# How to integrate Fly MCP with LlamaIndex

```json
{
  "title": "How to integrate Fly MCP with LlamaIndex",
  "toolkit": "Fly",
  "toolkit_slug": "fly",
  "framework": "LlamaIndex",
  "framework_slug": "llama-index",
  "url": "https://composio.dev/toolkits/fly/framework/llama-index",
  "markdown_url": "https://composio.dev/toolkits/fly/framework/llama-index.md",
  "updated_at": "2026-03-29T06:34:13.821Z"
}
```

## Introduction

This guide walks you through connecting Fly to LlamaIndex using the Composio tool router. By the end, you'll have a working Fly agent that can deploy latest image to fly in tokyo, list all running fly apps by region, scale up your fly app to 3 instances through natural language commands.
This guide will help you understand how to give your LlamaIndex agent real control over a Fly account through Composio's Fly MCP server.
Before we dive in, let's take a quick look at the key ideas and tools involved.

## Also integrate Fly with

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

The Fly MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Fly account. It provides structured and secure access so your agent can perform Fly operations on your behalf.

## Supported Tools

| Tool slug | Name | Description |
|---|---|---|
| `FLY_ADD_WIRE_GUARD_PEER` | Add WireGuard Peer | Tool to add a WireGuard peer connection to a Fly.io organization for private network access. Use when setting up VPN access or private networking between your infrastructure and Fly.io. |
| `FLY_CHECK_APP_NAME_AVAILABILITY` | Check App Name Availability | Tool to validate an app name for Fly.io app creation. Use when you need to check if a proposed app name is available before attempting to create a new app. Returns availability status via GraphQL query. |
| `FLY_CHECK_JOBS` | Check Jobs | Execute GraphQL queries against the Fly.io checkJobs endpoint. Retrieves check jobs with their schedules, URLs, and configuration. Supports pagination via first/last/after/before parameters. Returns both data and errors for flexible error handling. |
| `FLY_CHECK_USER_ONLY_TOKEN` | Check User Only Token | Check whether the authentication token only allows user access. Returns false if the token allows organization access, true if it only allows user access. |
| `FLY_CREATE_HEALTH_CHECK_JOB` | Create Health Check Job | Tool to create a health check job for monitoring application endpoints in Fly.io. Use when you need to set up automated health monitoring for a URL from multiple geographic locations. |
| `FLY_CREATE_CHECK_JOB_RUN` | Create Check Job Run | Triggers a run of an existing health check job on Fly.io. Use when you need to manually trigger a health check for monitoring or testing purposes. |
| `FLY_CREATE_DELEGATED_WIREGUARD_TOKEN` | Create Delegated WireGuard Token | Tool to create a delegated WireGuard token for peer management in a Fly.io organization. Use when you need to generate a token for managing WireGuard peers with delegated access. |
| `FLY_CREATE_THIRD_PARTY_CONFIGURATION` | Create Third-Party Configuration | Tool to create a third-party service configuration for discharging macaroon caveats. Use when you need to configure external authorization services for Fly.io token validation. |
| `FLY_DELETE_DELEGATED_WIREGUARD_TOKEN` | Delete Delegated WireGuard Token | Tool to delete a delegated WireGuard token from a Fly.io organization. Use when you need to revoke or remove an existing WireGuard token that was previously created. Either token or name must be provided to identify which token to delete. |
| `FLY_DELETE_ORGANIZATION` | Delete Organization | Tool to delete a Fly.io organization and all its associated resources using the GraphQL API. Use when you need to permanently remove an organization. This operation is irreversible. |
| `FLY_DELETE_REMOTE_BUILDER` | Delete Remote Builder | Tool to delete a remote builder configuration for a Fly.io organization. Use when you need to remove the remote builder setup from an organization. |
