# How to integrate Ipinfo io MCP with LlamaIndex

```json
{
  "title": "How to integrate Ipinfo io MCP with LlamaIndex",
  "toolkit": "Ipinfo io",
  "toolkit_slug": "ipinfo_io",
  "framework": "LlamaIndex",
  "framework_slug": "llama-index",
  "url": "https://composio.dev/toolkits/ipinfo_io/framework/llama-index",
  "markdown_url": "https://composio.dev/toolkits/ipinfo_io/framework/llama-index.md",
  "updated_at": "2026-05-12T10:16:20.672Z"
}
```

## Introduction

This guide walks you through connecting Ipinfo io to LlamaIndex using the Composio tool router. By the end, you'll have a working Ipinfo io agent that can get geolocation details for this ip address, check if this ip is using a vpn or proxy, find the company behind this ip address through natural language commands.
This guide will help you understand how to give your LlamaIndex agent real control over a Ipinfo io account through Composio's Ipinfo io MCP server.
Before we dive in, let's take a quick look at the key ideas and tools involved.

## Also integrate Ipinfo io with

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

The Ipinfo io MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Ipinfo io account. It provides structured and secure access to IP address intelligence, so your agent can perform actions like geolocating IPs, retrieving company and carrier details, detecting privacy risks, and fetching abuse contacts automatically.
- Bulk IP address lookups: Perform high-volume geolocation or information retrieval for up to 1,000 IPs or URLs in a single request for audits, analytics, or security reviews.
- Comprehensive IP geolocation and details: Instantly fetch precise geolocation, ASN, and network data for any IP address—including your own—helping with network diagnostics and user profiling.
- Company and carrier information retrieval: Ask your agent to identify the organization or mobile carrier behind an IP address for enhanced business intelligence or fraud analysis.
- Abuse contact identification: Quickly retrieve the correct abuse reporting contact for any IP, streamlining incident response or reporting suspicious activity.
- Privacy and anonymization detection: Let your agent check if an IP is using VPNs, proxies, Tor, or hosting services to identify anonymized or risky traffic for extra security and compliance.

