# How to integrate Radar MCP with LlamaIndex

```json
{
  "title": "How to integrate Radar MCP with LlamaIndex",
  "toolkit": "Radar",
  "toolkit_slug": "radar",
  "framework": "LlamaIndex",
  "framework_slug": "llama-index",
  "url": "https://composio.dev/toolkits/radar/framework/llama-index",
  "markdown_url": "https://composio.dev/toolkits/radar/framework/llama-index.md",
  "updated_at": "2026-05-12T10:23:13.738Z"
}
```

## Introduction

This guide walks you through connecting Radar to LlamaIndex using the Composio tool router. By the end, you'll have a working Radar agent that can autocomplete address based on partial input, get users currently inside geofence, convert address to latitude and longitude through natural language commands.
This guide will help you understand how to give your LlamaIndex agent real control over a Radar account through Composio's Radar MCP server.
Before we dive in, let's take a quick look at the key ideas and tools involved.

## Also integrate Radar with

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

The Radar MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Radar account. It provides structured and secure access to advanced location services, so your agent can perform actions like geocoding addresses, managing geofences, tracking trips, searching places, and retrieving location context on your behalf.
- Address and place autocomplete: Instantly get relevant address or place suggestions based on partial user input, improving data quality and user experience.
- Precise geocoding and location context: Convert full addresses to latitude/longitude and fetch rich context—including region, geofence, and place details—for any set of coordinates.
- Geofence management: Retrieve, create, or delete geofences to define dynamic boundaries and monitor activity within specific areas automatically.
- Trip creation and tracking: Start, fetch, or delete trips to enable real-time location tracking and trip management for devices or users.
- Live user monitoring in geofences: Effortlessly list all users currently inside a defined geofence, supporting presence-based automation and analytics.

## Supported Tools

| Tool slug | Name | Description |
|---|---|---|
| `RADAR_AUTOCOMPLETE_ADDRESS_OR_PLACE` | Autocomplete Address or Place | Tool to autocomplete partial addresses and place names based on relevance and proximity. Use after a user inputs a partial address/place to get suggestions, optionally biased by location. |
| `RADAR_CREATE_BEACON` | Create Beacon | Tool to create a new beacon in Radar. Use when you need to register a physical beacon device (iBeacon or Eddystone) for location tracking. |
| `RADAR_CREATE_TRIP` | Create Trip | Tool to create a new trip. Use after gathering origin and destination details to start tracking a trip. |
| `RADAR_DELETE_BEACON` | Delete Beacon | Tool to delete a beacon by its Radar ID. Use when supplying a beacon's unique identifier to remove it. |
| `RADAR_DELETE_GEOFENCE` | Delete Geofence | Tool to delete a geofence by ID. Use when supplying a geofence’s unique identifier to remove it. |
| `RADAR_DELETE_GEOFENCE_BY_TAG` | Delete Geofence By Tag | Tool to delete a geofence by tag and external ID. Use when you have both the tag and external identifier to remove a specific geofence. |
| `RADAR_DELETE_TRIP` | Delete Trip | Tool to delete a trip by its Radar ID or external ID. Use after confirming the trip exists. |
| `RADAR_DELETE_USER` | Delete User | Tool to delete a user by Radar _id, userId, or deviceId. Use after confirming the user identifier exists. |
| `RADAR_FORWARD_GEOCODE` | Forward Geocode | Tool to convert an address into geographic coordinates. Use when you have a full address string and need precise latitude/longitude before further location analysis. |
| `RADAR_GET_BEACON` | Get Beacon | Tool to retrieve a beacon by Radar _id. Use when you need to fetch full details of an existing beacon. |
| `RADAR_GET_BEACON_BY_TAG` | Get Beacon By Tag | Tool to get a specific beacon by tag and external ID. Use when you need to retrieve details of a beacon identified by its tag group and external ID. |
| `RADAR_GET_CONTEXT_FOR_LOCATION` | Get Context for Location | Tool to retrieve context for a given location. Use when you need geofences, place, and region information based on coordinates. Use after obtaining valid latitude and longitude. |
| `RADAR_GET_GEOFENCE` | Get Geofence | Tool to retrieve a geofence by Radar _id or tag/externalId. Use when you need to fetch full details of an existing geofence. |
| `RADAR_GET_PLACES_SETTINGS` | Get Places Settings | Tool to retrieve current Places settings for your Radar project. Use when you need to inspect chain detection, supported countries, external ID requirements, and other Places metadata. |
| `RADAR_GET_ROUTE_DIRECTIONS` | Get Route Directions | Tool to get turn-by-turn directions between multiple locations. Use when you need detailed navigation instructions with steps, distances, and durations for routing. |
| `RADAR_GET_ROUTE_MATRIX` | Get Route Matrix | Tool to calculate travel distance and duration between multiple origins and destinations for up to 625 routes. Use when you need to compute route metrics for multiple origin-destination pairs efficiently. |
| `RADAR_GET_TRIP` | Get Trip | Tool to retrieve a trip by ID or externalId. Use when you have a trip ID or externalId to fetch its details. |
| `RADAR_GET_USER` | Get User | Tool to get a user by Radar _id, userId, or deviceId. Returns the user with all location and context data including geofences, places, beacons, and trip information. |
| `RADAR_GET_USERS_IN_GEOFENCE` | Get Users in Geofence | Tool to retrieve users currently within a specific geofence. Use when you need to list all users inside a geofence by its tag and external ID. |
| `RADAR_IP_GEOCODE` | IP Geocode | Tool to geocode an IP address to city, state, and country. Use when you need location details based on an IP address. |
| `RADAR_LIST_EVENTS` | List Events | Tool to list events. Use when you need to retrieve a paginated list of events with optional filtering. |
| `RADAR_LIST_GEOFENCES` | List Geofences | Tool to list all geofences sorted by updated time. Use when you need an overview of all configured geofences. |
| `RADAR_LIST_TRIPS` | List Trips | Tool to list all trips, sorted by updated time. Use when you need to page through the latest trips. |
| `RADAR_LIST_USERS` | List Users | Tool to list Radar users sorted by update time. Use when you need to page through users in your project. |
| `RADAR_REVERSE_GEOCODE` | Reverse Geocode | Tool to convert geographic coordinates to structured addresses. Use when you have latitude/longitude and need a human-readable address. |
| `RADAR_ROUTE_DISTANCE` | Route Distance | Tool to compute distance and travel time between origins and destinations. Use when you need route metrics before optimizing or timing routes. |
| `RADAR_SEARCH_GEOFENCES_NEAR_LOCATION` | Search Geofences | Tool to search for geofences near a given location. Use when you need to find geofences within a radius of specified coordinates. |
| `RADAR_SEARCH_PLACES_NEAR_LOCATION` | Search Places Near Location | Tool to search for places near given coordinates. Use when you need to find points of interest around a location. |
| `RADAR_SEARCH_USERS_NEAR_LOCATION` | Search Users Near Location | Tool to search for users near a location. Use after obtaining coordinates when you need to retrieve users within a given radius. |
| `RADAR_TRACK_LOCATION_UPDATE` | Track Location Update | Tool to track a user's location update. Use when sending a location update for a user, creating or updating user and event data. |
| `RADAR_UPDATE_PLACES_SETTINGS` | Update Places Settings | Tool to update Places settings for your Radar project including chain metadata preferences. Use when you need to configure chain detection or other Places settings. |
| `RADAR_UPDATE_TRIP` | Update Trip | Tool to update a trip. Use when you need to modify mode, destination, schedule, or active status. |
| `RADAR_UPDATE_TRIP_BY_ID` | Update Trip By ID | Tool to update a trip status by Radar _id or external ID. Use when you need to change trip status to started, approaching, arrived, completed, or canceled. |
| `RADAR_UPSERT_BEACON_BY_ID` | Upsert Beacon by ID | Tool to create or update a beacon by Radar _id. Use when you need to ensure a beacon with a specific ID exists with updated properties. |
| `RADAR_UPSERT_BEACON_BY_TAG` | Upsert Beacon by Tag | Tool to create or update a beacon by tag and externalId. Use when you need to ensure a beacon exists or is updated with specific identifiers. |
| `RADAR_UPSERT_GEOFENCE` | Upsert Geofence | Tool to create or update a geofence by tag and externalId. Use when ensuring a geofence exists or is updated based on identifiers. |
| `RADAR_UPSERT_GEOFENCE_BY_ID` | Upsert Geofence By ID | Tool to create or update a geofence by Radar _id. Use when you need to upsert a geofence using its internal Radar identifier. |

## Supported Triggers

None listed.

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

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

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

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 Radar 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, radar)
- 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 Radar 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=["radar"],
    )

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

  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 Radar 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 Radar
```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 Radar, 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=["radar"],
    )

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

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

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

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

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

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

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