How to integrate Digital ocean MCP with Claude Agent SDK

BOOK A CALLGET STARTED FOR FREE
Framework Integration Gradient
Digital ocean Logo
Claude Agent SDK Logo
divider

Introduction

This guide walks you through connecting Digital ocean to the Claude Agent SDK 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 my domain, add my ssh key to all droplets through natural language commands.

This guide will help you understand how to give your Claude Agent SDK 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.

TL;DR

Here's what you'll learn:
  • Get and set up your Claude/Anthropic and Composio API keys
  • Install the necessary dependencies
  • Initialize Composio and create a Tool Router session for Digital ocean
  • Configure an AI agent that can use Digital ocean as a tool
  • Run a live chat session where you can ask the agent to perform Digital ocean operations

What is Claude Agent SDK?

The Claude Agent SDK is Anthropic's official framework for building AI agents powered by Claude. It provides a streamlined interface for creating agents with MCP tool support and conversation management.

Key features include:

  • Native MCP Support: Built-in support for Model Context Protocol servers
  • Permission Modes: Control tool execution permissions
  • Streaming Responses: Real-time response streaming for interactive applications
  • Context Manager: Clean async context management for sessions

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 & Triggers

Tools
Create Custom ImageTool to create a new custom image by providing a url to a linux vm image.
Create Database ClusterTool to create a new managed database cluster.
Create New Block Storage VolumeTool to create a new block storage volume.
Create New DomainTool to create a new domain.
Create Domain RecordTool to create a new dns record for a domain.
Create New DropletTool to create a new droplet.
Create New FirewallTool to create a new firewall.
Create New Kubernetes ClusterTool to create a new kubernetes cluster.
Create New SSH KeyTool to create a new ssh key.
Create New TagTool to create a new tag.
Create New VPCTool to create a new vpc.
Delete Block Storage VolumeTool to delete a block storage volume by id.
Delete Database ClusterTool to delete a database cluster by uuid.
Delete DomainTool to delete a domain by name.
Delete Domain RecordTool to delete a dns record by its record id for a domain.
Delete Existing DropletTool to delete a droplet by id.
Delete FirewallTool to delete a firewall by id.
Delete ImageTool to delete a snapshot or custom image by id.
Delete Load BalancerTool to delete a load balancer instance by id.
Delete SSH KeyTool to delete a public ssh key.
Delete TagTool to delete a tag by name.
Delete VPCTool to delete a vpc by its id.
Create New Load BalancerTool to create a new load balancer.
List Domain RecordsTool to list all dns records for a domain.
List All DatabasesTool to list all managed database clusters on your account.
List All DomainsTool to list all domains in your digitalocean account.
List All DropletsTool to list all droplets in your account.
List All FirewallsTool to list all firewalls on your digitalocean account.
List All ImagesTool to list all images available on your account.
List All Kubernetes ClustersTool to list all kubernetes clusters on your account.
List All Load BalancersTool to list all load balancer instances on your account.
List All SnapshotsTool to list all snapshots available on your digitalocean account.
List All SSH KeysTool to list all ssh keys in your account.
List All TagsTool to list all tags in your account.
List All VolumesTool to list all block storage volumes available on your account.
List All VPCsTool to list all vpcs on your account.
List Database OptionsTool to list valid database engine, version, region, and size options.
Retrieve DomainTool to retrieve details about a specific domain by its name.
Retrieve Domain RecordTool to retrieve a specific dns record for a domain by its record id.
Retrieve Existing DropletTool to show information about an individual droplet by id.
Retrieve Existing ImageTool to retrieve information about an image by id or slug.
Retrieve TagTool to retrieve an individual tag by name.
Retrieve VPCTool to retrieve details about a specific vpc by its id.
Tag ResourceTool to tag resources by name.
Untag ResourceTool to untag resources by tag name.
Update Domain RecordTool to update an existing dns record for a domain.
Update VPCTool to update information about a vpc.

