# How to integrate Digital ocean MCP with LlamaIndex

```json
{
  "title": "How to integrate Digital ocean MCP with LlamaIndex",
  "toolkit": "Digital ocean",
  "toolkit_slug": "digital_ocean",
  "framework": "LlamaIndex",
  "framework_slug": "llama-index",
  "url": "https://composio.dev/toolkits/digital_ocean/framework/llama-index",
  "markdown_url": "https://composio.dev/toolkits/digital_ocean/framework/llama-index.md",
  "updated_at": "2026-05-12T10:08:51.977Z"
}
```

## Introduction

This guide walks you through connecting Digital ocean to LlamaIndex using the Composio tool router. By the end, you'll have a working Digital ocean agent that can spin up a droplet for staging environment, provision a new postgresql database cluster, create a dns a record for your domain through natural language commands.
This guide will help you understand how to give your LlamaIndex agent real control over a Digital ocean account through Composio's Digital ocean MCP server.
Before we dive in, let's take a quick look at the key ideas and tools involved.

## Also integrate Digital ocean with

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

The Digital ocean MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your DigitalOcean account. It provides structured and secure access to your cloud infrastructure, so your agent can perform actions like creating droplets, managing domains and DNS, provisioning databases, and organizing resources on your behalf.
- Automated droplet provisioning: Instantly spin up new virtual machines (droplets) by specifying name, region, size, and image to quickly scale your infrastructure.
- Database and block storage management: Have your agent create managed database clusters or persistent block storage volumes with custom configurations for seamless backend scaling.
- Domain and DNS record automation: Simplify domain setup and DNS management by letting your agent create new domains and add or update DNS records as needed.
- Kubernetes and firewall setup: Easily deploy Kubernetes clusters and configure firewalls by defining rules, regions, and node pools—without manual dashboard work.
- SSH key and resource tagging: Register new SSH keys for secure access or organize your infrastructure with custom tags, making resource management effortless and consistent.