| `FLY_DELETE_THIRD_PARTY_CONFIGURATION` | Delete Third Party Configuration | Tool to delete a third-party service configuration from Fly.io. Use when you need to remove an existing third-party service integration or configuration that was previously created. |
| `FLY_DETACH_POSTGRES_CLUSTER` | Detach Postgres Cluster | Tool to detach a Postgres cluster from a Fly.io application, revoking access credentials. Use when you need to remove database connectivity from an application. |
| `FLY_ESTABLISH_SSH_KEY` | Establish SSH Key | Tool to establish an SSH key for a Fly.io organization. Use when setting up SSH access for secure connections to Fly.io infrastructure. |
| `FLY_FETCH_NODES_BY_IDS` | Fetch Nodes by IDs | Fetches a list of node objects from Fly.io given a list of IDs using the GraphQL nodes query. Use when you need to retrieve multiple objects by their IDs in a single request. Supports all Node interface types including Organization, App, Machine, Volume, and more. |
| `FLY_GET_ADD_ON` | Get Add-On | Tool to find a Fly.io add-on by ID, name, or provider. Use when you need to retrieve details about a specific add-on. Returns add-on information including status, organization, region, and access URLs. |
| `FLY_GET_ADD_ON_PROVIDER` | Get Add-On Provider | Tool to query information about a specific Fly.io add-on provider (extension) by name. Returns provider details including provisioning settings, terms of service, and configuration options. |
| `FLY_GET_APP_DETAILS` | Get app details | Tool to retrieve detailed information about a specific Fly.io application. Use when you need to get app details including certificates and configuration. |
| `FLY_GET_CERTIFICATE` | Get Certificate | Tool to retrieve a certificate by its ID from Fly.io. Use when you need to get details about a specific certificate including hostname, creation date, and configuration status. |
| `FLY_GET_CURRENT_TOKEN_INFO` | Get Current Token Info | Tool to get information about the current authentication token. Use when you need to retrieve details about the token being used for API authentication, including organizations, apps, and whether the token is from a user or machine. |
| `FLY_GET_LATEST_IMAGE_DETAILS` | Get Latest Image Details | Tool to retrieve the latest available tag details for a given image repository from Fly.io's registry. Use when you need to get digest, registry, repository, tag, and version information for a container image. |
| `FLY_GET_LATEST_IMAGE_TAG` | Get Latest Image Tag | Tool to retrieve the latest available image tag for a Fly.io Docker repository. Use when you need to find the most recent version of a Fly.io image. |
| `FLY_GET_MACHINE` | Get Machine | Tool to get a single machine by ID from Fly.io. Use when you need to retrieve details about a specific machine instance. |
| `FLY_GET_NEAREST_REGION` | Get Nearest Region | Tool to retrieve the nearest Fly.io region to the requesting client based on network location. Use when you need to determine which Fly.io region has the lowest latency from the current location. |
| `FLY_GET_NODE_BY_ID` | Get Node by ID | Tool to fetch an object by its globally unique ID using Fly.io's GraphQL node query. Returns a Node interface object with id and __typename fields. Use when you need to retrieve any Fly.io object by its ID. |
| `FLY_GET_ORGANIZATION` | Get Organization | Tool to find a Fly.io organization by slug using the GraphQL API. Use when you need to retrieve organization details including ID, name and slug. |
| `FLY_GET_PERSONAL_ORGANIZATION` | Get Personal Organization | Tool to retrieve the user's personal organization details from Fly.io. Use when you need to check credit balance, saved payment methods, certificates, or WireGuard peer information. |
| `FLY_GET_PLACEMENTS` | Get Placements | Tool to get placement recommendations for Machines in Fly.io regions. Use when you need to determine optimal regions for deploying machines based on resource requirements, volume constraints, and organizational limits. |
| `FLY_GET_PLATFORM_INFORMATION` | Get Platform Information | Tool to retrieve Fly.io platform information including available regions, VM sizes, and flyctl version. Use when you need infrastructure-level details about the Fly.io platform. |
