# How to integrate Cloudflare MCP with LlamaIndex

```json
{
  "title": "How to integrate Cloudflare MCP with LlamaIndex",
  "toolkit": "Cloudflare",
  "toolkit_slug": "cloudflare",
  "framework": "LlamaIndex",
  "framework_slug": "llama-index",
  "url": "https://composio.dev/toolkits/cloudflare/framework/llama-index",
  "markdown_url": "https://composio.dev/toolkits/cloudflare/framework/llama-index.md",
  "updated_at": "2026-05-12T10:06:40.688Z"
}
```

## Introduction

This guide walks you through connecting Cloudflare to LlamaIndex using the Composio tool router. By the end, you'll have a working Cloudflare agent that can add new a record for your domain, list all firewall rules for zone, show members of your cloudflare account through natural language commands.
This guide will help you understand how to give your LlamaIndex agent real control over a Cloudflare account through Composio's Cloudflare MCP server.
Before we dive in, let's take a quick look at the key ideas and tools involved.

## Also integrate Cloudflare with

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

The Cloudflare MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Cloudflare account. It provides structured and secure access to your Cloudflare infrastructure, so your agent can perform actions like managing DNS records, configuring WAF lists, auditing firewall rules, and overseeing zones and account members—all on your behalf.
- DNS record management: Effortlessly create or delete DNS records within any zone, allowing your agent to automate domain setup and maintenance tasks.
- WAF list and firewall rule automation: Direct your agent to create, list, or delete Web Application Firewall (WAF) lists and audit firewall rules to enhance your site's security posture.
- Zone administration: Enable your agent to create new zones when adding domains or delete zones that are no longer needed, streamlining domain onboarding and cleanup.
- Account and member management: Let your agent list all Cloudflare accounts you have access to and enumerate members within each account for audit or collaboration purposes.
- Comprehensive infrastructure visibility: Ask your agent to fetch and review your entire Cloudflare account structure, making it simple to monitor resources and configurations at scale.