## Supported Tools

| Tool slug | Name | Description |
|---|---|---|
| `DIGITAL_OCEAN_CREATE_CUSTOM_IMAGE` | Create Custom Image | Creates a custom image in DigitalOcean by importing a Linux VM disk image from a publicly accessible URL. Use this action to upload custom OS images (Ubuntu, Debian, CentOS, Fedora, etc.) that can later be used to create Droplets. The image will be processed asynchronously and its status can be monitored via the returned image ID. |
| `DIGITAL_OCEAN_CREATE_DATABASE_CLUSTER` | Create Database Cluster | Creates a new managed database cluster on DigitalOcean. Provisions a database with specified engine (PostgreSQL, MySQL, Valkey, MongoDB, Kafka, or OpenSearch), version, region, size, and node count. Returns connection credentials and cluster details. The cluster will be in 'creating' status initially and take several minutes to become fully operational. |
| `DIGITAL_OCEAN_CREATE_NEW_BLOCK_STORAGE_VOLUME` | Create New Block Storage Volume | Tool to create a new block storage volume. Use when you need to provision persistent block storage after confirming the target region supports volumes. Example: "Create a 100 GiB ext4 backup volume named 'db-backup' in nyc1." |
| `DIGITAL_OCEAN_CREATE_NEW_DOMAIN` | Create New Domain | Creates a new domain in DigitalOcean's DNS management system. This adds the domain to your DigitalOcean account and allows you to manage its DNS records. Use this action when you need to: - Add a domain to DigitalOcean DNS for DNS hosting and management - Set up a new domain with an optional initial A record pointing to an IP address - Transfer DNS management of an existing domain to DigitalOcean Note: The domain name must be unique within your DigitalOcean account and use a recognized top-level domain (TLD). After creation, you can add additional DNS records using the create domain record action. |
| `DIGITAL_OCEAN_CREATE_NEW_DOMAIN_RECORD` | Create Domain Record | Tool to create a new DNS record for a domain. Use after confirming domain exists and record specifics. |
| `DIGITAL_OCEAN_CREATE_NEW_DROPLET` | Create New Droplet | Tool to create a new Droplet. Use when you need to provision a VM with name, region, size, and image. The `image`, `region`, and `size` must be mutually compatible — the chosen `region` must be listed in the image's available regions. |
| `DIGITAL_OCEAN_CREATE_NEW_FIREWALL` | Create New Firewall | Creates a new cloud firewall with custom inbound and outbound rules. Use this action to set up network security rules that control traffic to and from your Droplets. You can specify rules using IP addresses (CIDR notation), Droplet IDs, tags, Load Balancer UUIDs, or Kubernetes cluster IDs. The firewall can be applied to specific Droplets, all Droplets with certain tags, or scoped to a VPC. Requires at least one inbound rule and one outbound rule. Supports tcp, udp, and icmp protocols. |
| `DIGITAL_OCEAN_CREATE_NEW_KUBERNETES_CLUSTER` | Create New Kubernetes Cluster | Creates a new DigitalOcean Kubernetes (DOKS) cluster with managed control plane. Required: cluster name, region slug, Kubernetes version slug, and at least one node pool configuration. Optional: tags, auto-upgrade settings, maintenance policy, node labels/taints, and auto-scaling. The cluster will be created in 'provisioning' state and may take several minutes to become 'running'. Query /v2/kubernetes/options endpoint to get available regions, versions, and node sizes. |
| `DIGITAL_OCEAN_CREATE_NEW_LOAD_BALANCER` | Create New Load Balancer | Tool to create a new load balancer. Use after specifying region, forwarding rules, and targets. |
| `DIGITAL_OCEAN_CREATE_NEW_SSH_KEY` | Create New SSH Key | Registers a new SSH public key with your DigitalOcean account. The registered key can then be automatically added to new Droplets during creation, enabling secure SSH access. The key must be provided in OpenSSH format (ssh-rsa, ssh-ed25519, etc.) and must not already exist on the account. |
| `DIGITAL_OCEAN_CREATE_NEW_TAG` | Create New Tag | Creates a new tag in DigitalOcean for organizing and grouping resources. Tags can be applied to droplets, images, volumes, volume snapshots, and databases. If a tag with the same name already exists, the API returns the existing tag (idempotent operation). Tag names must be 1-255 characters containing only letters, numbers, hyphens, or underscores. |
| `DIGITAL_OCEAN_CREATE_NEW_VPC` | Create New VPC | Creates a new Virtual Private Cloud (VPC) in a specified DigitalOcean region. VPCs are private networks for isolating your resources. Traffic within a VPC is free and doesn't count toward bandwidth limits. VPCs support Droplets, managed databases, load balancers, and Kubernetes clusters. The first VPC created in a region automatically becomes the default VPC for that region. |
| `DIGITAL_OCEAN_DELETE_BLOCK_STORAGE_VOLUME` | Delete Block Storage Volume | Permanently deletes a block storage volume by its unique ID. Use this tool when you need to remove an existing volume. The volume must not be attached to any Droplet before deletion. This operation cannot be undone. Returns HTTP 204 No Content on success. Note: To delete by volume name instead of ID, you would need a different endpoint that accepts both name and region parameters. |
| `DIGITAL_OCEAN_DELETE_DATABASE_CLUSTER` | Delete Database Cluster | Tool to delete a database cluster by UUID. Use when you have confirmed the cluster is no longer needed. Returns HTTP 204 No Content on success. |
