developer-toolsapi_key

DigitalOcean

DigitalOcean is a cloud infrastructure provider offering scalable compute platforms with a user-friendly interface.

Verdict

The DigitalOcean MCP gives your team direct control over cloud infrastructure from inside Switchy. @Mention it to spin up droplets, provision databases, configure DNS records, or manage Kubernetes clusters without leaving the conversation. Developers can prototype environments mid-discussion, DevOps can audit running resources, and PMs can check deployment status in plain English. It exposes 47 tools covering compute, storage, networking, and managed services. You'll need a DigitalOcean API token with write access, which means anyone invoking this MCP can create billable resources — set team expectations before connecting.

Common use cases

  • Spin up staging droplets during sprint planning
  • Check database cluster health from incident chat
  • Update DNS records without switching tabs
  • Audit firewall rules after security review
  • Provision Kubernetes nodes for load testing

Integration

Vendor
DigitalOcean
Category
developer-tools
Auth
API_KEY
Tools
47
Composio slug
digital_ocean

Tools

  • Create Custom Image

    Tool to create a new custom image by providing a url to a linux vm image. use when you need to import a vm image into digitalocean after specifying name, url, distribution, and region.

  • Create Database Cluster

    Tool to create a new managed database cluster. use when you need to provision a database cluster with name, engine, version, region, size, and number of nodes.

  • Create Domain Record

    Tool to create a new dns record for a domain. use after confirming domain exists and record specifics.

  • 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."

  • Create New Domain

    Tool to create a new domain. use when you have the domain name and optionally an ip address to assign an a record.

  • Create New Droplet

    Tool to create a new droplet. use when you need to provision a vm with name, region, size, and image.

  • Create New Firewall

    Tool to create a new firewall. use when you need to define a firewall name and custom rules (requires at least one inbound and one outbound rule).

  • Create New Kubernetes Cluster

    Tool to create a new kubernetes cluster. use when you have finalized the cluster name, region, version, and at least one node pool. confirm region supports kubernetes clusters before use.

  • Create New Load Balancer

    Tool to create a new load balancer. use after specifying region, forwarding rules, and targets.

  • Create New SSH Key

    Tool to create a new ssh key. use when you need to register a public key to access droplets.

  • Create New Tag

    Tool to create a new tag. use when you need to organize resources by grouping them under a custom tag. ensure the tag name passes validation before calling. example: "create a new tag named analytics".

  • Create New VPC

    Tool to create a new vpc. use when you need to provision a private network in a specific region.

  • Delete Block Storage Volume
    destructive

    Tool to delete a block storage volume by id. use when you need to permanently remove an existing block storage volume after confirming its id. returns http 204 no content on success.

  • Delete Database Cluster
    destructive

    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.

  • Delete Domain
    destructive

    Tool to delete a domain by name. use when you have confirmed the domain has no records assigned. returns 204 no content on success.

  • Delete Domain Record
    destructive

    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.

  • Delete Existing Droplet
    destructive

    Tool to delete a droplet by id. use when you need to permanently remove an existing droplet after confirming its id to avoid unintended deletions.

  • Delete Firewall
    destructive

    Tool to delete a firewall by id. use when you have confirmed the firewall is no longer needed.

  • Delete Image
    destructive

    Tool to delete a snapshot or custom image by id. use when cleaning up unused images after confirming there are no dependents.

  • Delete Load Balancer
    destructive

    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.

  • Delete SSH Key
    destructive

    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.

  • Delete Tag
    destructive

    Tool to delete a tag by name. use when you need to untag all resources previously tagged. returns 204 no content on success.

  • Delete VPC
    destructive

    Tool to delete a vpc by its id. use when you need to remove an existing virtual private cloud. returns 204 no content on success.

  • List All Databases

    Tool to list all managed database clusters on your account. use when you need to retrieve clusters and support pagination or filtering by tag.

  • List All Domains

    Tool to list all domains in your digitalocean account. use when you need to retrieve or iterate through domains, with optional pagination. use after authentication.

  • List All Droplets

    Tool to list all droplets in your account. use when you need an overview of droplets, optionally filtered by tag. use after authentication.

  • List All Firewalls

    Tool to list all firewalls on your digitalocean account. use when you need to audit or manage firewall rules with optional pagination.

  • 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.

  • List All Kubernetes Clusters

    Tool to list all kubernetes clusters on your account. use when you need to enumerate every cluster and handle pagination.

  • List All Load Balancers

    Tool to list all load balancer instances on your account. use when you need a paginated overview of load balancers after authentication.

  • 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.

  • List All SSH Keys

    Tool to list all ssh keys in your account. use when you need to retrieve ssh key metadata.

  • List All Tags

    Tool to list all tags in your account. use when you need to retrieve available tags and pagination info.

  • 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.

  • List All VPCs

    Tool to list all vpcs on your account. use when you need an inventory of your vpc resources; supports pagination.

