# How to integrate Brilliant directories MCP with LlamaIndex

```json
{
  "title": "How to integrate Brilliant directories MCP with LlamaIndex",
  "toolkit": "Brilliant directories",
  "toolkit_slug": "brilliant_directories",
  "framework": "LlamaIndex",
  "framework_slug": "llama-index",
  "url": "https://composio.dev/toolkits/brilliant_directories/framework/llama-index",
  "markdown_url": "https://composio.dev/toolkits/brilliant_directories/framework/llama-index.md",
  "updated_at": "2026-05-12T10:04:10.993Z"
}
```

## Introduction

This guide walks you through connecting Brilliant directories to LlamaIndex using the Composio tool router. By the end, you'll have a working Brilliant directories agent that can add a new member with company details, delete user and remove their uploaded images, list all categories used to organize members through natural language commands.
This guide will help you understand how to give your LlamaIndex agent real control over a Brilliant directories account through Composio's Brilliant directories MCP server.
Before we dive in, let's take a quick look at the key ideas and tools involved.

## Also integrate Brilliant directories with

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

The Brilliant directories MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Brilliant directories account. It provides structured and secure access to your membership community and business directory platform, so your agent can perform actions like managing users, retrieving data categories, and automating lead and review workflows on your behalf.
- User creation and management: Easily instruct your agent to create new users with detailed profiles or delete existing members, streamlining your directory's onboarding and maintenance.
- Deep data category access: Ask your agent to fetch all available data categories from your site, making it simple to organize content or power dynamic site navigation experiences.
- Lead field discovery and automation: Let your agent retrieve the full structure of your leads table, helping you automate lead capture, validation, or enrichment workflows with up-to-date field metadata.
- Review field extraction and insights: Direct your agent to pull all available review fields, enabling smarter review management, analytics, or custom reporting based on your site’s feedback system.
- User data field exploration: Have your agent fetch and analyze all user-related fields, supporting advanced user segmentation, targeted updates, or personalized communications.