## Supported Tools

| Tool slug | Name | Description |
|---|---|---|
| `IPINFO_IO_BATCH_LITE_LOOKUP` | Batch Lite Lookup | Perform bulk Lite IP lookups for up to 1000 IPs in a single request. Returns lightweight IP information including ASN (Autonomous System Number), AS organization details, and geolocation (country and continent). Use cases: - Look up geolocation for multiple IPs at once - Identify the ISP/organization owning IP addresses - Detect bogon/private IPs (192.168.x.x, 10.x.x.x, etc.) - Retrieve specific fields only (e.g., '8.8.8.8/country' returns just the country) Supports both IPv4 and IPv6 addresses. |
| `IPINFO_IO_BATCH_LOOKUP` | Batch IP Lookup | Perform batch IP lookups to retrieve geolocation and ASN information for multiple IPs in a single request. Use this tool when you need to look up multiple IP addresses efficiently. Supports up to 1000 IPs per request. IMPORTANT: For free tier API tokens, prefix each IP with 'lite/' (e.g., 'lite/8.8.8.8'). Bare IPs without the 'lite/' prefix require a paid subscription. |
| `IPINFO_IO_GET_ABUSE_CONTACT` | Get Abuse Contact | Retrieve abuse contact and organization information for an IP address. Use this tool when you need to identify who owns an IP address or find contact information for reporting malicious activity. Note: Full abuse contact details (email, phone, name) require IPinfo Enterprise tier. For standard tiers, returns organization info (org, country, city, region) which can be used to identify the IP owner. |
| `IPINFO_IO_GET_CARRIER_INFO` | Get IP Carrier Info | Retrieves mobile carrier information for a given IP address. Returns the carrier name, Mobile Country Code (MCC), and Mobile Network Code (MNC) for mobile network IPs. For non-mobile IPs (e.g., datacenter, ISP), returns the organization/ASN name with empty MCC/MNC values. Useful for identifying if an IP belongs to a mobile carrier network and which carrier it is. |
| `IPINFO_IO_GET_CITY_BY_IP` | Get City by IP | Retrieve the city name for a specific IP address. Returns the city name as plain text for any IPv4 or IPv6 address. |
| `IPINFO_IO_GET_COMPANY_INFO` | Get Company Info for an IP | Retrieve company/organization information for an IP address. Returns the company name, domain, and type (business, ISP, hosting, etc.) associated with the IP. Supports both IPv4 and IPv6 addresses. |
| `IPINFO_IO_GET_CORE_FIELD_BY_ME` | Get Core Field by Me | Retrieve a specific field from core IP information about the current IP. Use this tool when you need just one specific piece of information (like city, country, hostname, or AS details) about the caller's IP address instead of fetching the complete IP profile. |
| `IPINFO_IO_GET_COUNTRY_BY_IP` | Get Country by IP | Retrieve the two-letter ISO 3166 country code for an IP address. Use when you need to quickly identify which country an IP address is located in without requesting full geolocation details. |
| `IPINFO_IO_GET_CURRENT_IP` | Get Current IP | Retrieve the current public/external IP address. Use this tool when you need to determine the caller's public IP address. |
| `IPINFO_IO_GET_CURRENT_IP_INFO` | Get Current IP Information | Retrieve comprehensive IP information about the caller's current IP address. Returns geolocation (city, region, country, coordinates, postal code, timezone), ASN details, company info, privacy detection flags (VPN/proxy/Tor), carrier info for mobile IPs, and abuse contact information. Use this when you need to identify and analyze the caller's IP address without specifying an IP parameter. |
| `IPINFO_IO_GET_CURRENT_LOC` | Get Current Location | Retrieve geographic coordinates for the current IP address. Returns the latitude and longitude of the caller's IP address as a comma-separated string in the format 'latitude,longitude'. Use this when you need quick location coordinates without full geolocation details. |
| `IPINFO_IO_GET_CURRENT_REGION` | Get Current Region | Retrieve the region/state for the caller's current IP address. Use this tool when you need to identify the geographic region or state where the current IP address is located. Returns a plain text region name. |
| `IPINFO_IO_GET_GEO_BY_IP` | Get Geo by IP | Get geolocation data only for an IP address. Returns city, region, country, continent, coordinates, timezone, and postal code. Use this when you need detailed geographic location information for an IP address. |
| `IPINFO_IO_GET_HOSTNAME_BY_IP` | Get Hostname by IP | Retrieve the hostname (reverse DNS) for an IP address. Use this tool to look up the hostname associated with any IPv4 or IPv6 address. Returns the hostname as a string. If no hostname is available, returns an empty string. |
| `IPINFO_IO_GET_IP_BY_IP` | Get IP by IP | Retrieve the IP address for a specified IP as plain text. Use this tool to echo back an IP address from the IPInfo API. This endpoint returns the IP address as plain text (not JSON). Useful for verifying IP address formatting or testing connectivity. |
| `IPINFO_IO_GET_IP_INFO` | Get IP Information | Retrieve geolocation and ASN information for an IP address. Use this tool to look up country, continent, and Autonomous System (AS) details for any IPv4 or IPv6 address. Pass 'me' or omit the ip parameter to get information about the caller's own IP address. For private/reserved (bogon) IP addresses like 192.168.x.x or 10.x.x.x, only the ip and bogon fields will be populated. |