  • List Database Options

    Tool to list valid database engine, version, region, and size options. use when configuring a new managed database cluster.

  • 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.

  • Retrieve Domain

    Tool to retrieve details about a specific domain by its name. use after creating or importing a domain to verify ttl and zone file configuration.

  • 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.

  • Retrieve Existing Droplet

    Tool to show information about an individual droplet by id. use when you have a droplet id and need detailed status.

  • Retrieve Existing Image

    Tool to retrieve information about an image by id or slug. use when you need detailed metadata for a known image.

  • Retrieve Tag

    Tool to retrieve an individual tag by name. use when you need to inspect the resources grouped under a specific tag.

  • 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.

  • 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.

  • 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.

  • 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.

  • 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.

Setup

Setup guide

  1. 11. In Switchy, open your workspace settings and navigate to the Integrations tab. 2. Find DigitalOcean in the MCP directory and click Connect. 3. You'll be prompted to paste a DigitalOcean API token — generate one in your DigitalOcean account under API > Tokens with read and write scopes. 4. Paste the token into Switchy and click Authorize. 5. Switchy confirms the connection and shows which tools are now available. 6. Open any Space, type '@DigitalOcean list my droplets' and send — if you see a response listing your VMs, the integration works. 7. From now on, @mention DigitalOcean in any message to invoke its tools; the AI will route your request to the appropriate endpoint and return results inline.

What teammates see: by default, memories from DigitalOcean are scoped to the Space (PROJECT visibility) - you can mark any memory PRIVATE or share it ORG-wide.

Works well with

Top models

Compatibility data appears once enough Spaces have used this MCP together with a given model.

How Switchy teams use it

Not enough Spaces yet to publish anonymised usage stats (we require ≥ 50 Spaces per week).

Starter prompts

List Active Droplets

@DigitalOcean show me all active droplets with their names, IP addresses, and regions
Open in a Space →

Create Staging Server

@DigitalOcean create a new droplet named staging-api-test in nyc3 region, size s-1vcpu-1gb, using ubuntu-22-04-x64 image
Open in a Space →

Add DNS A Record

@DigitalOcean add an A record for api.example.com pointing to 192.0.2.50 with TTL 3600
Open in a Space →

Provision Postgres Cluster

@DigitalOcean create a postgres database cluster named prod-db version 15 in sfo3 region, size db-s-1vcpu-1gb, single node
Open in a Space →

Check Volume Attachments

@DigitalOcean list all block storage volumes and show which droplets they're attached to
Open in a Space →

Example outputs

Illustrative - representative of the model's voice and quality, not literal recordings.

Prompt

@digitalocean list all droplets in the nyc3 region and show me their current status, IP addresses, and monthly cost

Output

Found 4 droplets in nyc3: • web-prod-01 (Active) — 159.89.142.73 — s-2vcpu-4gb — $24/mo • api-staging-02 (Active) — 167.99.38.201 — s-1vcpu-2gb — $12/mo • worker-queue (Off) — 138.197.64.19 — s-1vcpu-1gb — $6/mo • db-backup (Active) — 104.131.52.88 — s-4vcpu-8gb — $48/mo Total monthly cost for these 4 droplets: $90. The worker-queue droplet is powered off but still incurs storage charges.

Notes

This read-heavy example demonstrates resource inventory across your infrastructure. Requires a DigitalOcean API token with read scope. The MCP fetches live data, so costs and IPs reflect your actual account state at query time. Useful for cost audits and capacity planning before scaling decisions.

Prompt

@digitalocean create a new droplet named analytics-node in sfo3 using Ubuntu 22.04, size s-2vcpu-4gb, and attach it to my existing vpc-analytics network

Output

Droplet creation initiated: • Name: analytics-node • Region: sfo3 • Image: Ubuntu 22.04 x64 • Size: s-2vcpu-4gb (2 vCPUs, 4GB RAM, 80GB SSD) • VPC: vpc-analytics • Estimated time: 55 seconds • IPv4 will be assigned on boot • Monthly cost: $24 The droplet is now provisioning. You'll receive the assigned IP address once boot completes. SSH keys from your account will be automatically installed.

Notes

This write example shows infrastructure provisioning with a single prompt. Requires write scope on your API token. The MCP creates real resources that incur charges immediately—confirm size and region before running. Side-effect: a billable droplet appears in your account. Always verify VPC and SSH key settings match your security requirements.

Prompt

@digitalocean review my last 30 days of invoice line items and identify the top 3 cost drivers, then suggest rightsizing opportunities for underutilized resources

Output

Analyzed your November 2024 invoice ($847 total): Top 3 cost drivers: 1. Managed Databases (3 clusters) — $420 (49.6%) 2. Droplets (12 instances) — $288 (34.0%) 3. Load Balancers (2 active) — $72 (8.5%) Rightsizing opportunities: • db-prod-primary: Provisioned for 16GB RAM but averaging 38% utilization over 30 days. Downgrade from db-s-4vcpu-8gb ($120/mo) to db-s-2vcpu-4gb ($60/mo) could save $60/mo. • Droplets: 4 instances in nyc1 show <15% CPU usage. Consider consolidating workloads or switching to smaller sizes.