| `FLY_GET_PRODUCTS_AND_PRICING` | Get Products and Pricing | Tool to retrieve Fly.io product and price information via GraphQL. Use when you need to fetch product catalog, pricing tiers, or billing information. |
| `FLY_GET_REGIONS` | Get Regions | Tool to get the list of available Fly.io regions with optional filtering. Use when you need to discover which regions are available for deploying machines, or to filter regions by specific resource requirements like CPU, memory, or GPU. |
| `FLY_GET_VIEWER_INFO` | Get Viewer Info | Tool to retrieve the authenticated user's account information from Fly.io. Use when you need to get the current user's profile details, including avatar, email, creation date, and feature flags. |
| `FLY_ISSUE_CERTIFICATE` | Issue Certificate | Tool to issue an SSH certificate for accessing Fly.io infrastructure. Returns an SSH certificate in OpenSSH format. Use when you need to authenticate SSH access to Fly.io machines or apps. |
| `FLY_LIST_ADD_ON_PLANS` | List Add-On Plans | Tool to list available add-on service plans from Fly.io. Use when you need to discover pricing, features, and resource limits for Fly.io add-on services. Supports cursor-based pagination. |
| `FLY_LIST_ADD_ONS` | List Add-Ons | Tool to list add-ons associated with an organization in Fly.io. Use when you need to retrieve add-ons for apps in an organization. Supports querying personal organization or specific organizations by slug. Returns comprehensive add-on details including status, creation date, and configuration. |
| `FLY_LIST_APPS` | List Apps | Tool to list all Fly Apps in an organization. Use when you need to retrieve apps for a specific organization using its slug. |
| `FLY_LIST_APPS_VIA_GRAPHQL` | List Apps via GraphQL | List all Fly.io applications with details including volumes, services, and VMs using GraphQL. Use when you need to retrieve a comprehensive overview of all apps in your Fly.io organization. |
| `FLY_CHECK_LOCATIONS` | Check Locations | Retrieve all available Fly.io health check locations. Returns a comprehensive list of global locations where health checks can be performed, including geographic details and coordinates. Use when you need to determine available monitoring points for setting up health checks. |
| `FLY_LIST_MACHINES` | List Machines | Tool to list Fly.io machines using GraphQL API with pagination support. Use when you need to retrieve information about deployed machines including their state, region, and creation time. |
| `FLY_LIST_ORGANIZATION_MACHINES` | List Organization Machines | Tool to list all Machines across all apps in a Fly organization. Use when you need to retrieve machines for monitoring, management, or inventory purposes. Supports filtering by region, state, and time ranges with pagination for large result sets. |
| `FLY_REMOVE_WIREGUARD_PEER` | Remove WireGuard Peer | Tool to remove a WireGuard peer connection from a Fly.io organization. Use when you need to delete or revoke an existing WireGuard peer from your organization's network. |
| `FLY_SET_APPS_V2_DEFAULT` | Set Apps V2 Default | Tool to configure whether new apps in an organization use Apps V2 by default on Fly.io. Use when you need to enable or disable Apps V2 as the default for new applications in a specific organization. |
| `FLY_UPDATE_THIRD_PARTY_CONFIGURATION` | Update Third-Party Configuration | Tool to update an existing third-party service configuration for discharging macaroon caveats. Use when you need to modify settings of external authorization services for Fly.io token validation. |
| `FLY_VALIDATE_CONFIG` | Validate Config | Tool to validate a Fly.io app configuration. Use when you need to check if a fly.toml configuration is valid before deploying or updating an app. |
| `FLY_VALIDATE_WIREGUARD_PEERS` | Validate WireGuard Peers | Tool to validate WireGuard peer IP addresses in a Fly.io organization. Use when you need to verify which peer IPs are valid or invalid before establishing VPN connections. |

