# How to integrate Discord MCP with LlamaIndex

```json
{
  "title": "How to integrate Discord MCP with LlamaIndex",
  "toolkit": "Discord",
  "toolkit_slug": "discord",
  "framework": "LlamaIndex",
  "framework_slug": "llama-index",
  "url": "https://composio.dev/toolkits/discord/framework/llama-index",
  "markdown_url": "https://composio.dev/toolkits/discord/framework/llama-index.md",
  "updated_at": "2026-05-12T10:08:53.927Z"
}
```

## Introduction

This guide walks you through connecting Discord to LlamaIndex using the Composio tool router. By the end, you'll have a working Discord agent that can list all discord servers i belong to, show your connected accounts on discord, fetch your discord profile information through natural language commands.
This guide will help you understand how to give your LlamaIndex agent real control over a Discord account through Composio's Discord MCP server.
Before we dive in, let's take a quick look at the key ideas and tools involved.

## Also integrate Discord with

- [ChatGPT](https://composio.dev/toolkits/discord/framework/chatgpt)
- [OpenAI Agents SDK](https://composio.dev/toolkits/discord/framework/open-ai-agents-sdk)
- [Claude Agent SDK](https://composio.dev/toolkits/discord/framework/claude-agents-sdk)
- [Claude Code](https://composio.dev/toolkits/discord/framework/claude-code)
- [Claude Cowork](https://composio.dev/toolkits/discord/framework/claude-cowork)
- [Codex](https://composio.dev/toolkits/discord/framework/codex)
- [Cursor](https://composio.dev/toolkits/discord/framework/cursor)
- [VS Code](https://composio.dev/toolkits/discord/framework/vscode)
- [OpenCode](https://composio.dev/toolkits/discord/framework/opencode)
- [OpenClaw](https://composio.dev/toolkits/discord/framework/openclaw)
- [Hermes](https://composio.dev/toolkits/discord/framework/hermes-agent)
- [CLI](https://composio.dev/toolkits/discord/framework/cli)
- [Google ADK](https://composio.dev/toolkits/discord/framework/google-adk)
- [LangChain](https://composio.dev/toolkits/discord/framework/langchain)
- [Vercel AI SDK](https://composio.dev/toolkits/discord/framework/ai-sdk)
- [Mastra AI](https://composio.dev/toolkits/discord/framework/mastra-ai)
- [CrewAI](https://composio.dev/toolkits/discord/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 Discord
- Connect LlamaIndex to the Discord MCP server
- Build a Discord-powered agent using LlamaIndex
- Interact with Discord 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 Discord MCP server, and what's possible with it?

The Discord MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Discord account. It provides structured and secure access to your Discord profile, connected accounts, servers, and invites, so your agent can fetch user details, list your servers (guilds), retrieve invite info, and manage your Discord presence on your behalf.
- Retrieve and manage user profile information: Your agent can fetch your Discord profile details, including email and connected third-party accounts, to help keep your data organized and up-to-date.
- Server (guild) discovery and membership checks: Effortlessly list all servers you belong to and verify your membership status in any server.
- Access invite details and server info: Instantly get information about specific Discord invite codes, including the destination server or channel details.
- Guild member insights: Allow your agent to retrieve your own guild member information across servers, including permissions and roles.
- OAuth2 application and authorization review: Let your agent fetch your app’s OAuth2 authorization details, so you always know what permissions are granted and when tokens expire.