What is the Composio tool router, and how does it fit here?

What is Tool Router?

Composio's Tool Router helps agents find the right tools for a task at runtime. You can plug in multiple toolkits (like Gmail, HubSpot, and GitHub), and the agent will identify the relevant app and action to complete multi-step workflows. This can reduce token usage and improve the reliability of tool calls. Read more here: Getting started with Tool Router

The tool router generates a secure MCP URL that your agents can access to perform actions.

How the Tool Router works

The Tool Router follows a three-phase workflow:

  1. Discovery: Searches for tools matching your task and returns relevant toolkits with their details.
  2. Authentication: Checks for active connections. If missing, creates an auth config and returns a connection URL via Auth Link.
  3. Execution: Executes the action using the authenticated connection.

Step-by-step Guide

Prerequisites

Before starting, make sure you have:
  • Composio API Key and Claude/Anthropic API Key
  • Primary know-how of Claude Agents SDK
  • A Digital ocean account
  • Some knowledge of Python

Getting API Keys for Claude/Anthropic and Composio

Claude/Anthropic API Key
  • Go to the Anthropic Console and create an API key. You'll need credits to use the models.
  • Keep the API key safe.
Composio API Key
  • Log in to the Composio dashboard.
  • Navigate to your API settings and generate a new API key.
  • Store this key securely as you'll need it for authentication.

Install dependencies

pip install composio-anthropic claude-agent-sdk python-dotenv

Install the Composio SDK and the Claude Agents SDK.

What's happening:

  • composio-anthropic provides Composio integration for Anthropic
  • claude-agent-sdk is the core agent framework
  • python-dotenv loads environment variables

Set up environment variables

bash
COMPOSIO_API_KEY=your_composio_api_key_here
USER_ID=your_user_id_here
ANTHROPIC_API_KEY=your_anthropic_api_key_here

Create a .env file in your project root.

What's happening:

  • COMPOSIO_API_KEY authenticates with Composio
  • USER_ID identifies the user for session management
  • ANTHROPIC_API_KEY authenticates with Anthropic/Claude

Import dependencies

import asyncio
from claude_agent_sdk import ClaudeSDKClient, ClaudeAgentOptions
import os
from composio import Composio
from dotenv import load_dotenv

load_dotenv()
What's happening:
  • We're importing all necessary libraries including the Claude Agent SDK and Composio
  • The load_dotenv() function loads environment variables from your .env file
  • This setup prepares the foundation for connecting Claude with Digital ocean functionality

Create a Composio instance and Tool Router session

async def chat_with_remote_mcp():
    api_key = os.getenv("COMPOSIO_API_KEY")
    if not api_key:
        raise RuntimeError("COMPOSIO_API_KEY is not set")

    composio = Composio(api_key=api_key)

    # Create Tool Router session for Digital ocean
    mcp_server = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["digital_ocean"]
    )

    url = mcp_server.mcp.url

    if not url:
        raise ValueError("Session URL not found")
What's happening:
  • The function checks for the required COMPOSIO_API_KEY environment variable
  • We're creating a Composio instance using our API key
  • The create method creates a Tool Router session for Digital ocean
  • The returned url is the MCP server URL that your agent will use

Configure Claude Agent with MCP

# Configure remote MCP server for Claude
options = ClaudeAgentOptions(
    permission_mode="bypassPermissions",
    mcp_servers={
        "composio": {
            "type": "http",
            "url": url,
            "headers": {
                "x-api-key": os.getenv("COMPOSIO_API_KEY")
            }
        }
    },
    system_prompt="You are a helpful assistant with access to Digital ocean tools via Composio.",
    max_turns=10
)
What's happening:
  • We're configuring the Claude Agent options with the MCP server URL
  • permission_mode="bypassPermissions" allows the agent to execute operations without asking for permission each time
  • The system prompt instructs the agent that it has access to Digital ocean
  • max_turns=10 limits the conversation length to prevent excessive API usage

Create client and start chat loop

# Create client with context manager
async with ClaudeSDKClient(options=options) as client:
    print("\nChat started. Type 'exit' or 'quit' to end.\n")

    # Main chat loop
    while True:
        user_input = input("You: ").strip()
        if user_input.lower() in {"exit", "quit"}:
            print("Goodbye!")
            break

        # Send query
        await client.query(user_input)

        # Receive and print response
        print("Claude: ", end="", flush=True)
        async for message in client.receive_response():
            if hasattr(message, "content"):
                for block in message.content:
                    if hasattr(block, "text"):
                        print(block.text, end="", flush=True)
        print()
What's happening:
  • The Claude SDK client is created using the async context manager pattern
  • The agent processes each query and streams the response back in real-time
  • The chat loop continues until the user types 'exit' or 'quit'

Run the application

if __name__ == "__main__":
    asyncio.run(chat_with_remote_mcp())
What's happening:
  • This entry point runs the async chat_with_remote_mcp() function using asyncio.run()
  • The application will start, create the MCP connection, and begin the interactive chat session

Complete Code

Here's the complete code to get you started with Digital ocean and Claude Agent SDK:

import asyncio
from claude_agent_sdk import ClaudeSDKClient, ClaudeAgentOptions
import os
from composio import Composio
from dotenv import load_dotenv

load_dotenv()

async def chat_with_remote_mcp():
    api_key = os.getenv("COMPOSIO_API_KEY")
    if not api_key:
        raise RuntimeError("COMPOSIO_API_KEY is not set")

    composio = Composio(api_key=api_key)

    # Create Tool Router session for Digital ocean
    mcp_server = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["digital_ocean"]
    )

    url = mcp_server.mcp.url

    if not url:
        raise ValueError("Session URL not found")

    # Configure remote MCP server for Claude
    options = ClaudeAgentOptions(
        permission_mode="bypassPermissions",
        mcp_servers={
            "composio": {
                "type": "http",
                "url": url,
                "headers": {
                    "x-api-key": os.getenv("COMPOSIO_API_KEY")
                }
            }
        },
        system_prompt="You are a helpful assistant with access to Digital ocean tools via Composio.",
        max_turns=10
    )

    # Create client with context manager
    async with ClaudeSDKClient(options=options) as client:
        print("\nChat started. Type 'exit' or 'quit' to end.\n")

        # Main chat loop
        while True:
            user_input = input("You: ").strip()
            if user_input.lower() in {"exit", "quit"}:
                print("Goodbye!")
                break

            # Send query
            await client.query(user_input)

            # Receive and print response
            print("Claude: ", end="", flush=True)
            async for message in client.receive_response():
                if hasattr(message, "content"):
                    for block in message.content:
                        if hasattr(block, "text"):
                            print(block.text, end="", flush=True)
            print()

if __name__ == "__main__":
    asyncio.run(chat_with_remote_mcp())

Conclusion

You've successfully built a Claude Agent SDK agent that can interact with Digital ocean through Composio's Tool Router.

Key features:

  • Native MCP support through Claude's agent framework
  • Streaming responses for real-time interaction
  • Permission bypass for smooth automated workflows
You can extend this by adding more toolkits, implementing custom business logic, or building a web interface around the agent.

How to build Digital ocean MCP Agent with another framework

OpenAI Agents SDK

OpenAI Agents SDK

Use Digital ocean MCP with OpenAI Agents SDK

Google ADK

Google ADK

Use Digital ocean MCP with Google ADK

LangChain

LangChain

Use Digital ocean MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Digital ocean MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Digital ocean MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Digital ocean MCP with LlamaIndex

CrewAI

CrewAI

Use Digital ocean MCP with CrewAI

FAQ

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 Claude Agent SDK?

Yes, you can. Claude Agent SDK 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.

Used by agents from

Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai

Never worry about agent reliability

We handle tool reliability, observability, and security so you never have to second-guess an agent action.

Book a call↗Get started for free