## Supported Tools

| Tool slug | Name | Description |
|---|---|---|
| `BRILLIANT_DIRECTORIES_CREATE_ALBUM_PHOTO` | Create Album Photo | Tool to add a new album photo to a user's portfolio in Brilliant Directories. Use when you need to upload or create a photo entry in a user's album. Required fields are user_id (the owner of the album) and title (photo title). Optional fields include description, status, keywords, file paths, and various metadata for organizing and categorizing photos. Supports e-commerce features like price, availability, and product information. The API endpoint expects application/x-www-form-urlencoded data and returns the created photo data with a generated photo_id. |
| `BRILLIANT_DIRECTORIES_CREATE_DATA_CATEGORY` | Create Data Category | Creates a new data category (post type) in the Brilliant Directories website database. Post types are content types like Videos, Articles, Jobs, Events, Coupons, Classifieds, etc. Required fields: data_name (display name), data_filename (identifier), system_name (system identifier), data_type (numeric type), and form_name (associated form fields name). Optional fields include display configuration (h1, h2, icon, caption_length), sorting options (category_order_by, profile_order_by), pagination (per_page, profile_per_page), layout settings (category_sidebar, profile_sidebar, search_results_layout), and many other customization options. Returns success status with the created data category information. |
| `BRILLIANT_DIRECTORIES_CREATE_DATA_POST` | Create Data Post | Tool to create a new Single Image Post (member post) in the Brilliant Directories database. Use when adding blog posts, articles, or other content types with images to the website. Required fields: post_title, post_content, user_id, data_id, data_type, and post_status. Optional fields include author info, categories, tags, dates, geolocation, and image settings. The API uses application/x-www-form-urlencoded content type for the request body. |
| `BRILLIANT_DIRECTORIES_CREATE_LEAD` | Create Lead | Tool to create a new lead in the Brilliant Directories database. Use when adding new inquiries or contact requests from visitors. Supports automatic geocoding, member matching, and email notifications. Can specify categories, location data, pricing, and custom notes. |
| `BRILLIANT_DIRECTORIES_CREATE_PORTFOLIO_GROUP` | Create Portfolio Group | Creates a new multi-image portfolio post in the Brilliant Directories database. This action allows users to publish content with multiple images, descriptions, and metadata such as categories, tags, and location information. Required fields: user_id (existing user), data_type (use 4 for multi-image posts), data_id (data record identifier), and group_name (post title). Optional fields include: content (group_desc), publication status (group_status), category, location, display order, image URLs with titles and descriptions, tags, geographic data, property details for real estate, and sticky post settings. Use this action when creating portfolio posts, blog articles with galleries, or any content requiring multiple images with rich metadata. |
| `BRILLIANT_DIRECTORIES_CREATE_UNSUBSCRIBE` | Create Unsubscribe | Tool to add an unsubscriber to the database and unsubscribe a member from email campaigns. Use when you need to remove a member's email address from the email campaign list. Requires email address, code (source of unsubscribe), type ('unsubscribe'), and website_id. Optional parameters include date (timestamp), definitive flag (permanent unsubscribe), and id. |
| `BRILLIANT_DIRECTORIES_CREATE_USER` | Create User | Creates a new user/member account in the Brilliant Directories website database. Required fields: email, password (minimum 6 characters), and subscription_id (must reference an existing membership plan in the system). Optional fields include: personal information (first_name, last_name, company, position), contact details (phone_number, website), address fields (address1, address2, city, state_code, zip_code, country_code), profile information (about_me), and account status flags (active, verified). Returns complete user data including the generated user_id, authentication token, and assigned membership plan details. |
| `BRILLIANT_DIRECTORIES_CREATE_USERS_CLICK` | Create Users Click | Tool to add a new user clicked link tracking record to the database. Creates a click tracking entry that records when and where users click on links within the directory. Required fields: click_url, click_name, click_type, user_id, date_clicked (format: YYYYMMDDHHmmss), and click_from (source page where click originated). Optional fields include click tracking details (click_ip, click_token, visitor_token) and post association fields (is_single_post, post_id). Note: The click_url must be a valid HTTP/HTTPS URL. Protocol schemes like tel: or mailto: are not supported by the API. Use this when you need to track user engagement with links in profiles, listings, or other directory pages. |
| `BRILLIANT_DIRECTORIES_CREATE_WIDGET` | Create Widget | Tool to create a new widget in the Brilliant Directories website database. Use when you need to add custom HTML/PHP content, CSS styles, or JavaScript to create a reusable widget component. |
| `BRILLIANT_DIRECTORIES_DELETE_ALBUM_PHOTO` | Delete Album Photo | Tool to delete an album photo and its related data from the database. Use when you need to permanently remove a photo from a user's portfolio album. |
| `BRILLIANT_DIRECTORIES_DELETE_DATA_CATEGORY` | Delete Data Category | Tool to permanently delete a post type (data category) and all related data from the database. Use when you need to completely remove a post type such as Videos, Articles, Jobs, Events, Coupons, Audios, or Discussions. This is a destructive operation that cannot be undone. |
| `BRILLIANT_DIRECTORIES_DELETE_LEAD` | Delete Lead | Tool to delete a lead and their related data from the database. Use when you need to permanently remove a lead record. |
| `BRILLIANT_DIRECTORIES_DELETE_PORTFOLIO_GROUP` | Delete Portfolio Group | Tool to delete a multi-image post (portfolio group) and its related data from the database. Use when you need to permanently remove a portfolio group/multi-image post. |
| `BRILLIANT_DIRECTORIES_DELETE_UNSUBSCRIBE` | Delete Unsubscribe Record | Tool to delete an unsubscribe record and its related data from the database. Use when you need to remove an email from the unsubscribe list. |