Notes

This synthesis example pairs billing data with AI reasoning to surface cost optimization insights. The MCP fetches invoice and monitoring metrics; the AI identifies patterns humans might miss. Recommendations are illustrative—always validate utilization data over longer windows and test downgrades in staging before production changes.

Use-case deep-dives

Dev environment spin-up for contractors

When DigitalOcean MCP beats manual provisioning for temp infra

A 6-person agency brings on two contract developers for a 3-month project. They need isolated staging environments that match production topology: a Droplet running the app, a managed Postgres cluster, and a firewall locking down SSH. The DigitalOcean MCP handles this in one Switchy thread—create the Droplet with the right region and size, provision the database cluster, wire up the firewall rules—without anyone opening the DO console. The contractor offboards in 90 days, and the same thread tears it all down. This works because the MCP exposes 47 tools covering the full provisioning surface, so you're not context-switching between chat and UI. If your team spins up fewer than one environment per quarter, the learning curve isn't worth it—just use the dashboard. But for agencies or consultancies doing this monthly, the MCP pays back in week two.

DNS cutover during site migration

Why this MCP is the right call for coordinated DNS changes

A 3-person SaaS team is migrating their marketing site from Vercel to a self-hosted Droplet to cut costs. The cutover window is Sunday morning: they need to create the new Droplet, import a custom Ubuntu image with their build baked in, then update four DNS records (A, CNAME, two TXT for email) to point at the new IP—all within 20 minutes to minimize downtime. The DigitalOcean MCP lets them script the entire sequence in a Switchy thread: provision the Droplet, confirm it's live, update the domain records in one pass. The alternative is toggling between SSH, the DO console, and a checklist in Notion, which doubles the error surface. The threshold: if you're only changing one or two records and have no other infra steps, the MCP is overkill. But for coordinated multi-step cutovers where timing matters, it's the difference between 18 minutes and 45.

Customer demo environment provisioning

When this MCP wins for on-demand trial infrastructure

A 10-person B2B startup gives enterprise prospects a private demo environment: a Kubernetes cluster running their app, a managed MySQL instance for sample data, and block storage for uploaded files. Sales closes 2-3 demos per week, and each environment lives for 7 days. Before the MCP, a backend engineer spent 30 minutes per demo clicking through the DO console—create the cluster, wait for it to provision, spin up the database, attach the volume. With the DigitalOcean MCP in Switchy, the sales engineer does it in a shared thread: specify the cluster config, database size, and volume, then hand off the endpoint URLs to the prospect. The engineer reviews the thread async and tears it down on day 8. This only makes sense if you're provisioning at least twice a month—otherwise the API key setup and tool familiarity aren't worth the overhead. But at 8+ demos per month, it's a 4-hour monthly time save.

Frequently asked

What can the DigitalOcean MCP do in Switchy?

The DigitalOcean MCP lets your team provision and manage DigitalOcean infrastructure directly from Switchy conversations. You can create Droplets, Kubernetes clusters, managed databases, block storage volumes, firewalls, DNS records, and custom images without leaving the workspace. It's useful when you need AI assistance to spin up dev environments or manage cloud resources through natural language instead of the control panel.

Do I need a DigitalOcean API token to connect this MCP?

Yes. You'll need to generate a personal access token from your DigitalOcean account settings with read and write permissions. The token authenticates all 47 tools in this MCP. Anyone on your Switchy team who connects it will need their own token — you can't share one token across multiple users. DigitalOcean doesn't use OAuth for API access, so token management is manual.

Can the DigitalOcean MCP delete or modify existing infrastructure?

No. This MCP only creates new resources — Droplets, databases, volumes, firewalls, DNS records, Kubernetes clusters, and custom images. It can't delete, resize, or reconfigure existing infrastructure. If you need to tear down resources or change settings on running services, use the DigitalOcean control panel or CLI directly. The MCP is designed for provisioning workflows, not full lifecycle management.

How is this different from using the DigitalOcean web console?

The MCP lets you describe what you need in plain language and have AI handle the API calls, including parameter validation and region checks. The web console requires you to click through forms and remember which regions support which services. Use the MCP when you're prototyping or want conversational guidance. Use the console when you need to monitor existing resources or perform operations this MCP doesn't support, like scaling or deletion.

Who on my team should connect the DigitalOcean MCP?

Whoever provisions infrastructure. Typically that's your DevOps engineer or backend developer who already has DigitalOcean API access. Each person needs their own API token, so don't connect it for team members who only need to view infrastructure status. The MCP creates billable resources in your DigitalOcean account, so limit access to people who understand your cloud budget and architecture decisions.

Data last verified 607 hours ago.Sources aggregated hourly to weekly. See docs/architecture/model-directory.md.