## Supported Tools

| Tool slug | Name | Description |
|---|---|---|
| `DISCORD_CONSUME_ENTITLEMENT` | Consume Entitlement | Marks a one-time purchase consumable entitlement as consumed for a given application. Only applicable to entitlements backed by one-time purchase consumable SKUs. |
| `DISCORD_DELETE_TEST_ENTITLEMENT` | Delete Test Entitlement | Deletes a currently active test entitlement for a given application. Use this to clean up test entitlements that are no longer needed. |
| `DISCORD_DELETE_USER_APPLICATION_ROLE_CONNECTION` | Delete User Application Role Connection | Deletes the current user's application role connection for the specified application. Removes the platform metadata and linked role connection. |
| `DISCORD_EDIT_APPLICATION_COMMAND_PERMISSIONS` | Edit Application Command Permissions | Edits the permissions for a specific application command in a guild. Requires OAuth2 Bearer token (bot tokens will error). The authorizing user must have MANAGE_GUILD and MANAGE_ROLES permissions in the target guild. |
| `DISCORD_GET_APPLICATION_COMMAND_PERMISSIONS` | Get Application Command Permissions | Retrieves the permissions for a specific application command in a guild. Requires OAuth2 Bearer token (bot tokens will error). The authorizing user must have MANAGE_GUILD and MANAGE_ROLES permissions in the target guild. |
| `DISCORD_GET_BATCH_APPLICATION_COMMAND_PERMISSIONS` | Get Batch Application Command Permissions | Retrieves permissions for all commands of an application in a guild. Returns a list of permission objects for each command. Requires OAuth2 Bearer token (Bot tokens will error). |
| `DISCORD_GET_CURRENT_USER_APPLICATION_ENTITLEMENTS` | Get Current User Application Entitlements | Tool to retrieve entitlements for the current user for a given application. Use when you need to check what premium offerings or subscriptions the authenticated user has access to. |
| `DISCORD_GET_GATEWAY` | Get Gateway | Tool to retrieve a valid WebSocket (wss) URL for establishing a Gateway connection to Discord. Use when you need to connect to the Discord Gateway for real-time events. |
| `DISCORD_GET_GUILD_TEMPLATE` | Get Guild Template | Tool to retrieve information about a Discord guild template using its unique template code. Use when you need to get details about a guild template for creating new servers. |
| `DISCORD_GET_GUILD_WIDGET` | Get Guild Widget | Tool to retrieve the guild widget in JSON format. Use when you need to get public information about a Discord guild's widget that can be displayed on external websites. The widget must be enabled in the guild's server settings. |
| `DISCORD_GET_GUILD_WIDGET_PNG` | Get Guild Widget PNG | Tool to retrieve a PNG image widget for a Discord guild. Use when you need a visual representation of the guild widget that can be displayed on external websites. The widget must be enabled in the guild's server settings. |
| `DISCORD_GET_MY_GUILD_MEMBER` | Get my guild member | Retrieves the guild member object for the currently authenticated user within a specified guild, including roles, nickname, join date, and permissions. |
| `DISCORD_GET_MY_OAUTH2_AUTHORIZATION` | Get my OAuth2 authorization | Retrieves current OAuth2 authorization details for the application, including app info, scopes, token expiration, and user data (contingent on scopes like 'identify'). |
| `DISCORD_GET_MY_USER` | Get My User | Fetches comprehensive profile information for the currently authenticated Discord user, including email if the 'email' scope is granted. |
| `DISCORD_GET_OPENID_CONNECT_USERINFO` | Get OpenID Connect userinfo | Retrieve OpenID Connect compliant user information for the authenticated user. Returns standardized OIDC user claims (sub, email, nickname, picture, locale, etc.) following the OpenID Connect specification. Requires OAuth2 access token with 'openid' scope; additional fields require 'identify' and 'email' scopes. |
| `DISCORD_GET_PUBLIC_KEYS` | Get Public Keys | Tool to retrieve Discord OAuth2 public keys. Use when you need to verify OAuth2 tokens or access public keys for cryptographic operations. |
| `DISCORD_GET_SKU_SUBSCRIPTION` | Get SKU Subscription | Retrieves a specific subscription by ID for a given SKU. Use to check details of a single user subscription. |
| `DISCORD_GET_USER` | Get User | Retrieve information about a Discord user. With OAuth Bearer token authentication, this returns the authenticated user's information (use '@me'). With Bot token authentication, you can query any user by their ID. Use this when you need user details like username, avatar, email (if email scope is granted), locale, premium status, or other profile information. |
| `DISCORD_GET_USER_APPLICATION_ROLE_CONNECTION` | Get User Application Role Connection | Retrieves the application role connection for the currently authenticated user for a specified application. Requires the role_connections.write OAuth2 scope. |
| `DISCORD_INVITE_RESOLVE` | Resolve Invite | Tool to resolve and retrieve information about a Discord invite code. Use when you need to get details about a guild, channel, or event associated with an invite code. |
| `DISCORD_LEAVE_GUILD` | Leave Guild | Leaves a Discord guild (server) on behalf of the currently authenticated user. |
| `DISCORD_LIST_MY_CONNECTIONS` | List My Connections | Retrieves a list of the authenticated user's connected third-party accounts on Discord. |
| `DISCORD_LIST_MY_GUILDS` | List My Guilds | Lists the current user's guilds, returning partial data for each; primarily used for displaying server lists or verifying memberships. |
| `DISCORD_LIST_SKU_SUBSCRIPTIONS` | List SKU Subscriptions | Lists all subscriptions for a given SKU. When using a Bot token, the user_id query parameter is required. Returns paginated subscription objects. |
| `DISCORD_LIST_STICKER_PACKS` | List Sticker Packs | Tool to retrieve all available Discord Nitro sticker packs. Use when you need to list or browse official Discord sticker packs. |
| `DISCORD_MODIFY_CURRENT_USER` | Modify Current User | Modifies the currently authenticated Discord user's profile. Can update username (limited to 2 changes per hour) and avatar. |
| `DISCORD_UPDATE_USER_APPLICATION_ROLE_CONNECTION` | Update User Application Role Connection | Updates the application role connection for the currently authenticated user for a specified application. Requires the role_connections.write OAuth2 scope. |