| `BRILLIANT_DIRECTORIES_DELETE_USER` | Delete User | This tool deletes an existing user record from the Brilliant Directories website database. It allows for the complete removal of a user record and, optionally, the deletion of the member's uploaded images. |
| `BRILLIANT_DIRECTORIES_DELETE_USERS_CLICK` | Delete Users Click | Tool to delete a user clicked link and their related data from the database. Permanently removes a click record identified by click_id. |
| `BRILLIANT_DIRECTORIES_DELETE_WIDGET` | Delete Widget | Tool to delete a widget and its related data from the database. Use when you need to permanently remove a widget. This is a destructive operation that cannot be undone. |
| `BRILLIANT_DIRECTORIES_GET_ALBUM_PHOTO` | Get Album Photo | Retrieves the complete metadata and details for a single album image from Brilliant Directories. This action fetches comprehensive information about an album photo including its title, description, file paths, timestamps, status, and other metadata. Use when you need to read the data of a specific album image based on its photo_id. Use cases: - Retrieve metadata for a specific photo - Access photo URLs and file paths - Check photo status and visibility settings - Get photo details for display or editing |
| `BRILLIANT_DIRECTORIES_GET_DATA_CATEGORIES` | Get Data Categories Fields | This tool retrieves all available custom fields for Data Categories (Post Types) in a Brilliant Directories website. Data categories/post types include content types like Videos, Articles, Jobs, Events, Coupons, Audios, and Discussions. The endpoint returns field metadata including field keys, labels, types, whether they're required, and help text. This information is useful for understanding what fields are available when working with post types. |
| `BRILLIANT_DIRECTORIES_GET_DATA_CATEGORY` | Get Data Category | Tool to retrieve configuration data for a single post type (data category) in Brilliant Directories. Post types include content types like Videos, Articles, Jobs, Events, Coupons, Audios, and Discussions. This action returns the complete configuration and settings for the specified post type based on its data_id. Use this when you need to inspect or retrieve settings for a specific post type rather than listing all available post types. |
| `BRILLIANT_DIRECTORIES_GET_DATA_POST` | Get Data Post | Tool to retrieve a single image/video post from the Brilliant Directories member posts system. Use this action when you need to read the complete data and metadata for a specific post based on its post_id. Returns detailed post information including content, author details, category information, and associated user data. |
| `BRILLIANT_DIRECTORIES_GET_LEAD` | Get Lead | Tool to retrieve a single lead's complete information from Brilliant Directories. Use when you need to fetch detailed data about a specific lead by its ID. |
| `BRILLIANT_DIRECTORIES_GET_LEAD_FIELDS` | Get Lead Fields | This tool retrieves all available fields in the leads table from a Brilliant Directories website. It returns a JSON object containing a list of fields and their associated metadata (field name, field type, field label, whether the field is required, and if it is a system field) that can be used to understand the structure and metadata of lead-related fields. |
| `BRILLIANT_DIRECTORIES_GET_PORTFOLIO_GROUP` | Get Portfolio Group | Tool to retrieve multi-image post data by group_id. Use when you need to fetch content and metadata for a specific portfolio group or multi-image post. Returns comprehensive information including images, descriptions, location, tags, and property details if applicable. |
| `BRILLIANT_DIRECTORIES_GET_REVIEW` | Get Review | Tool to retrieve complete review data from Brilliant Directories based on review_id. Use when you need to read full review details including content, ratings, reviewer info, and timestamps. |
| `BRILLIANT_DIRECTORIES_GET_REVIEWS_FIELDS` | Get Reviews Fields | Get metadata about all available fields in the users_reviews table from a Brilliant Directories website. This tool returns comprehensive field definitions for the reviews system, including: - Core review fields (review_id, review_title, review_description, review_status) - Reviewer information fields (review_name, review_email) - Rating fields (rating_overall, rating_service, rating_response, rating_expertise, rating_results, rating_language) - Timestamp fields (review_added, review_updated, review_approved) - Technical fields (review_token, ip, httpr, formname, revision_timestamp) - Media fields (review_images) - Association fields (user_id, member_id, service_id) This is a read-only tool that requires only authentication and does not make API calls. It provides the standard field schema based on Brilliant Directories API documentation, useful for understanding what fields are available when creating, updating, or searching for reviews. |
| `BRILLIANT_DIRECTORIES_GET_UNSUBSCRIBE` | Get Unsubscribe Record | Tool to retrieve a single unsubscriber record by ID. Use when you need to get details about a specific unsubscribe entry, including the email address, unsubscribe date, and source (admin, email link, or API). |
| `BRILLIANT_DIRECTORIES_GET_USER` | Get User by ID | Tool to retrieve comprehensive data for a single user by their user_id. Use when you need to fetch complete user profile information including contact details, subscription data, and membership information. This action queries the Brilliant Directories API using the user_id as a path parameter, returning detailed user information including profile data, contact details, subscription information, social media links, and more. |
| `BRILLIANT_DIRECTORIES_GET_USER_FIELDS` | Get User Data | Retrieves comprehensive user data from the Brilliant Directories database by searching for a specific property value. This action queries the users_data table using a property (column name) and value pair, returning detailed user information including profile data, contact details, subscription information, social media links, and more. Commonly used to fetch user records by user_id, email, or any other database column. Use cases: - Look up a user by their ID or email - Retrieve complete user profile information - Access subscription and membership details - Get contact information and social media links |
