# How to integrate Neutrino MCP with LlamaIndex

```json
{
  "title": "How to integrate Neutrino MCP with LlamaIndex",
  "toolkit": "Neutrino",
  "toolkit_slug": "neutrino",
  "framework": "LlamaIndex",
  "framework_slug": "llama-index",
  "url": "https://composio.dev/toolkits/neutrino/framework/llama-index",
  "markdown_url": "https://composio.dev/toolkits/neutrino/framework/llama-index.md",
  "updated_at": "2026-05-12T10:20:03.375Z"
}
```

## Introduction

This guide walks you through connecting Neutrino to LlamaIndex using the Composio tool router. By the end, you'll have a working Neutrino agent that can detect profanity in user-submitted comments, convert 50 usd to eur instantly, geocode address to get latitude and longitude through natural language commands.
This guide will help you understand how to give your LlamaIndex agent real control over a Neutrino account through Composio's Neutrino MCP server.
Before we dive in, let's take a quick look at the key ideas and tools involved.

## Also integrate Neutrino with

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

The Neutrino MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Neutrino account. It provides structured and secure access to Neutrino’s robust suite of APIs, so your agent can validate data, analyze geolocations, assess security risks, convert currencies, and clean content automatically on your behalf.
- Real-time data validation and analysis: Have your agent validate email addresses, check mobile numbers, and analyze BIN (bank identification numbers) for accuracy and reliability.
- Geolocation and address intelligence: Ask your agent to geocode addresses to coordinates, or perform reverse geocoding to turn latitude and longitude into real-world locations for smarter workflows.
- Content safety and cleaning: Let your agent scan text for profanity using the Bad Word Filter or sanitize untrusted HTML to ensure safe, presentable content anywhere it’s needed.
- Security and risk assessment: Automate reputation checks on hosts and domains, enabling your agent to proactively identify potential threats or block risky sources without manual effort.
- Currency and unit conversion: Empower your agent to convert between different units or currencies on demand, streamlining financial or scientific operations with ease.