| `IPINFO_IO_GET_IP_INFO_BY_IP` | Get Comprehensive IP Information | Retrieve comprehensive information about a specified IP address. Returns geographic location (city, region, country, coordinates), ASN details, company/organization info, privacy detection flags (VPN, proxy, Tor), carrier information for mobile IPs, and associated domain names. Supports both IPv4 and IPv6 addresses. |
| `IPINFO_IO_GET_LITE_FIELD_BY_IP` | Get Lite Field By IP | Retrieve a specific field from lightweight IP information. Use this tool to get a single piece of information about an IP address (e.g., just the country, or just the ASN) without fetching the full IP data. This is more efficient when you only need one specific field. Supported fields: ip, asn, as_name, as_domain, country_code, country, continent_code, continent. |
| `IPINFO_IO_GET_LOCATION_BY_IP` | Get Location by IP | Retrieve geographic coordinates (latitude, longitude) for an IP address. Returns location as comma-separated text in the format 'latitude,longitude'. Use when you need precise geolocation coordinates for IPv4 or IPv6 addresses. |
| `IPINFO_IO_GET_ORG_BY_IP` | Get Organization by IP | Retrieve ASN and organization name for an IP address as plain text. Use this tool when you need to quickly identify which organization or ASN owns a specific IP address. Returns a plain text string containing the Autonomous System Number (ASN) and organization name (e.g., 'AS15169 Google LLC'). |
| `IPINFO_IO_GET_PLUS_FIELD_BY_ME` | Get Plus Field for Current IP | Retrieve a specific field from plus IP information about the current IP. Use this tool to get individual fields from IPInfo's Plus API for your current IP address. This includes detailed geographic data (city, region, coordinates), AS information, mobile carrier details, and privacy flags. Each field returns its specific data type (string, number, boolean, or object). Note: This endpoint requires a Plus API subscription. Returns 403 if the subscription doesn't include Plus features. |
| `IPINFO_IO_GET_POSTAL_BY_IP` | Get Postal Code by IP | Retrieve the postal/zip code for an IP address. Use this when you need to identify the geographic postal code associated with an IPv4 or IPv6 address. |
| `IPINFO_IO_GET_PRIVACY_DETAILS` | Get IP Privacy Details | Retrieve privacy/anonymous IP detection flags for an IP address. Returns whether the IP is associated with VPN, proxy, Tor, relay, or hosting services. Use this to detect potentially anonymous or masked traffic from an IP address. Note: This endpoint requires a Privacy Detection API subscription. If privacy data is unavailable for your subscription level, the action will return default values (all flags set to False). |
| `IPINFO_IO_GET_REGION_BY_IP` | Get Region by IP | Retrieve the region/state for a specified IP address. Use this tool when you need to identify the geographic region or state where a specific IPv4 or IPv6 address is located. Returns a plain text region name. |
| `IPINFO_IO_GET_TIMEZONE_BY_IP` | Get Timezone by IP | Retrieve the IANA timezone for a given IP address. Use this tool when you need to determine the local timezone of an IP address location for scheduling, time conversion, or geographic analysis purposes. |
| `IPINFO_IO_GET_TOKEN_INFO` | Get Token Information | Retrieve API service request limit information by access token. Returns usage statistics, request limits, remaining quota, and available API features. Use this to check your token's rate limits, current usage, and feature access before making other API calls. |
| `IPINFO_IO_MAP_IPS` | Map IP Addresses | Create an IPinfo map visualization from a list of IP addresses. Use this tool to generate an interactive map showing the geographic locations of multiple IP addresses. The tool accepts up to 500,000 IPs and returns a link to a visual map where all IP locations are plotted. Useful for visualizing the geographic distribution of network traffic, analyzing user locations, or investigating security incidents across multiple IP addresses. |

## Supported Triggers

None listed.

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

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

### 1. Getting API Keys for OpenAI, Composio, and Ipinfo io

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 Ipinfo io 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, ipinfo io)
- 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 Ipinfo io 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=["ipinfo_io"],
    )

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

  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 Ipinfo io 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 Ipinfo io
```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 Ipinfo io, 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=["ipinfo_io"],
    )

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

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

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

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

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

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

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