KeyboardInterrupt: print("\nBye!") ``` ```typescript import "dotenv/config"; import readline from "node:readline/promises"; import { stdin as input, stdout as output } from "node:process"; import { Composio } from "@composio/core"; import { LlamaindexProvider } from "@composio/llamaindex"; import { mcp } from "@llamaindex/tools"; import { agent as createAgent } from "@llamaindex/workflow"; import { openai } from "@llamaindex/openai"; dotenv.config(); const OPENAI_API_KEY = process.env.OPENAI_API_KEY; const COMPOSIO_API_KEY = process.env.COMPOSIO_API_KEY; const COMPOSIO_USER_ID = process.env.COMPOSIO_USER_ID; if (!OPENAI_API_KEY) { throw new Error("OPENAI_API_KEY is not set in the environment"); } if (!COMPOSIO_API_KEY) { throw new Error("COMPOSIO_API_KEY is not set in the environment"); } if (!COMPOSIO_USER_ID) { throw new Error("COMPOSIO_USER_ID is not set in the environment"); } async function buildAgent() { console.log(`Initializing Composio client...${COMPOSIO_USER_ID!}...`); console.log(`COMPOSIO_USER_ID: ${COMPOSIO_USER_ID!}...`); const composio = new Composio({ apiKey: COMPOSIO_API_KEY, provider: new LlamaindexProvider(), }); const session = await composio.create( COMPOSIO_USER_ID!, { toolkits: ["devto"], }, ); const mcpUrl = session.mcp.url; console.log(`Composio Tool Router MCP URL: ${mcpUrl}`); const server = mcp({ url: mcpUrl, clientName: "composio_tool_router_with_llamaindex", requestInit: { headers: { "x-api-key": COMPOSIO_API_KEY!, }, }, // verbose: true, }); const tools = await server.tools(); const llm = openai({ apiKey: OPENAI_API_KEY, model: "gpt-5" }); const agent = createAgent({ name: "composio_tool_router_with_llamaindex", description: "An agent that uses Composio Tool Router MCP tools to perform actions.", systemPrompt: "You are a helpful assistant connected to Composio Tool Router."+ "Use the available tools to answer user queries and perform DEV Community actions." , llm, tools, }); return agent; } async function chatLoop(agent: ReturnType) { const rl = readline.createInterface({ input, output }); console.log("Type 'quit' or 'exit' to stop."); while (true) { let userInput: string; try { userInput = (await rl.question("\nYou: ")).trim(); } catch { console.log("\nAgent: Bye!"); break; } if (!userInput) { continue; } const lower = userInput.toLowerCase(); if (lower === "quit" || lower === "exit") { console.log("Agent: Bye!"); break; } try { process.stdout.write("Agent: "); const stream = agent.runStream(userInput); let finalResult: any = null; for await (const event of stream) { // The event.data contains the streamed content const data: any = event.data; // Check for streaming delta content if (data?.delta) { process.stdout.write(data.delta); } // Store final result for fallback if (data?.result || data?.message) { finalResult = data; } } // If no streaming happened, show the final result if (finalResult) { const answer = finalResult.result ?? finalResult.message?.content ?? finalResult.message ?? ""; if (answer && typeof answer === "string" && !answer.includes("[object")) { process.stdout.write(answer); } } console.log(); // New line after streaming completes } catch (err: any) { console.error("\nAgent error:", err?.message ?? err); } } rl.close(); } async function main() { try { const agent = await buildAgent(); await chatLoop(agent); } catch (err: any) { console.error("Failed to start agent:", err?.message ?? err); process.exit(1); } } main(); ``` ## Conclusion You've successfully connected DEV Community to LlamaIndex through Composio's Tool Router MCP layer. Key takeaways: - Tool Router dynamically exposes DEV Community tools through an MCP endpoint - LlamaIndex's ReActAgent handles reasoning and orchestration; Composio handles integrations - The agent becomes more capable without increasing prompt size - Async Python provides clean, efficient execution of agent workflows You can easily extend this to other toolkits like Gmail, Notion, Stripe, GitHub, and more by adding them to the toolkits parameter. ## 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) - [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 LlamaIndex? Yes, you can. LlamaIndex 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)