# How to integrate Fluxguard MCP with LlamaIndex

```json
{
  "title": "How to integrate Fluxguard MCP with LlamaIndex",
  "toolkit": "Fluxguard",
  "toolkit_slug": "fluxguard",
  "framework": "LlamaIndex",
  "framework_slug": "llama-index",
  "url": "https://composio.dev/toolkits/fluxguard/framework/llama-index",
  "markdown_url": "https://composio.dev/toolkits/fluxguard/framework/llama-index.md",
  "updated_at": "2026-05-12T10:11:58.419Z"
}
```

## Introduction

This guide walks you through connecting Fluxguard to LlamaIndex using the Composio tool router. By the end, you'll have a working Fluxguard agent that can add competitor's homepage for daily monitoring, list all recent alerts for your sites, acknowledge today's website change alert through natural language commands.
This guide will help you understand how to give your LlamaIndex agent real control over a Fluxguard account through Composio's Fluxguard MCP server.
Before we dive in, let's take a quick look at the key ideas and tools involved.

## Also integrate Fluxguard with

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

The Fluxguard MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Fluxguard account. It provides structured and secure access to your website monitoring and alerting data, so your agent can perform actions like adding new monitored pages, categorizing sites, retrieving alerts, acknowledging changes, and managing webhooks on your behalf.
- Automated website monitoring setup: Direct your agent to add new web pages or entire sites for continuous change detection and tracking with just a quick prompt.
- Alert retrieval and analysis: Have your agent fetch detailed information about recent alerts, surfacing critical changes on any monitored page instantly.
- Intelligent alert acknowledgment: Let your agent acknowledge and mark alerts as reviewed, helping your team stay organized and responsive.
- Site and category management: Organize your monitored properties by creating, updating, or deleting site categories to keep your web asset monitoring streamlined.
- Webhook automation: Set up or remove webhooks to automate notifications, ensuring you never miss an important website change event.

## Supported Tools

| Tool slug | Name | Description |
|---|---|---|
| `FLUXGUARD_ADD_PAGE` | Add FluxGuard Page | Tool to add a new page for monitoring in FluxGuard. This action can: 1. Create a new site with a page (when siteId/sessionId are not provided) 2. Add a page to an existing site (when siteId/sessionId are provided) When creating a new site, you can optionally assign it to categories and provide a nickname. Use this when you need to start monitoring a URL for changes. |
| `FLUXGUARD_CREATE_SITE_CATEGORY` | Create FluxGuard Site Category | Creates a new site category in FluxGuard for organizing monitored websites. Site categories help you group and manage your monitored sites logically (e.g., by environment like 'Production' or 'Staging', by purpose like 'Marketing' or 'E-commerce', or by client/team). Use this action to create categories before adding sites, making it easier to filter and organize your monitoring dashboard. The returned category ID can be used when adding sites to assign them to this category. |
| `FLUXGUARD_CREATE_WEBHOOK` | Create Webhook | Creates a webhook endpoint registration in FluxGuard to receive real-time notifications when changes are detected on monitored pages. When changes occur, FluxGuard will POST JSON data to your specified URL containing change details, diff information, and file references. Use this when you need to integrate FluxGuard change detection into your own systems, automation workflows, or alerting infrastructure. Note: Only one webhook can be active per account. Creating a new webhook will replace any existing webhook configuration. |
| `FLUXGUARD_DELETE_PAGE` | Delete Fluxguard Page | Permanently deletes a monitored page from FluxGuard along with all its captured snapshots and version history. This is a destructive operation that cannot be undone. Use this when you need to remove a page that is no longer needed for monitoring. The operation is idempotent - deleting an already-deleted page will succeed without error. To obtain the required IDs (site_id, session_id, page_id), first use FLUXGUARD_ADD_PAGE to create a page or FLUXGUARD_GET_SITES to list existing sites and their pages. |
| `FLUXGUARD_DELETE_SITE` | Delete Fluxguard Site | Permanently deletes a monitored site and all associated data including sessions, pages, and captured versions. This operation is idempotent - deleting a non-existent site returns success. Use when you need to remove a site from FluxGuard monitoring. |
| `FLUXGUARD_DELETE_WEBHOOK` | Delete Webhook | Permanently removes a webhook from your FluxGuard account by its ID. After deletion, the webhook will no longer receive notifications about monitored page changes. This operation is idempotent - deleting a non-existent webhook will succeed without error. Use this tool when you need to remove a webhook configuration that is no longer needed. |
| `FLUXGUARD_GET_ALL_CATEGORIES` | Get All FluxGuard Categories | Retrieves all categories defined in your FluxGuard account. Use this tool when you need to: - List all available categories for organizing sites or pages - Get category IDs for use in other operations - Check what categories exist before creating new ones This is a read-only operation that returns both site and page categories. No parameters are required - simply call this action to get all categories. |
| `FLUXGUARD_GET_PAGE_DATA` | Get FluxGuard Page Data | Tool to retrieve comprehensive data for a monitored page in FluxGuard. This action fetches detailed information about a specific page including its URL, monitoring status, capture history, and metadata. Use this when you need to verify a page exists, check its monitoring status, or retrieve page configuration details. The page must be identified by its site_id, session_id, and page_id, which are typically obtained from FLUXGUARD_ADD_PAGE when creating a page or from FLUXGUARD_GET_SITES when listing existing sites and their pages. |
| `FLUXGUARD_GET_SAMPLE_WEBHOOK` | Get Sample Webhook Payload | Tool to retrieve a sample webhook payload. Use when you need to inspect the structure of webhook notifications. |
| `FLUXGUARD_GET_USER` | Get Current FluxGuard Account | Retrieves the authenticated FluxGuard account's information as a user profile. Returns details about the current organization's account including ID, status, creation date, and last update timestamp. This provides account information in a user-friendly format for the authenticated API key's organization. |
| `FLUXGUARD_GET_WEBHOOKS` | Get FluxGuard Webhooks | Retrieves all configured webhooks for the FluxGuard account. Use this action to list all webhook endpoints that are configured to receive FluxGuard change notifications. Each webhook includes its URL, secret for signature verification, API version, and associated site categories. No parameters required - returns all webhooks for the authenticated account. |
| `FLUXGUARD_INITIATE_CRAWL` | Initiate FluxGuard Crawl | Tool to initiate a crawl for a session identified by siteId and sessionId. Use when you need to start monitoring a site for changes after adding pages with FLUXGUARD_ADD_PAGE. |
| `FLUXGUARD_WEBHOOK_NOTIFICATION` | Fluxguard Webhook Notification | Simulate Fluxguard webhook notification by sending change detection data to your webhook endpoint. Use this tool to test your webhook receiver implementation by sending it a properly formatted Fluxguard webhook payload with optional HMAC signature authentication. This helps verify your endpoint can receive and process Fluxguard change notifications correctly. Note: This does NOT retrieve data from Fluxguard or trigger actual monitoring - it only sends test notifications to your webhook URL. |