## Supported Triggers

| Trigger slug | Name | Description |
|---|---|---|
| `DISCORD_NEW_MESSAGE_TRIGGER` | New Discord Message Trigger | Polls a specific Discord channel for new messages. |

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

The Discord MCP server is an implementation of the Model Context Protocol that connects your AI agent to Discord. It provides structured and secure access so your agent can perform Discord 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 Discord account and project
- Basic familiarity with async Python/Typescript

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

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 Discord 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, discord)
- 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 Discord 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=["discord"],
    )

    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 Discord actions."
    system_prompt = """
    You are a helpful assistant connected to Composio Tool Router.
    Use the available tools to answer user queries and perform Discord 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: ["discord"],
    },
  );

  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 Discord 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<typeof createAgent>) {
  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 Discord
```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 Discord, 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=["discord"],
    )

    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 Discord actions."
    system_prompt = """
    You are a helpful assistant connected to Composio Tool Router.
    Use the available tools to answer user queries and perform Discord 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: ["discord"],
    },
  );

  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 Discord actions." ,
    llm,
    tools,
  });

  return agent;
}

async function chatLoop(agent: ReturnType<typeof createAgent>) {
  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 Discord to LlamaIndex through Composio's Tool Router MCP layer.
Key takeaways:
- Tool Router dynamically exposes Discord 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 Discord MCP Agent with another framework

- [ChatGPT](https://composio.dev/toolkits/discord/framework/chatgpt)
- [OpenAI Agents SDK](https://composio.dev/toolkits/discord/framework/open-ai-agents-sdk)
- [Claude Agent SDK](https://composio.dev/toolkits/discord/framework/claude-agents-sdk)
- [Claude Code](https://composio.dev/toolkits/discord/framework/claude-code)
- [Claude Cowork](https://composio.dev/toolkits/discord/framework/claude-cowork)
- [Codex](https://composio.dev/toolkits/discord/framework/codex)
- [Cursor](https://composio.dev/toolkits/discord/framework/cursor)
- [VS Code](https://composio.dev/toolkits/discord/framework/vscode)
- [OpenCode](https://composio.dev/toolkits/discord/framework/opencode)
- [OpenClaw](https://composio.dev/toolkits/discord/framework/openclaw)
- [Hermes](https://composio.dev/toolkits/discord/framework/hermes-agent)
- [CLI](https://composio.dev/toolkits/discord/framework/cli)
- [Google ADK](https://composio.dev/toolkits/discord/framework/google-adk)
- [LangChain](https://composio.dev/toolkits/discord/framework/langchain)
- [Vercel AI SDK](https://composio.dev/toolkits/discord/framework/ai-sdk)
- [Mastra AI](https://composio.dev/toolkits/discord/framework/mastra-ai)
- [CrewAI](https://composio.dev/toolkits/discord/framework/crew-ai)

## Related Toolkits

- [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.
- [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.
- [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.
- [Gong](https://composio.dev/toolkits/gong) - Gong is a platform for video meetings, call recording, and team collaboration. It helps teams capture conversations, analyze calls, and turn insights into action.