## Supported Tools

| Tool slug | Name | Description |
|---|---|---|
| `CLOUDFLARE_CREATE_DNS_RECORD` | Create DNS record | Tool to create a new DNS record within a specific zone. Requires write privileges and makes live changes to the zone. Use after obtaining the zone ID via CLOUDFLARE_LIST_ZONES to programmatically add DNS entries. |
| `CLOUDFLARE_CREATE_LIST` | Create WAF List | Create a new empty custom list for use in WAF rules and filters. Lists can contain IP addresses, hostnames, ASNs, or redirects. Once created, use separate actions to add items to the list. Note: List availability depends on plan (Free: 1 list, Pro/Business: 10 lists, Enterprise: 1000 lists). Example: CREATE_LIST(account_id="abc123", kind="ip", name="blocklist", description="Block malicious IPs") |
| `CLOUDFLARE_CREATE_ZONE` | Create Zone | Creates a new DNS zone (domain) in Cloudflare. A zone represents a domain and its DNS records. Use this when adding a new domain to manage with Cloudflare. Requires account ID (obtainable via LIST_ACCOUNTS). The zone will be in 'pending' status until nameservers are updated at the domain registrar. |
| `CLOUDFLARE_DELETE_DNS_RECORD` | Delete DNS Record | Tool to delete a DNS record within a specific zone. Deletion is immediate and irreversible. Use only after confirming both zone and record IDs. Requires write privileges on the zone. Example: "Delete DNS record 372e6795... from zone 023e105f4ecef..." |
| `CLOUDFLARE_DELETE_LIST` | Delete WAF List | Tool to delete a WAF list. Use when you need to remove a list after verifying no filters reference it. Example: DELETE_LIST(account_id="", list_id="") |
| `CLOUDFLARE_DELETE_ZONE` | Delete Zone | Tool to delete a zone. Use after confirming the zone identifier to permanently remove a DNS zone and all its DNS records from your Cloudflare account. Example: DELETE_ZONE(zone_identifier="023e105f4ecef8ad9ca31a8372d0c353") |
| `CLOUDFLARE_GET_BOT_MANAGEMENT_SETTINGS` | Get Bot Management Settings | Tool to retrieve a zone's Bot Management configuration (Bot Fight Mode / Super Bot Fight Mode / Enterprise Bot Management). Use after identifying the correct zone_id (e.g., via CLOUDFLARE_LIST_ZONES). This tool is the canonical way to audit bot-related configuration; firewall rules are adjacent controls but not equivalent to Bot Management settings. |
| `CLOUDFLARE_GET_LISTS` | List WAF Lists | Tool to fetch all WAF lists (no items) for an account. Results are paginated; iterate using page and per_page parameters until result_info.total_pages is reached to retrieve all lists. Use after confirming account ID. |
| `CLOUDFLARE_LIST_ACCOUNT_MEMBERS` | List Account Members | Lists all members of a Cloudflare account with their roles, permissions, and status. Returns detailed information about each account member including their user details (name, email, 2FA status), assigned roles with granular permissions, membership status (accepted/pending/rejected), and access policies. Supports filtering by status, sorting by various fields, and pagination for accounts with many members. Use this action when you need to: - View all users with access to a Cloudflare account - Audit account member permissions and roles - Check membership status of invited users - List members with specific roles or statuses Requires the account ID which can be obtained using the List Accounts action. Note: caller's account role may restrict visibility of some members if permissions are insufficient. |
| `CLOUDFLARE_LIST_ACCOUNTS` | List Accounts | List all Cloudflare accounts you have ownership or verified access to. Retrieves a paginated list of accounts with their details including account ID, name, type, settings, and creation date. An empty or partial result may indicate insufficient API token scope or permissions, not the absence of accounts. When multiple accounts are returned, confirm the intended account_id before performing any write operations to avoid acting on unintended environments. Use this when you need to: - Discover available accounts before performing account-specific operations - Find an account ID for other API calls that require an account identifier - Audit account configurations and settings - Filter accounts by name or paginate through large account lists |
| `CLOUDFLARE_LIST_DNS_RECORDS` | List DNS records | Tool to list and search DNS records in a Cloudflare zone. Use when you need to find existing DNS record IDs for update or delete operations, especially after a "record already exists" error during creation. Returns matching records with their IDs, names, types, content, and other properties. |
| `CLOUDFLARE_LIST_FIREWALL_RULES` | List Firewall Rules | Tool to list firewall rules for a specific DNS zone. Use after confirming the zone ID to retrieve and audit current firewall rules. Does not expose Workers routes or other routing constructs. |
| `CLOUDFLARE_LIST_MONITORS` | List Monitors | Tool to list all load-balancer monitors in a Cloudflare account. Use after creating or updating monitors to retrieve a paginated list. Response includes `result_info.total_pages` to determine when all pages have been fetched. |
| `CLOUDFLARE_LIST_POOLS` | List Pools | Tool to list all load balancer pools in a Cloudflare account. Use after confirming account ID to discover pool IDs. Paginate using `page` and `per_page`; check `result_info.total_pages` in the response to determine if additional pages exist. |
| `CLOUDFLARE_LIST_TUNNELS` | List Tunnels | List Cloudflare Tunnel (cloudflared) tunnels in an account to discover tunnel IDs, names, and statuses. Use when you need to find a tunnel_id before performing tunnel operations like routing, DNS configuration, or debugging. |
| `CLOUDFLARE_LIST_ZONES` | List Zones | Lists, searches, sorts, and filters zones in the authenticated account. Use `page`/`per_page` to paginate; check `result_info.total_pages` in the response to iterate all pages. Does not return DNS records — extract `zone_id` from results before passing to zone-scoped tools (DNS, firewall, etc.). Only zones delegated to Cloudflare nameservers appear; empty results indicate scope or delegation constraints, not errors. |
| `CLOUDFLARE_UPDATE_DNS_RECORD` | Update DNS record | Tool to update an existing DNS record within a specific zone. Use after confirming both zone and record identifiers; only provided fields are modified. Updates to records used by active tunnels take effect immediately and can disrupt live traffic. |
| `CLOUDFLARE_UPDATE_LIST` | Update WAF List | Tool to update the description of a WAF list (cannot update items). Use after confirming list metadata. |
| `CLOUDFLARE_UPDATE_TUNNEL_CONFIGURATION` | Update Tunnel Configuration | Tool to update a remotely-managed Cloudflare Tunnel's configuration (ingress rules and routing). Use when you need to programmatically configure hostname-to-origin mappings for a tunnel. WARNING: This operation REPLACES the entire configuration - incorrect configuration can break routing and make services unreachable. Best practice: fetch current configuration first (if patching) to preserve existing rules. At least one ingress rule is required, and the last rule should typically be a catch-all (hostname='*' or omitted) with service='http_status:404'. |
| `CLOUDFLARE_UPDATE_ZONE` | Update Zone | Tool to update properties of an existing zone; changes apply immediately to the live zone. Confirm zone ID and intended change with the user before calling. Only one field can be modified per call. |

## Supported Triggers

None listed.

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

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

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

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 Cloudflare 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, cloudflare)
- 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 Cloudflare 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=["cloudflare"],
    )

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

  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 Cloudflare 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 Cloudflare
```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 Cloudflare, 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=["cloudflare"],
    )

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

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

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

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

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

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

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