## Supported Triggers

None listed.

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

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

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

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 Fluxguard 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, fluxguard)
- 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 Fluxguard 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=["fluxguard"],
    )

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

  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 Fluxguard 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 Fluxguard
```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 Fluxguard, 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=["fluxguard"],
    )

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

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

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

## Related Toolkits

- [Excel](https://composio.dev/toolkits/excel) - Microsoft Excel is a robust spreadsheet application for organizing, analyzing, and visualizing data. It's the go-to tool for calculations, reporting, and flexible data management.
- [21risk](https://composio.dev/toolkits/_21risk) - 21RISK is a web app built for easy checklist, audit, and compliance management. It streamlines risk processes so teams can focus on what matters.
- [Abstract](https://composio.dev/toolkits/abstract) - Abstract provides a suite of APIs for automating data validation and enrichment tasks. It helps developers streamline workflows and ensure data quality with minimal effort.
- [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.
- [Agenty](https://composio.dev/toolkits/agenty) - Agenty is a web scraping and automation platform for extracting data and automating browser tasks—no coding needed. It streamlines data collection, monitoring, and repetitive online actions.
- [Ambee](https://composio.dev/toolkits/ambee) - Ambee is an environmental data platform providing real-time, hyperlocal APIs for air quality, weather, and pollen. Get precise environmental insights to power smarter decisions in your apps and workflows.
- [Ambient weather](https://composio.dev/toolkits/ambient_weather) - Ambient Weather is a platform for personal weather stations with a robust API for accessing local, real-time, and historical weather data. Get detailed environmental insights directly from your own sensors for smarter apps and automations.
- [Anonyflow](https://composio.dev/toolkits/anonyflow) - Anonyflow is a service for encryption-based data anonymization and secure data sharing. It helps organizations meet GDPR, CCPA, and HIPAA data privacy compliance requirements.
- [Api ninjas](https://composio.dev/toolkits/api_ninjas) - Api ninjas offers 120+ public APIs spanning categories like weather, finance, sports, and more. Developers use it to supercharge apps with real-time data and actionable endpoints.
- [Api sports](https://composio.dev/toolkits/api_sports) - Api sports is a comprehensive sports data platform covering 2,000+ competitions with live scores and 15+ years of stats. Instantly access up-to-date sports information for analysis, apps, or chatbots.
- [Apify](https://composio.dev/toolkits/apify) - Apify is a cloud platform for building, deploying, and managing web scraping and automation tools called Actors. It lets you automate data extraction and workflow tasks at scale—no infrastructure headaches.
- [Autom](https://composio.dev/toolkits/autom) - Autom is a lightning-fast search engine results data platform for Google, Bing, and Brave. Developers use it to access fresh, low-latency SERP data on demand.
- [Beaconchain](https://composio.dev/toolkits/beaconchain) - Beaconchain is a real-time analytics platform for Ethereum 2.0's Beacon Chain. It provides detailed insights into validators, blocks, and overall network performance.
- [Big data cloud](https://composio.dev/toolkits/big_data_cloud) - BigDataCloud provides APIs for geolocation, reverse geocoding, and address validation. Instantly access reliable location intelligence to enhance your applications and workflows.
- [Bigpicture io](https://composio.dev/toolkits/bigpicture_io) - BigPicture.io offers APIs for accessing detailed company and profile data. Instantly enrich your applications with up-to-date insights on 20M+ businesses.
- [Bitquery](https://composio.dev/toolkits/bitquery) - Bitquery is a blockchain data platform offering indexed, real-time, and historical data from 40+ blockchains via GraphQL APIs. Get unified, reliable access to complex on-chain data for analytics, trading, and research.
- [Brightdata](https://composio.dev/toolkits/brightdata) - Brightdata is a leading web data platform offering advanced scraping, SERP APIs, and anti-bot tools. It lets you collect public web data at scale, bypassing blocks and friction.
- [Builtwith](https://composio.dev/toolkits/builtwith) - BuiltWith is a web technology profiler that uncovers the technologies powering any website. Gain actionable insights into analytics, hosting, and content management stacks for smarter research and lead generation.
- [Byteforms](https://composio.dev/toolkits/byteforms) - Byteforms is an all-in-one platform for creating forms, managing submissions, and integrating data. It streamlines workflows by centralizing form data collection and automation.
- [Cabinpanda](https://composio.dev/toolkits/cabinpanda) - Cabinpanda is a data collection platform for building and managing online forms. It helps streamline how you gather, organize, and analyze responses.

## Frequently Asked Questions

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

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

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

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

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