- [Microsoft teams](https://composio.dev/toolkits/microsoft_teams) - Microsoft Teams is a collaboration platform that combines chat, meetings, and file sharing within Microsoft 365. It keeps distributed teams connected and productive through seamless virtual communication.
- [Slackbot](https://composio.dev/toolkits/slackbot) - Slackbot is a conversational automation tool for Slack that handles reminders, notifications, and automated responses. It boosts team productivity by streamlining onboarding, answering FAQs, and managing timely alerts—all right inside Slack.
- [2chat](https://composio.dev/toolkits/_2chat) - 2chat is an API platform for WhatsApp and multichannel text messaging. It streamlines chat automation, group management, and real-time messaging for developers.
- [Agent mail](https://composio.dev/toolkits/agent_mail) - Agent mail provides AI agents with dedicated email inboxes for sending, receiving, and managing emails. It empowers agents to communicate autonomously with people, services, and other agents—no human intervention needed.
- [Basecamp](https://composio.dev/toolkits/basecamp) - Basecamp is a project management and team collaboration tool by 37signals. It helps teams organize tasks, share files, and communicate efficiently in one place.
- [Chatwork](https://composio.dev/toolkits/chatwork) - Chatwork is a team communication platform with group chats, file sharing, and task management. It helps businesses boost collaboration and streamline productivity.
- [Clickmeeting](https://composio.dev/toolkits/clickmeeting) - ClickMeeting is a cloud-based platform for running online meetings and webinars. It helps businesses and individuals host, manage, and engage virtual audiences with ease.
- [Confluence](https://composio.dev/toolkits/confluence) - Confluence is Atlassian's team collaboration and knowledge management platform. It helps your team organize, share, and update documents and project content in one secure workspace.
- [Dailybot](https://composio.dev/toolkits/dailybot) - DailyBot streamlines team collaboration with chat-based standups, reminders, and polls. It keeps work flowing smoothly in your favorite messaging platforms.
- [Dialmycalls](https://composio.dev/toolkits/dialmycalls) - Dialmycalls is a mass notification service for sending voice and text messages to contacts. It helps teams and organizations quickly broadcast urgent alerts and updates.
- [Dialpad](https://composio.dev/toolkits/dialpad) - Dialpad is a cloud-based business phone and contact center system for teams. It unifies voice, video, messaging, and meetings across your devices.
- [Discordbot](https://composio.dev/toolkits/discordbot) - Discordbot is an automation tool for Discord servers that handles moderation, messaging, and user engagement. It helps communities run smoothly by automating routine and complex tasks.
- [Echtpost](https://composio.dev/toolkits/echtpost) - Echtpost is a secure digital communication platform for encrypted document and message exchange. It ensures confidential data stays private and protected during transmission.
- [Egnyte](https://composio.dev/toolkits/egnyte) - Egnyte is a cloud-based platform for secure file sharing, storage, and governance. It helps teams collaborate efficiently while maintaining data compliance and security.
- [Google Meet](https://composio.dev/toolkits/googlemeet) - Google Meet is a secure video conferencing platform for virtual meetings, chat, and screen sharing. It helps teams connect, collaborate, and communicate seamlessly from anywhere.
- [Heartbeat](https://composio.dev/toolkits/heartbeat) - Heartbeat is a plug-and-play platform for building and managing online communities. It helps you organize users, channels, events, and discussions in one place.

## Frequently Asked Questions

### What are the differences in Tool Router MCP and Discord MCP?

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

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

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

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