| `DIGITAL_OCEAN_DELETE_DOMAIN` | Delete Domain | Deletes a domain from DigitalOcean DNS. This action is permanent and cannot be undone. Note: If the domain is associated with a Let's Encrypt certificate, delete the certificate first and reconfigure any resources using it (e.g., load balancer SSL termination, Spaces CDN endpoints). Returns 204 No Content on successful deletion. |
| `DIGITAL_OCEAN_DELETE_DOMAIN_RECORD` | Delete Domain Record | Tool to delete a DNS record by its record ID for a domain. Use when you need to remove an existing DNS record and have the domain name and record ID. Returns HTTP 204 No Content on success. |
| `DIGITAL_OCEAN_DELETE_EXISTING_DROPLET` | Delete Existing Droplet | Tool to delete a Droplet by ID. Deletion is irreversible — all data is permanently lost. Confirm droplet_id with the user and verify a backup or snapshot exists before proceeding. |
| `DIGITAL_OCEAN_DELETE_FIREWALL` | Delete Firewall | Tool to delete a firewall by ID. Use when you have confirmed the firewall is no longer needed. |
| `DIGITAL_OCEAN_DELETE_IMAGE` | Delete Image | Deletes a user-created custom image or snapshot from your DigitalOcean account by its numeric ID. This action permanently removes the image and cannot be undone. Only custom images and snapshots you own can be deleted - attempting to delete distribution images or marketplace applications will fail with a 403 Forbidden error. Use this when cleaning up unused images that are no longer needed and have no dependent resources. |
| `DIGITAL_OCEAN_DELETE_LOAD_BALANCER` | Delete Load Balancer | Tool to delete a load balancer instance by ID. Use when you need to permanently remove an existing load balancer after confirming its ID. Returns 204 No Content on success. |
| `DIGITAL_OCEAN_DELETE_SSH_KEY` | Delete SSH Key | Tool to delete a public SSH key. Use when you need to remove an SSH key from your account by its ID or fingerprint after confirming its ownership. Returns 204 No Content on success. |
| `DIGITAL_OCEAN_DELETE_TAG` | Delete Tag | Deletes a tag from your DigitalOcean account. When a tag is deleted, it is automatically removed from all resources that were tagged with it. This operation is idempotent - deleting a non-existent tag will also return success (204 No Content). |
| `DIGITAL_OCEAN_DELETE_VPC` | Delete VPC | Delete a VPC (Virtual Private Cloud) by its unique identifier. Use this tool when you need to permanently remove a VPC from your DigitalOcean account. Deletion is irreversible — always confirm the vpc_id with the user before proceeding. **Important Restrictions:** - Cannot delete a VPC that is the default VPC for its region - Cannot delete a VPC that has member resources (droplets, databases, load balancers, etc.) — all resources must be detached or migrated first - VPC must be empty before deletion Returns an empty response (HTTP 204) on successful deletion. |
| `DIGITAL_OCEAN_LIST_ALL_DATABASES` | List All Databases | Tool to list all managed database clusters on your account. Supports pagination and filtering by tag. A single request returns only one page; iterate using `page` and `per_page` to retrieve all clusters. |
| `DIGITAL_OCEAN_LIST_ALL_DOMAINS` | List All Domains | Lists all DNS domains configured in your DigitalOcean account. Returns domain names, TTL values, and complete zone files. Supports pagination for large domain lists. Use this action to discover available domains, check domain configurations, or as a prerequisite for domain-specific operations like managing DNS records. No parameters are required - calling without parameters returns the first 20 domains (default page size). |
| `DIGITAL_OCEAN_LIST_ALL_DROPLETS` | List All Droplets | Lists all Droplets (virtual machines) in your DigitalOcean account with pagination support. Returns detailed information including: ID, name, specs (memory, vCPUs, disk), status, networking (IP addresses), region, image, size, tags, and VPC. Supports filtering by tag and pagination for large result sets. Use this to get an overview of your infrastructure, find specific droplets, or monitor droplet status. Default page size is 20; accounts with more droplets require explicit pagination (increment `page`, up to `per_page=200`) to avoid silently incomplete results. |
| `DIGITAL_OCEAN_LIST_ALL_FIREWALLS` | List All Firewalls | List all cloud firewalls configured in your DigitalOcean account. Returns comprehensive firewall details including inbound/outbound rules, associated droplets, tags, and status. Supports pagination for accounts with many firewalls. Use this to audit network security, discover existing firewall configurations, or retrieve firewall IDs for subsequent operations. |
| `DIGITAL_OCEAN_LIST_ALL_IMAGES` | List All Images | Tool to list all images available on your account. Use after obtaining a valid API token to retrieve images optionally filtered by type, private visibility, or tag_name. |
| `DIGITAL_OCEAN_LIST_ALL_KUBERNETES_CLUSTERS` | List All Kubernetes Clusters | Tool to list all Kubernetes clusters on your account. Use when you need to enumerate every cluster and handle pagination. |
| `DIGITAL_OCEAN_LIST_ALL_LOAD_BALANCERS` | List All Load Balancers | List all load balancers in your DigitalOcean account with pagination support. Returns load balancer details including IDs, names, IP addresses, forwarding rules, health checks, sticky sessions, assigned Droplets, and region information. Use this to get an overview of all load balancers or to find specific load balancers by iterating through results. |