## Supported Tools

| Tool slug | Name | Description |
|---|---|---|
| `NEUTRINO_ADD_WATERMARK_TO_IMAGE` | Add Watermark to Image | Add a watermark to an image with customizable position, opacity, and output format. Use when you need to overlay a logo, text image, or branding on photos or graphics. Supports resizing the output and multiple positioning options. |
| `NEUTRINO_BAD_WORD_FILTER` | Bad Word Filter | Tool to detect bad words and profanity in text. Use when scanning content for swear words. |
| `NEUTRINO_BIN_LOOKUP` | BIN Lookup | Perform a BIN (Bank Identification Number) lookup to retrieve comprehensive card issuer information. This tool identifies the card brand (VISA, MASTERCARD, AMEX, etc.), card type (debit/credit), issuer details, and issuer country from the first 6-8 digits of a card number. Optionally performs fraud detection by comparing the customer's IP geolocation with the card issuer country. Use cases: - Payment fraud detection and prevention - Card validation before processing transactions - Geographic risk assessment for e-commerce - Card type identification for routing payments The database contains ~2.5 million BIN records covering all major card issuers globally and is updated weekly. |
| `NEUTRINO_CHECK_IP_BLOCKLIST` | IP Blocklist | Check if an IP address is on a blocklist. Detect IPs associated with malware, anonymous proxies, TOR exit nodes, botnets, spam sources and malicious servers. Use when you need to verify if an IP address is known to be malicious or part of a threat network. |
| `NEUTRINO_CONVERT` | Convert Value | Tool to perform unit and currency conversions. Use when you need to convert a value from one unit or currency to another. Example: convert 100 USD to EUR. |
| `NEUTRINO_EMAIL_VALIDATE` | Validate and analyze an email address | Validates and analyzes email addresses for syntax, domain validity, DNS/MX records, and detects freemail/disposable providers. This tool performs comprehensive email validation including: - RFC822/RFC2822 syntax compliance checking - Domain existence and DNS verification - Mail exchange (MX) record validation - Detection of free email providers (Gmail, Yahoo, etc.) - Identification of disposable/temporary email services - Optional automatic typo correction for common domain mistakes Important: This does NOT verify if a specific email address/mailbox actually exists with the provider. For mailbox verification, use the EMAIL_VERIFY action instead. Use this tool when you need to validate email addresses before sending, check email quality, or filter out disposable addresses. |
| `NEUTRINO_EMAIL_VERIFY` | Verify Email Address | Tool to verify and analyze the deliverability of an email address. Use when you need SMTP-based validation before sending emails. |
| `NEUTRINO_GEOCODE_ADDRESS` | Geocode Address | Tool to geocode an address. Use when you need geographic coordinates for an address or place name. |
| `NEUTRINO_GEOCODE_REVERSE` | Reverse Geocode | Convert geographic coordinates (latitude/longitude) into real-world address information. Returns comprehensive location data including formatted addresses, administrative boundaries, timezone information, and location metadata. Useful for translating GPS coordinates into human-readable locations or enriching location data with regional details. The zoom parameter controls detail level: 'address' returns building-level precision, while 'city' or 'country' returns broader geographic information. |
| `NEUTRINO_HLR_LOOKUP` | HLR Lookup | Perform real-time HLR (Home Location Register) lookup to validate mobile numbers and retrieve detailed network information. This tool connects to the global mobile cellular network to check if a mobile number is active, registered, and reachable. It provides comprehensive details including carrier information, porting status, roaming status, and network identifiers (MCC, MNC, IMSI). Use this tool to: - Validate that a mobile number is currently active and registered on a network - Determine the current carrier and check if a number has been ported - Check device reachability and roaming status in real-time - Retrieve mobile network identifiers (MCC, MNC, IMSI) for telecom operations Note: Numbers must be in international format (e.g., +447911123456) or provide a country-code parameter. |
| `NEUTRINO_HOST_REPUTATION` | Host Reputation | Check if an IP address, domain, or URL is listed on DNS-based Blackhole Lists (DNSBLs). DNSBLs track IPs and domains associated with spam, malware, proxies, and other malicious activity. This action queries 150+ DNSBLs to determine if a host has a bad reputation. Useful for: - Email spam filtering and sender reputation checks - Security threat assessment - Identifying compromised or malicious hosts Note: This performs realtime DNS lookups and may take 5-20 seconds to complete. |
| `NEUTRINO_HTML_CLEAN` | HTML Clean | Tool to clean and sanitize untrusted HTML. Use when you need to strip or neutralize unwanted tags and attributes before rendering. |
| `NEUTRINO_HTML_RENDER` | HTML Render | Render HTML content to PDF, PNG, or JPG format. Converts HTML strings or URLs into downloadable files with extensive customization options including page size, margins, headers/footers, and JavaScript execution. |
| `NEUTRINO_IMAGE_RESIZE` | Resize Image | Resize, crop, and convert images to PNG or JPG format. Supports multiple resize modes (scale to preserve aspect ratio, pad with background color, or crop). Use when you need to adjust image dimensions, change format, or prepare images for specific size requirements. Supports GIF, ICO, JPEG, PNG, and TIFF input formats. |
| `NEUTRINO_IP_INFO` | IP Info | Get comprehensive geolocation and network information for an IPv4 or IPv6 address. Returns location data (country, region, city, coordinates), timezone information, and optionally reverse DNS hostname. Does NOT include VPN/proxy detection or user-agent parsing. For VPN detection, use the IP Probe action instead. |
| `NEUTRINO_IP_PROBE` | IP Probe | Analyzes an IPv4 or IPv6 address to extract detailed network intelligence including geolocation, ISP/hosting provider information, ASN details, and security flags (VPN, proxy, TOR detection). Performs live network scanning and service probes. Use when you need comprehensive IP address analysis beyond basic geolocation. |
| `NEUTRINO_LOOKUP_DOMAIN` | Domain Lookup | Tool to perform a domain lookup to retrieve WHOIS, DNS records, domain registration information and detect potentially malicious or dangerous domains. Use when you need to assess domain reputation, check for security threats, or gather comprehensive domain intelligence. |
| `NEUTRINO_PHONE_VALIDATE` | Phone Validate | Tool to validate and lookup phone numbers. Use when you need to confirm number format and fetch location, carrier, and type details. |
| `NEUTRINO_QR_CODE` | QR Code | Generate a QR code or Code 128 barcode as a PNG image. Use when you need to encode URLs, text, phone numbers, or other data into a scannable code. Examples: Create QR code for a website URL, encode contact information, generate barcode for product tracking. |
| `NEUTRINO_RUN_BROWSER_BOT` | Browser Bot | Tool to automate browser interactions using a real Chromium browser. Use when you need to extract content, fill forms, capture screenshots, or navigate complex JavaScript-heavy websites. |
| `NEUTRINO_SMS_VERIFY` | SMS Verify | Tool to send a unique security code via SMS. Use when verifying a user's phone number after collection. |
| `NEUTRINO_UA_LOOKUP` | UA Lookup | Parse and analyze User-Agent strings to extract detailed browser, device, and operating system information. Returns device type (desktop/phone/tablet/robot), browser name and version, OS details, device specifications (brand, model, screen resolution, price), and indicators for mobile devices, webviews, and frozen User-Agents. Supports both traditional UA strings and modern User-Agent Client Hints. |
| `NEUTRINO_URL_INFO` | URL Info | Tool to parse, analyze, and retrieve content from the supplied URL. Use when you need detailed URL metadata or to fetch page content. |
| `NEUTRINO_VERIFY_SECURITY_CODE` | Verify Security Code | Verify a security code generated by SMS Verify or Phone Verify APIs. Use this after sending a security code via SMS or phone call to validate that the user provided the correct code. Codes expire after 15 minutes. The verification must use the same API credentials that generated the code. |

## Supported Triggers

None listed.

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

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

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

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 Neutrino 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, neutrino)
- 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 Neutrino 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=["neutrino"],
    )

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

  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 Neutrino 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 Neutrino
```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 Neutrino, 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=["neutrino"],
    )

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

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

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

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

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

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

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