How to Use the DigitalOcean MCP in CrewAI

Q: How do I restrict which DigitalOcean tools my CrewAI agents can access via the MCP Server?

Use the toolfilter option in CrewAI's MCPServerHTTP setup to only expose specific tools like listdomains. This prevents agents from accidentally modifying critical infrastructure.

Deploy a CrewAI team of specialized agents to audit, monitor, and manage your DigitalOcean cloud.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect DigitalOcean MCP to CrewAI

Create your Vinkius account to connect DigitalOcean to CrewAI and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup DigitalOcean with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Agent Infrastructure Auditing with CrewAI

`get_account_info` provides your CrewAI audit team with the baseline resource limits for your DigitalOcean subscription. One specialized CrewAI agent can verify your account thresholds while another scans active resources to find discrepancies. `list_droplets` gives the CrewAI auditing agent a complete list of running DigitalOcean virtual servers to cross-reference against your billing targets. The crew compares active node specs with your actual usage requirements to find overprovisioned systems.

Collaborative Database and Storage Monitoring

`list_databases` allows your CrewAI monitoring agent to inspect active DigitalOcean database clusters and engine versions. While this agent tracks database health, a CrewAI storage specialist agent uses `list_volumes` to check attached block storage. `get_droplet_details` is called by the coordinator agent when a DigitalOcean database node shows signs of distress. The CrewAI agents collaborate to isolate the issue, checking if the underlying droplet or the database cluster itself is running out of resources.

Autonomous DNS and Image Auditing

`list_domains` lets your CrewAI security agent review active DigitalOcean web domains and DNS records for vulnerabilities. The CrewAI agent flags dangling records or outdated pointers that could lead to subdomain takeovers. `list_images` is scanned by a CrewAI compliance agent to clean up obsolete DigitalOcean snapshots and custom disk images. The agent identifies old backups that are costing you money but are no longer needed.

Setup guide

Set up DigitalOcean MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke DigitalOcean tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="DigitalOcean Analyst",
    goal="Access and analyze DigitalOcean data via MCP.",
    backstory="Expert analyst with direct DigitalOcean access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent DigitalOcean transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="DigitalOcean Analyst",
        goal="Access and analyze DigitalOcean data via MCP.",
        backstory="Expert analyst with direct DigitalOcean access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent DigitalOcean transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by DigitalOcean. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect DigitalOcean now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about DigitalOcean MCP in CrewAI

CrewAI agents use shared memory to pass the results of tools like `list_droplets` between specialized roles. The monitoring agent checks the list, and the analysis agent processes the specs.

Yes, you can point your local CrewAI agents to the hosted MCP Server URL. The agents will securely run `list_kubernetes_clusters` over HTTP without needing local cloud configurations.

Use the `tool_filter` option in CrewAI's `MCPServerHTTP` setup to only expose specific tools like `list_domains`. This prevents agents from accidentally modifying critical infrastructure.

Yes, you can set up a hierarchical crew where a supervisor agent first runs `get_account_info` before letting worker agents inspect individual droplets. This guarantees systematic infrastructure checks.

This MCP Server uses a zero-trust, ephemeral V8 sandbox to process DNS records and volume configurations. No data is stored, and the connection uses end-to-end encryption to prevent exposure to external networks.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript