Skip to main content
Glama
dwin-gharibi

ArvanCloud MCP Server

by dwin-gharibi

arvan_provision_server

Automate server creation and initial setup on ArvanCloud with cloud-init, package installs, Docker, and custom scripts in one call.

Instructions

Provision a server and (optionally) configure it, in one call.

Supports several configuration methods (combine as needed):

  • init_script — cloud-init that runs at first boot (no SSH needed).

  • packages / install_docker / setup_script — run over SSH after boot (builds and runs a bash script). For Terraform-based provisioning use the arvan_iac_terraform_* tools; for Kubernetes use the arvan_k8s_* / arvan_helm_* tools.

Steps: register/generate an SSH key, create the server (optionally with cloud-init), wait for boot, detect its public IP, then SSH in and run the install script built from packages / install_docker / setup_script.

Args: name: Server name. flavor_id: Plan id (see arvan_list_plans). image_id: Image id (see arvan_list_images). region: Region; defaults to ARVAN_DEFAULT_REGION. disk_size: Root disk size (GB). networks: Network ids to attach (include a public network for SSH). security_group_names: Security groups to apply. ssh_public_key: Existing public key to inject. If omitted and generate_ssh_key is true, a new ed25519 keypair is generated and the private key is returned (store it securely!). ssh_key_name: Name to register the key under (default <name>-key). generate_ssh_key: Generate a keypair when no public key is given. ssh_user: SSH user for the install step (default ARVAN_SSH_USER/root). ssh_password: Use password auth for the install step instead of a key. packages: apt packages to install. install_docker: Install Docker via get.docker.com. setup_script: Extra shell commands to run after package install. wait_timeout: Max seconds to wait for boot + SSH availability. host_override: Use this IP/host for SSH instead of auto-detection.

Returns a summary with the server details, public IP, SSH info (incl. any generated private key), and install output.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nameYes
flavor_idYes
image_idYes
regionNo
disk_sizeNo
networksNo
security_group_namesNo
ssh_public_keyNo
ssh_key_nameNo
generate_ssh_keyNo
ssh_userNo
ssh_passwordNo
packagesNo
install_dockerNo
setup_scriptNo
init_scriptNo
wait_timeoutNo
host_overrideNo
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Discloses complete workflow: key generation, server creation, wait, SSH, install. Even warns 'store it securely!' about generated private key. All behaviors are transparent and consistent with annotations (readOnlyHint=false, etc.).

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Well-structured: summary, configuration methods, steps, then Args. Efficiently uses bullet points for methods and plain language for Args. No superfluous sentences despite high complexity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Covers all lifecycle details, dependencies (public network for SSH), return contents, and error cases. With 18 parameters and no output schema, the description provides a thorough mental model for correct invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 0% schema coverage, the description fully compensates by explaining each parameter's purpose and interplay (e.g., 'If omitted and generate_ssh_key is true, a new ed25519 keypair is generated'). References to arvan_list_plans add extra context.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Description precisely states 'Provision a server and (optionally) configure it, in one call', clearly distinguishing from Terraform and Kubernetes tools mentioned as alternatives. Verb 'provision' plus resource 'server' is specific and distinct from sibling tools like arvan_create_server.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly tells when to use this tool versus alternatives: 'For Terraform-based provisioning use the arvan_iac_terraform_* tools; for Kubernetes use the arvan_k8s_* / arvan_helm_* tools.' Also outlines steps and methods, giving clear guidance on context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/dwin-gharibi/arvancloud-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server