| `BRILLIANT_DIRECTORIES_GET_USERS_CLICK` | Get User Clicked Link | Tool to retrieve click tracking data for a single user clicked link based on the click_id. Use when you need to fetch detailed information about a specific click event, including the user who clicked, the click type, source and destination URLs, timestamps, and associated tokens. |
| `BRILLIANT_DIRECTORIES_GET_USER_TRANSACTIONS` | Get User Transactions | Retrieves payment and transaction history for a member in Brilliant Directories. This action queries transaction records using either user_id or client_id, returning detailed payment history including transaction amounts, dates, payment methods, and status. Optionally returns user schema and credit card information when return_schema is set to 'yes'. Use cases: - Retrieve all transactions for a specific user - Access payment history and invoice details - Get credit card information on file - View transaction status and payment methods |
| `BRILLIANT_DIRECTORIES_GET_WIDGET` | Get Widget | Retrieves the data of a single widget based on the widget_id. Use this to fetch widget configuration and settings from the Brilliant Directories website database. |
| `BRILLIANT_DIRECTORIES_MATCH_LEADS` | Match Leads | Tool to match a batch of emails or user IDs to a specific lead record. Use this when you need to associate multiple contacts or users with an existing lead in the Brilliant Directories system. The users_to_match parameter accepts a comma-separated list of either email addresses or user IDs. |
| `BRILLIANT_DIRECTORIES_SEARCH_REVIEWS` | Search Reviews | Search reviews and their related data from the database. Filter reviews by various criteria. Supports filtering by location (address), keyword search (q), overall rating, and pagination (page, limit). Results can be ordered by date (ascending/descending) or randomly. Use output_type to specify response format (html or array). Enable caching with post_type_cache_system for faster subsequent searches. Use search_priority_flag to prioritize results by membership plan settings. |
| `BRILLIANT_DIRECTORIES_SEARCH_USERS` | Search Users | Search for users/members in the Brilliant Directories database with advanced filtering options. Allows searching and filtering members by keywords, location, categories, and other criteria. Supports pagination, multiple sort orders, and dynamic category filtering for complex queries. Returns comprehensive user data including profile information, contact details, subscription status, and related metadata. |
| `BRILLIANT_DIRECTORIES_UPDATE_ALBUM_PHOTO` | Update Album Photo | Updates an existing album photo record in the Brilliant Directories database. Modifies photo metadata such as title, description, keywords, and status. The photo_id is required to identify which photo to update. All other fields are optional and only the provided fields will be updated. Use when you need to modify photo information, update visibility status, change organization (order, group), or edit photo metadata. |
| `BRILLIANT_DIRECTORIES_UPDATE_DATA_CATEGORY` | Update Data Category | Tool to update an existing post type (data category) record in Brilliant Directories. Use when you need to modify post type settings such as name, display options, layout templates, pagination settings, or other configuration parameters. Requires the data_id parameter to identify which post type to update. All other parameters are optional and only the provided fields will be updated. |
| `BRILLIANT_DIRECTORIES_UPDATE_DATA_POST` | Update Data Post | Updates a single image post record and related data in the Brilliant Directories database. Use this action to modify existing post content including title, content, status, metadata, and other post-related fields. The post_id is required to identify which post to update. All other fields are optional - only the fields you provide will be updated. This allows for partial updates of post records. |
| `BRILLIANT_DIRECTORIES_UPDATE_LEAD` | Update Lead | Updates an existing lead record in the Brilliant Directories website database. The lead_id field is required to identify which lead to update. All other fields are optional - only provide the fields you want to update. This action modifies lead information including contact details (name, email, phone), inquiry details (message, notes, price), location data (coordinates, boundaries, location type), categorization (category IDs and names), and matching settings (auto-match, email notifications, direct member matching). |
| `BRILLIANT_DIRECTORIES_UPDATE_PORTFOLIO_GROUP` | Update Portfolio Group | Tool to update a multi-image post (portfolio group) record in the Brilliant Directories database. Use when you need to modify existing portfolio content, change post details, update images, or modify property information for real estate listings. |
| `BRILLIANT_DIRECTORIES_UPDATE_UNSUBSCRIBE` | Update Unsubscribe | Updates an existing unsubscribe list record in the Brilliant Directories database. Use this to modify unsubscribe settings for email campaigns. |
| `BRILLIANT_DIRECTORIES_UPDATE_USER` | Update User | Updates an existing user record in the Brilliant Directories website database. Modifies user profile information, contact details, social media links, account status, membership plan, and other user-related data. Only user_id is required; all other fields are optional and will only update the specified fields. |
| `BRILLIANT_DIRECTORIES_UPDATE_USERS_CLICK` | Update User Click Record | Updates a user clicked link record and their related data from the database. Modifies click tracking data for existing click records. This action is used to update click tracking information such as click names, URLs, timestamps, user associations, and other metadata for existing click records. The click_id is required to identify which record to update, and all other fields are optional - only provided fields will be updated. Use when you need to correct or update click tracking data, modify click metadata, or update user associations for click records. |
| `BRILLIANT_DIRECTORIES_UPDATE_WIDGET` | Update Widget | Tool to update an existing widget record in the Brilliant Directories database. Modifies widget settings including name, HTML/PHP content, CSS styles, and JavaScript code. |