| `DIGITAL_OCEAN_LIST_ALL_SNAPSHOTS` | List All Snapshots | Tool to list all snapshots available on your DigitalOcean account. Use when you need to fetch and optionally filter snapshots by resource type (droplet or volume) and handle pagination for inventory or backup workflows. |
| `DIGITAL_OCEAN_LIST_ALL_SSH_KEYS` | List All SSH Keys | Lists all SSH keys associated with your DigitalOcean account. Returns SSH key details including ID, name, public key content, and fingerprint. Supports pagination for accounts with many SSH keys. Use this when you need to view available SSH keys or retrieve an SSH key ID for use with other operations like creating droplets. |
| `DIGITAL_OCEAN_LIST_ALL_TAGS` | List All Tags | Tool to list all tags in your account. Use when you need to retrieve available tags and pagination info. A single request returns only one page of results; iterate using `page` and `per_page` to retrieve all tags. |
| `DIGITAL_OCEAN_LIST_ALL_VOLUMES` | List All Volumes | Tool to list all block storage volumes available on your account. Use when you need to retrieve volumes and optionally filter by name and region. |
| `DIGITAL_OCEAN_LIST_ALL_VPCS` | List All VPCs | Tool to list all VPCs on your account. Use when you need an inventory of your VPC resources. A single request returns only one page; iterate through all pages using `page` and `per_page` (max 200) to retrieve the complete set. |
| `DIGITAL_OCEAN_LIST_APPS` | List Apps | Tool to list all App Platform apps in your DigitalOcean account. Use when you need to discover app IDs by name, retrieve app metadata, or enumerate all apps with pagination support. |
| `DIGITAL_OCEAN_LIST_DATABASE_OPTIONS` | List Database Options | Lists all available configuration options for DigitalOcean managed database clusters, including supported engines (PostgreSQL, MySQL, MongoDB, Valkey, Kafka, OpenSearch), versions, regions, and cluster sizes/layouts. Use this to discover valid parameter values when creating a new database cluster. |
| `DIGITAL_OCEAN_LIST_DOMAIN_RECORDS` | List Domain Records | Tool to list all DNS records for a domain. Use when you need to inspect or filter a domain's DNS configuration. |
| `DIGITAL_OCEAN_RETRIEVE_DOMAIN` | Retrieve Domain | Retrieves complete details about a specific domain including its TTL and DNS zone file configuration. Use this when you need to check domain settings, verify DNS configuration, or get the full zone file contents for a domain in your DigitalOcean account. |
| `DIGITAL_OCEAN_RETRIEVE_DOMAIN_RECORD` | Retrieve Domain Record | Tool to retrieve a specific DNS record for a domain by its record ID. Use when you have the domain name and record ID to fetch record details. |
| `DIGITAL_OCEAN_RETRIEVE_EXISTING_DROPLET` | Retrieve Existing Droplet | Retrieve detailed information about a specific DigitalOcean Droplet by its unique numeric ID. Returns comprehensive droplet details including: current status, specifications (memory, CPU, disk), networking configuration (IPv4/IPv6 addresses), image information, region, VPC, backup settings, attached volumes, and tags. Use this when you need to check a droplet's current state, configuration, or IP addresses. |
| `DIGITAL_OCEAN_RETRIEVE_EXISTING_IMAGE` | Retrieve Existing Image | Tool to retrieve information about an image by ID or slug. Use when you need detailed metadata for a known image. |
| `DIGITAL_OCEAN_RETRIEVE_TAG` | Retrieve Tag | Tool to retrieve an individual tag by name. Use when you need to inspect the resources grouped under a specific tag. |
| `DIGITAL_OCEAN_RETRIEVE_VPC` | Retrieve VPC | Tool to retrieve details about a specific VPC by its ID. Use when you need to inspect VPC properties for configuration or auditing. |
| `DIGITAL_OCEAN_TAG_RESOURCE` | Tag Resource | Tool to tag resources by name. Use when you need to assign an existing tag to one or more resources. Returns 204 No Content on success. |
| `DIGITAL_OCEAN_UNTAG_RESOURCE` | Untag Resource | Tool to untag resources by tag name. Use when you need to remove an existing tag from multiple resources in a single operation. |
| `DIGITAL_OCEAN_UPDATE_DOMAIN_RECORD` | Update Domain Record | Tool to update an existing DNS record for a domain. Use when you need to modify any valid attribute of a record after confirming its record ID. |
| `DIGITAL_OCEAN_UPDATE_VPC` | Update VPC | Tool to update information about a VPC. Use when you need to modify the name, description, or default status of an existing VPC. |

## Supported Triggers

None listed.

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

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

### 1. Getting API Keys for OpenAI, Composio, and Digital ocean

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 Digital ocean 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, digital ocean)
- 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 Digital ocean 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=["digital_ocean"],
    )

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

  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 Digital ocean 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 Digital ocean
```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 Digital ocean, 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=["digital_ocean"],
    )

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

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

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

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

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

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

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