## Supported Triggers

None listed.

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

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

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

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 Fly 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, fly)
- 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 Fly 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=["fly"],
    )

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

  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 Fly 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 Fly
```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 Fly, 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=["fly"],
    )

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

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

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

## Related Toolkits

- [Supabase](https://composio.dev/toolkits/supabase) - Supabase is an open-source backend platform offering scalable Postgres databases, authentication, storage, and real-time APIs. It lets developers build modern apps without managing infrastructure.
- [Codeinterpreter](https://composio.dev/toolkits/codeinterpreter) - Codeinterpreter is a Python-based coding environment with built-in data analysis and visualization. It lets you instantly run scripts, plot results, and prototype solutions inside supported platforms.
- [GitHub](https://composio.dev/toolkits/github) - GitHub is a code hosting platform for version control and collaborative software development. It streamlines project management, code review, and team workflows in one place.
- [Ably](https://composio.dev/toolkits/ably) - Ably is a real-time messaging platform for live chat and data sync in modern apps. It offers global scale and rock-solid reliability for seamless, instant experiences.
- [Abuselpdb](https://composio.dev/toolkits/abuselpdb) - Abuselpdb is a central database for reporting and checking IPs linked to malicious online activity. Use it to quickly identify and report suspicious or abusive IP addresses.
- [Alchemy](https://composio.dev/toolkits/alchemy) - Alchemy is a blockchain development platform offering APIs and tools for Ethereum apps. It simplifies building and scaling Web3 projects with robust infrastructure.
- [Algolia](https://composio.dev/toolkits/algolia) - Algolia is a hosted search API that powers lightning-fast, relevant search experiences for web and mobile apps. It helps developers deliver instant, typo-tolerant, and scalable search without complex infrastructure.
- [Anchor browser](https://composio.dev/toolkits/anchor_browser) - Anchor browser is a developer platform for AI-powered web automation. It transforms complex browser actions into easy API endpoints for streamlined web interaction.
- [Apiflash](https://composio.dev/toolkits/apiflash) - Apiflash is a website screenshot API for programmatically capturing web pages. It delivers high-quality screenshots on demand for automation, monitoring, or reporting.
- [Apiverve](https://composio.dev/toolkits/apiverve) - Apiverve delivers a suite of powerful APIs that simplify integration for developers. It's designed for reliability and scalability so you can build faster, smarter applications without the integration headache.
- [Appcircle](https://composio.dev/toolkits/appcircle) - Appcircle is an enterprise-grade mobile CI/CD platform for building, testing, and publishing mobile apps. It streamlines mobile DevOps so teams ship faster and with more confidence.
- [Appdrag](https://composio.dev/toolkits/appdrag) - Appdrag is a cloud platform for building websites, APIs, and databases with drag-and-drop tools and code editing. It accelerates development and iteration by combining hosting, database management, and low-code features in one place.
- [Appveyor](https://composio.dev/toolkits/appveyor) - AppVeyor is a cloud-based continuous integration service for building, testing, and deploying applications. It helps developers automate and streamline their software delivery pipelines.
- [Backendless](https://composio.dev/toolkits/backendless) - Backendless is a backend-as-a-service platform for mobile and web apps, offering database, file storage, user authentication, and APIs. It helps developers ship scalable applications faster without managing server infrastructure.
- [Baserow](https://composio.dev/toolkits/baserow) - Baserow is an open-source no-code database platform for building collaborative data apps. It makes it easy for teams to organize data and automate workflows without writing code.
- [Bench](https://composio.dev/toolkits/bench) - Bench is a benchmarking tool for automated performance measurement and analysis. It helps you quickly evaluate, compare, and track your systems or workflows.
- [Better stack](https://composio.dev/toolkits/better_stack) - Better Stack is a monitoring, logging, and incident management solution for apps and services. It helps teams ensure application reliability and performance with real-time insights.
- [Bitbucket](https://composio.dev/toolkits/bitbucket) - Bitbucket is a Git-based code hosting and collaboration platform for teams. It enables secure repository management and streamlined code reviews.
- [Blazemeter](https://composio.dev/toolkits/blazemeter) - Blazemeter is a continuous testing platform for web and mobile app performance. It empowers teams to automate and analyze large-scale tests with ease.
- [Blocknative](https://composio.dev/toolkits/blocknative) - Blocknative delivers real-time mempool monitoring and transaction management for public blockchains. Instantly track pending transactions and optimize blockchain interactions with live data.

## Frequently Asked Questions

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

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

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

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

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