## Supported Triggers

None listed.

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

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

### 1. Getting API Keys for OpenAI, Composio, and Brilliant directories

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 Brilliant directories 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, brilliant directories)
- 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 Brilliant directories 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=["brilliant_directories"],
    )

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

  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 Brilliant directories 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 Brilliant directories
```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 Brilliant directories, 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=["brilliant_directories"],
    )

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

  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 Brilliant directories 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 Brilliant directories to LlamaIndex through Composio's Tool Router MCP layer.
Key takeaways:
- Tool Router dynamically exposes Brilliant directories 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 Brilliant directories MCP Agent with another framework

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

## Related Toolkits

- [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.
- [Pipedrive](https://composio.dev/toolkits/pipedrive) - Pipedrive is a sales management platform offering pipeline visualization, lead tracking, and workflow automation. It helps sales teams keep deals moving forward efficiently and never miss a follow-up.
- [Salesforce](https://composio.dev/toolkits/salesforce) - Salesforce is a leading CRM platform that helps businesses manage sales, service, and marketing. It centralizes customer data, enabling teams to drive growth and build strong relationships.
- [Apollo](https://composio.dev/toolkits/apollo) - Apollo is a CRM and lead generation platform that helps businesses discover contacts and manage sales pipelines. Use it to streamline customer outreach and track your deals from one place.
- [Attio](https://composio.dev/toolkits/attio) - Attio is a customizable CRM and workspace for managing your team's relationships and workflows. It helps teams organize contacts, automate tasks, and collaborate more efficiently.
- [Acculynx](https://composio.dev/toolkits/acculynx) - AccuLynx is a cloud-based roofing business management software for contractors. It streamlines project tracking, lead management, and document sharing.
- [Addressfinder](https://composio.dev/toolkits/addressfinder) - Addressfinder is a data quality platform for verifying addresses, emails, and phone numbers. It helps you ensure accurate customer and contact data every time.
- [Affinity](https://composio.dev/toolkits/affinity) - Affinity is a relationship intelligence CRM that helps private capital investors find, manage, and close more deals. It streamlines deal flow and surfaces key connections to help you win opportunities.
- [Agencyzoom](https://composio.dev/toolkits/agencyzoom) - AgencyZoom is a sales and performance platform built for P&C insurance agencies. It helps agents boost sales, retain clients, and analyze producer results in one place.
- [Bettercontact](https://composio.dev/toolkits/bettercontact) - Bettercontact is a smart contact enrichment tool for finding emails and phone numbers. It helps boost lead generation with automated, waterfall search across multiple sources.
- [Blackbaud](https://composio.dev/toolkits/blackbaud) - Blackbaud provides cloud-based software for nonprofits, schools, and healthcare institutions. It streamlines fundraising, donor management, and mission-driven operations.
- [Capsule crm](https://composio.dev/toolkits/capsule_crm) - Capsule CRM is a user-friendly CRM platform for managing contacts and sales pipelines. It helps businesses organize relationships and streamline their sales process efficiently.
- [Centralstationcrm](https://composio.dev/toolkits/centralstationcrm) - CentralStationCRM is an easy-to-use CRM software focused on collaboration and long-term customer relationships. It helps teams manage contacts, deals, and communications all in one place.
- [Clientary](https://composio.dev/toolkits/clientary) - Clientary is a platform for managing clients, invoices, projects, proposals, and more. It streamlines client work and saves you serious admin time.
- [Close](https://composio.dev/toolkits/close) - Close is a CRM platform built for sales teams, combining calling, email automation, and predictive dialers. It streamlines sales workflows and boosts productivity with all-in-one communication tools.
- [Dropcontact](https://composio.dev/toolkits/dropcontact) - Dropcontact is a B2B email finder and data enrichment service for professionals. It delivers verified email addresses and enriches contact info with up-to-date data.
- [Dynamics365](https://composio.dev/toolkits/dynamics365) - Dynamics 365 is Microsoft's platform combining CRM, ERP, and productivity apps. It streamlines sales, marketing, service, and operations in one place.
- [Espocrm](https://composio.dev/toolkits/espocrm) - EspoCRM is an open-source web application for managing customer relationships. It helps businesses organize contacts, track leads, and streamline their sales process.
- [Fireberry](https://composio.dev/toolkits/fireberry) - Fireberry is a CRM platform that streamlines customer and sales management. It helps businesses organize contacts, automate sales, and integrate with other business tools.
- [Firmao](https://composio.dev/toolkits/firmao) - Firmao is a business information platform offering company, industry, and market data. Use it to quickly research firms and gain competitive market insights.

## Frequently Asked Questions

### What are the differences in Tool Router MCP and Brilliant directories MCP?

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

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

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

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